此 MCP 可以做什么
Provides structured reviews and searches of arXiv papers, including claims, premises, falsifiers, citations, reviewer assessments, and extracted evidence.
功能
工具
20
工具
analyze_paper_claims
Analyze a paper's claims, premises, and logical structure
The structured argument of one specific paper: what it actually
asserts, the premises it assumes, the machinery connecting those
premises to the claim, and the falsifier, as short labeled statements
in argument order (premise, machinery, claim, falsifier). Use this for
requests about a paper's claims, premises, assumptions, reasoning,
logical dependencies, logical structure, argument structure, or
conclusion. Each entry includes its text, role, type, and status.
只读
幂等
输入模式
{'type': 'object', 'title': 'analyze_paper_claimsArguments', 'required': ['arxiv_id'], 'properties': {'arxiv_id': {'type': 'string', 'title': 'Arxiv Id', 'description': 'Any form the user gave: bare arXiv id (2401.00001), arXiv abs/pdf URL, DOI or doi.org URL, or Pith Number.'}}}
输出模式
{'type': 'object', '$defs': {'Claim': {'type': 'object', 'title': 'Claim', 'required': ['claim_key', 'claim_role', 'claim_type', 'status', 'claim_text'], 'properties': {'status': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Status'}, 'claim_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Claim Key'}, 'claim_role': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Claim Role'}, 'claim_text': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Claim Text'}, 'claim_type': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Claim Type'}}}}, 'title': 'ClaimLedger', 'required': ['arxiv_id', 'title', 'count', 'claims', 'url', 'source_name', 'citation_url'], 'properties': {'url': {'type': 'string', 'title': 'Url'}, 'note': {'type': 'string', 'title': 'Note'}, 'count': {'type': 'integer', 'title': 'Count'}, 'title': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Title'}, 'claims': {'type': 'array', 'items': {'$ref': '#/$defs/Claim'}, 'title': 'Claims'}, 'arxiv_id': {'type': 'string', 'title': 'Arxiv Id'}, 'source_name': {'type': 'string', 'title': 'Source Name'}, 'citation_url': {'type': 'string', 'title': 'Citation Url'}}}
check_claim
Check a claim against the literature
Which arXiv papers support a scientific statement, which contradict
it, and which study it without deciding, each with the paper's own main
claim quoted and the classifier's probability. Call this before asserting a
scientific result, when a user asks whether something is established or
disputed, or when two sources disagree. Candidates are papers whose title
and abstract match the statement's words, plus papers Pith's connected
record links to them as stating the same or a conflicting result; a paper
that states the result in other words can be missed, so an empty answer
is not evidence of absence. Reported supporters and contradictions agreed
with two blind model families 110 times in 112
(https://pith.science/connected-record).
只读
可访问外部资源
幂等
输入模式
{'type': 'object', 'title': 'check_claimArguments', 'required': ['statement'], 'properties': {'limit': {'type': 'integer', 'title': 'Limit', 'default': 16, 'maximum': 24, 'minimum': 4, 'description': 'Candidate papers to judge. 4 to 24.'}, 'statement': {'type': 'string', 'title': 'Statement', 'description': 'One scientific statement in plain words, for example a result a user asserts or that you are about to assert.'}}}
输出模式
{'type': 'object', 'title': 'ClaimCheck', 'properties': {'bank': {'type': 'string', 'title': 'Bank'}, 'note': {'type': 'string', 'title': 'Note'}, 'found': {'type': 'boolean', 'title': 'Found'}, 'model': {'type': 'string', 'title': 'Model'}, 'method': {'type': 'string', 'title': 'Method'}, 'supports': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'title': 'Supports'}, 'addresses': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'title': 'Addresses'}, 'statement': {'type': 'string', 'title': 'Statement'}, 'candidates': {'type': 'integer', 'title': 'Candidates'}, 'contradicts': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'title': 'Contradicts'}, 'unrelated_count': {'type': 'integer', 'title': 'Unrelated Count'}, 'via_connected_record': {'type': 'integer', 'title': 'Via Connected Record'}}, 'description': 'Papers that support, contradict or address a statement.'}
citation_neighbors
One hop of the citation graph
One hop from a paper: every reference entry with its resolved work
identity, the papers that cite it, and, where a record exists, the
citing sentences with their labeled intent. An edge means the paper
names the other work, not that the work supports the citing claim.
只读
幂等
输入模式
{'type': 'object', 'title': 'citation_neighborsArguments', 'required': ['arxiv_id'], 'properties': {'limit': {'type': 'integer', 'title': 'Limit', 'default': 12, 'maximum': 40, 'minimum': 1, 'description': 'Graph rows per side. 1 to 40.'}, 'arxiv_id': {'type': 'string', 'title': 'Arxiv Id', 'description': 'Any form the user gave: bare arXiv id (2401.00001), arXiv abs/pdf URL, DOI or doi.org URL, or Pith Number.'}, 'direction': {'type': 'string', 'title': 'Direction', 'default': 'both', 'description': 'out: works this paper cites. in: papers that cite it. both.'}}}
输出模式
{'type': 'object', 'title': 'CitationNeighbors', 'required': ['ok'], 'properties': {'ok': {'type': 'boolean', 'title': 'Ok'}, 'error': {'type': 'string', 'title': 'Error'}, 'input': {'type': 'string', 'title': 'Input'}, 'arxiv_id': {'title': 'Arxiv Id'}, 'coverage': {'type': 'object', 'title': 'Coverage', 'additionalProperties': True}, 'resolved': {'type': 'boolean', 'title': 'Resolved'}, 'direction': {'type': 'string', 'title': 'Direction'}, 'from_graph': {'type': 'object', 'title': 'From Graph', 'additionalProperties': True}, 'empty_means': {'type': 'string', 'title': 'Empty Means'}, 'from_record': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'title': 'From Record'}}, 'description': 'One hop of the citation graph, record edges and graph edges kept apart.'}
find_passages
Find sentences by role across records
Author sentences the classifier labeled with one role, across every stored
record, each with its probability and paper. Abstract-tier records
cover limitation, result and main_claim; full-text records add
condition, citation and measurement.
只读
幂等
输入模式
{'type': 'object', 'title': 'find_passagesArguments', 'required': ['role'], 'properties': {'role': {'type': 'string', 'title': 'Role', 'description': 'limitation, condition, result, main_claim, citation, or measurement.'}, 'limit': {'type': 'integer', 'title': 'Limit', 'default': 20, 'maximum': 50, 'minimum': 1, 'description': '1 to 50.'}, 'query': {'type': 'string', 'title': 'Query', 'default': '', 'description': "Words to match in the author's sentence. Empty returns the role."}, 'arxiv_id': {'type': 'string', 'title': 'Arxiv Id', 'default': '', 'description': 'One paper, or empty for every stored record.'}}}
输出模式
{'type': 'object', 'title': 'Passages', 'required': ['ok'], 'properties': {'ok': {'type': 'boolean', 'title': 'Ok'}, 'role': {'type': 'string', 'title': 'Role'}, 'count': {'type': 'integer', 'title': 'Count'}, 'error': {'type': 'string', 'title': 'Error'}, 'input': {'type': 'string', 'title': 'Input'}, 'query': {'type': 'string', 'title': 'Query'}, 'matched': {'type': 'integer', 'title': 'Matched'}, 'arxiv_id': {'title': 'Arxiv Id'}, 'coverage': {'type': 'object', 'title': 'Coverage', 'additionalProperties': True}, 'passages': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'title': 'Passages'}, 'resolved': {'type': 'boolean', 'title': 'Resolved'}, 'empty_means': {'type': 'string', 'title': 'Empty Means'}}, 'description': "Author sentences of one role with the classifier's probabilities."}
get_claims
Get a paper's claim ledger
Alias of analyze_paper_claims: the same ledger of what the paper
asserts, its premises, machinery, and falsifier, in argument order.
只读
幂等
输入模式
{'type': 'object', 'title': 'get_claimsArguments', 'required': ['arxiv_id'], 'properties': {'arxiv_id': {'type': 'string', 'title': 'Arxiv Id', 'description': 'Any form the user gave: bare arXiv id (2401.00001), arXiv abs/pdf URL, DOI or doi.org URL, or Pith Number.'}}}
输出模式
{'type': 'object', '$defs': {'Claim': {'type': 'object', 'title': 'Claim', 'required': ['claim_key', 'claim_role', 'claim_type', 'status', 'claim_text'], 'properties': {'status': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Status'}, 'claim_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Claim Key'}, 'claim_role': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Claim Role'}, 'claim_text': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Claim Text'}, 'claim_type': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Claim Type'}}}}, 'title': 'ClaimLedger', 'required': ['arxiv_id', 'title', 'count', 'claims', 'url', 'source_name', 'citation_url'], 'properties': {'url': {'type': 'string', 'title': 'Url'}, 'note': {'type': 'string', 'title': 'Note'}, 'count': {'type': 'integer', 'title': 'Count'}, 'title': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Title'}, 'claims': {'type': 'array', 'items': {'$ref': '#/$defs/Claim'}, 'title': 'Claims'}, 'arxiv_id': {'type': 'string', 'title': 'Arxiv Id'}, 'source_name': {'type': 'string', 'title': 'Source Name'}, 'citation_url': {'type': 'string', 'title': 'Citation Url'}}}
get_falsifier
Get a paper's falsifier
Alias of get_paper_falsifier: the same falsifier and watcher count.
只读
幂等
输入模式
{'type': 'object', 'title': 'get_falsifierArguments', 'required': ['arxiv_id'], 'properties': {'arxiv_id': {'type': 'string', 'title': 'Arxiv Id', 'description': 'Any form the user gave: bare arXiv id (2401.00001), arXiv abs/pdf URL, DOI or doi.org URL, or Pith Number.'}}}
输出模式
{'type': 'object', 'title': 'Falsifier', 'required': ['found', 'arxiv_id'], 'properties': {'url': {'type': 'string', 'title': 'Url'}, 'found': {'type': 'boolean', 'title': 'Found'}, 'title': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Title'}, 'arxiv_id': {'type': 'string', 'title': 'Arxiv Id'}, 'watchers': {'type': 'integer', 'title': 'Watchers'}, 'falsifier': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Falsifier'}, 'watch_url': {'type': 'string', 'title': 'Watch Url'}, 'source_name': {'type': 'string', 'title': 'Source Name'}, 'citation_url': {'type': 'string', 'title': 'Citation Url'}}}
get_paper_falsifier
Get the test or result that could disprove a paper
The falsifier for one specific paper's core claim: the concrete
observation, experiment, or computation that would settle or disprove
it, plus how many people are watching for that result. Use this when the
user asks what would falsify the paper, prove it wrong, test its central
claim, settle the claim, or show that the conclusion fails.
只读
幂等
输入模式
{'type': 'object', 'title': 'get_paper_falsifierArguments', 'required': ['arxiv_id'], 'properties': {'arxiv_id': {'type': 'string', 'title': 'Arxiv Id', 'description': 'Any form the user gave: bare arXiv id (2401.00001), arXiv abs/pdf URL, DOI or doi.org URL, or Pith Number.'}}}
输出模式
{'type': 'object', 'title': 'Falsifier', 'required': ['found', 'arxiv_id'], 'properties': {'url': {'type': 'string', 'title': 'Url'}, 'found': {'type': 'boolean', 'title': 'Found'}, 'title': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Title'}, 'arxiv_id': {'type': 'string', 'title': 'Arxiv Id'}, 'watchers': {'type': 'integer', 'title': 'Watchers'}, 'falsifier': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Falsifier'}, 'watch_url': {'type': 'string', 'title': 'Watch Url'}, 'source_name': {'type': 'string', 'title': 'Source Name'}, 'citation_url': {'type': 'string', 'title': 'Citation Url'}}}
get_record
Get a paper's compiled record
The compiled record of one paper: the authors' own sentences, arranged
with typed labels. It carries the main claim in the authors' words, each
abstract sentence's role, results with the qualifications the authors
state beside them, the conditions of the study, measurements with where
they appear, the arXiv listing abstract compared with the manuscript's
abstract, resources including what is not stated, the authors' own
limitations, how the paper uses its references, and what was and was not
examined. No sentence in it was written by a model; every label carries
its probability. Use this for what a paper states and under what
conditions, including papers Pith has not reviewed, where get_review
reports no review. Accepts an arXiv id or URL, DOI, or Pith Number.
只读
幂等
输入模式
{'type': 'object', 'title': 'get_recordArguments', 'required': ['arxiv_id'], 'properties': {'arxiv_id': {'type': 'string', 'title': 'Arxiv Id', 'description': 'Any form the user gave: bare arXiv id (2401.00001), arXiv abs/pdf URL, DOI or doi.org URL, or Pith Number.'}}}
输出模式
{'type': 'object', 'title': 'CompiledRecord', 'required': ['found'], 'properties': {'url': {'type': 'string', 'title': 'Url'}, 'note': {'type': 'string', 'title': 'Note'}, 'found': {'type': 'boolean', 'title': 'Found'}, 'record': {'type': 'object', 'title': 'Record', 'additionalProperties': True}, 'arxiv_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Arxiv Id'}, 'coverage': {'type': 'string', 'title': 'Coverage'}, 'record_url': {'type': 'string', 'title': 'Record Url'}, 'source_name': {'type': 'string', 'title': 'Source Name'}, 'citation_url': {'type': 'string', 'title': 'Citation Url'}, 'labels_illustrative': {'type': 'boolean', 'title': 'Labels Illustrative'}}, 'description': "A paper's compiled record: the authors' sentences with typed labels."}
get_review
Get a paper's Pith review
Pith's review of one specific paper, in one call: the verdict,
confidence, novelty and correctness scores, one-line summary, weakest
assumption, and the paper's argument as short labeled statements
(premise, machinery, core claim, falsifier) already extracted, so the
paper's premises and logical structure can be stated without reading
the PDF. Use this for any question about a specific paper: what it
asserts, what it assumes, how the argument runs, how sound it is, or
what Pith concluded. Accepts an arXiv id or URL, DOI, or Pith Number.
只读
幂等
输入模式
{'type': 'object', 'title': 'get_reviewArguments', 'required': ['arxiv_id'], 'properties': {'arxiv_id': {'type': 'string', 'title': 'Arxiv Id', 'description': 'Any form the user gave: bare arXiv id (2401.00001), arXiv abs/pdf URL, DOI or doi.org URL, or Pith Number.'}}}
输出模式
{'type': 'object', '$defs': {'Claim': {'type': 'object', 'title': 'Claim', 'required': ['claim_key', 'claim_role', 'claim_type', 'status', 'claim_text'], 'properties': {'status': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Status'}, 'claim_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Claim Key'}, 'claim_role': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Claim Role'}, 'claim_text': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Claim Text'}, 'claim_type': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Claim Type'}}}}, 'title': 'Review', 'required': ['found'], 'properties': {'url': {'type': 'string', 'title': 'Url'}, 'lead': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Lead'}, 'note': {'type': 'string', 'title': 'Note'}, 'found': {'type': 'boolean', 'title': 'Found'}, 'title': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Title'}, 'verdict': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Verdict'}, 'argument': {'type': 'array', 'items': {'$ref': '#/$defs/Claim'}, 'title': 'Argument'}, 'arxiv_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Arxiv Id'}, 'falsifier': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Falsifier'}, 'confidence': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Confidence'}, 'core_claim': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Core Claim'}, 'primary_cat': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Primary Cat'}, 'reviewed_at': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Reviewed At'}, 'source_name': {'type': 'string', 'title': 'Source Name'}, 'citation_url': {'type': 'string', 'title': 'Citation Url'}, 'submitted_at': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Submitted At'}, 'novelty_score': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Novelty Score'}, 'discovery_kind': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Discovery Kind'}, 'correctness_risk': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Correctness Risk'}, 'one_line_summary': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'One Line Summary'}, 'weakest_assumption': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Weakest Assumption'}}, 'description': "One paper's full machine review."}
get_reviewer_record
Get a reviewer's record
A reviewer's published signed reviews and, when present, their
calibration record (Brier score, open predictions, positivity skew).
Call this when the user asks about a named Pith reviewer or how
trustworthy a reviewer's track record is.
只读
幂等
输入模式
{'type': 'object', 'title': 'get_reviewer_recordArguments', 'required': ['handle'], 'properties': {'handle': {'type': 'string', 'title': 'Handle'}}}
输出模式
{'type': 'object', 'title': 'ReviewerRecord', 'required': ['handle', 'found'], 'properties': {'url': {'type': 'string', 'title': 'Url'}, 'error': {'type': 'string', 'title': 'Error'}, 'found': {'type': 'boolean', 'title': 'Found'}, 'handle': {'type': 'string', 'title': 'Handle'}, 'record': {'title': 'Record'}, 'reviews': {'type': 'array', 'items': {}, 'title': 'Reviews'}}}
get_signed_reviews
Get a paper's signed human reviews
Published human signed reviews of one paper: reviewer identity, axis
deltas against the machine review, claim verdicts, defects, predictions,
and who paid. Call this when the user asks what human experts said about
a paper, on top of the machine review.
只读
幂等
输入模式
{'type': 'object', 'title': 'get_signed_reviewsArguments', 'required': ['arxiv_id'], 'properties': {'arxiv_id': {'type': 'string', 'title': 'Arxiv Id', 'description': 'Any form the user gave: bare arXiv id (2401.00001), arXiv abs/pdf URL, DOI or doi.org URL, or Pith Number.'}}}
输出模式
{'type': 'object', 'title': 'SignedReviews', 'required': ['arxiv_id', 'count', 'reviews'], 'properties': {'url': {'type': 'string', 'title': 'Url'}, 'count': {'type': 'integer', 'title': 'Count'}, 'error': {'type': 'string', 'title': 'Error'}, 'reviews': {'type': 'array', 'items': {}, 'title': 'Reviews'}, 'arxiv_id': {'type': 'string', 'title': 'Arxiv Id'}}}
latest_reviews
List recently reviewed papers
The papers Pith reviewed most recently, newest first. Call this when
the user asks what is new, notable, or recently reviewed in a field or
overall. days caps how far back to look (max 90).
只读
幂等
输入模式
{'type': 'object', 'title': 'latest_reviewsArguments', 'properties': {'days': {'type': 'integer', 'title': 'Days', 'default': 7}, 'limit': {'type': 'integer', 'title': 'Limit', 'default': 10}, 'category': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Category', 'default': None, 'description': "Field to filter by: an arXiv archive ('cond-mat'), a full category ('cond-mat.str-el'), or a plain field name like 'condensed matter' or 'machine learning'; omit for all fields."}}}
输出模式
{'type': 'object', '$defs': {'ReviewedPaper': {'type': 'object', 'title': 'ReviewedPaper', 'required': ['arxiv_id', 'title', 'primary_cat', 'submitted_at', 'verdict', 'one_line_summary', 'url', 'source_name', 'citation_url', 'reviewed_at'], 'properties': {'url': {'type': 'string', 'title': 'Url'}, 'title': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Title'}, 'verdict': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Verdict'}, 'arxiv_id': {'type': 'string', 'title': 'Arxiv Id'}, 'primary_cat': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Primary Cat'}, 'reviewed_at': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Reviewed At'}, 'source_name': {'type': 'string', 'title': 'Source Name'}, 'citation_url': {'type': 'string', 'title': 'Citation Url'}, 'submitted_at': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Submitted At'}, 'one_line_summary': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'One Line Summary'}}}}, 'title': 'LatestReviews', 'required': ['category', 'days', 'count', 'results'], 'properties': {'days': {'type': 'integer', 'title': 'Days'}, 'note': {'type': 'string', 'title': 'Note'}, 'count': {'type': 'integer', 'title': 'Count'}, 'results': {'type': 'array', 'items': {'$ref': '#/$defs/ReviewedPaper'}, 'title': 'Results'}, 'category': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Category'}}}
paper_bridge
What two papers share
Whether either paper cites the other, the resolved works both cite
(on or off arXiv), and the papers that cite both.
只读
幂等
输入模式
{'type': 'object', 'title': 'paper_bridgeArguments', 'required': ['a', 'b'], 'properties': {'a': {'type': 'string', 'title': 'A', 'description': 'Any form the user gave: bare arXiv id (2401.00001), arXiv abs/pdf URL, DOI or doi.org URL, or Pith Number.'}, 'b': {'type': 'string', 'title': 'B', 'description': 'Any form the user gave: bare arXiv id (2401.00001), arXiv abs/pdf URL, DOI or doi.org URL, or Pith Number.'}, 'limit': {'type': 'integer', 'title': 'Limit', 'default': 12, 'maximum': 40, 'minimum': 1, 'description': 'Shared graph neighbors per side. 1 to 40.'}}}
输出模式
{'type': 'object', 'title': 'PaperBridge', 'required': ['ok'], 'properties': {'a': {'type': 'string', 'title': 'A'}, 'b': {'type': 'string', 'title': 'B'}, 'ok': {'type': 'boolean', 'title': 'Ok'}, 'error': {'type': 'string', 'title': 'Error'}, 'input': {'type': 'string', 'title': 'Input'}, 'direct': {'type': 'object', 'title': 'Direct', 'additionalProperties': True}, 'arxiv_id': {'title': 'Arxiv Id'}, 'coverage': {'type': 'object', 'title': 'Coverage', 'additionalProperties': True}, 'resolved': {'type': 'boolean', 'title': 'Resolved'}, 'from_graph': {'type': 'object', 'title': 'From Graph', 'additionalProperties': True}, 'empty_means': {'type': 'string', 'title': 'Empty Means'}, 'shared_citation_labels': {'type': 'array', 'items': {'type': 'string'}, 'title': 'Shared Citation Labels'}, 'shared_relation_candidates': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'title': 'Shared Relation Candidates'}}, 'description': 'What two papers share, each list on its own identity.'}
paper_connections
How papers use this one
What other arXiv papers do with this paper, and what it does with the
arXiv papers it cites: builds on, uses the method or tool, uses the data,
compares with, cites as support or background, or contests. Each group
counts distinct papers and quotes the citing authors' own sentences.
Labels come from each citing paper's LaTeX source typed by Pith's classifier and are
shown only at intent probability 0.8 or more (contests at 0.7 or more);
the rest are counted as unlabelled. Measured agreement of every label with
independent model families: https://pith.science/connected-record. Use this
for how a result has been taken up, challenged or built on across arXiv.
只读
幂等
输入模式
{'type': 'object', 'title': 'paper_connectionsArguments', 'required': ['arxiv_id'], 'properties': {'quotes': {'type': 'integer', 'title': 'Quotes', 'default': 5, 'maximum': 20, 'minimum': 1, 'description': 'Quoted sentences per group. 1 to 20.'}, 'arxiv_id': {'type': 'string', 'title': 'Arxiv Id', 'description': 'Any form the user gave: bare arXiv id (2401.00001), arXiv abs/pdf URL, DOI or doi.org URL, or Pith Number.'}}}
输出模式
{'type': 'object', 'title': 'PaperConnections', 'properties': {'url': {'type': 'string', 'title': 'Url'}, 'note': {'type': 'string', 'title': 'Note'}, 'found': {'type': 'boolean', 'title': 'Found'}, 'method': {'type': 'string', 'title': 'Method'}, 'arxiv_id': {'type': 'string', 'title': 'Arxiv Id'}, 'incoming': {'type': 'object', 'title': 'Incoming', 'additionalProperties': True}, 'outgoing': {'type': 'object', 'title': 'Outgoing', 'additionalProperties': True}, 'thresholds': {'type': 'object', 'title': 'Thresholds', 'additionalProperties': {'type': 'number'}}}, 'description': 'How the literature uses one paper, and how it uses what it cites.'}
paper_packet
Read one paper's record packet
One paper's compiled record, small enough to hold beside others: the
main claim and contribution in the authors' words, each abstract
sentence with its role and probability, paper-level labels, and, for
full-text records, conditions, measurements, results and limitations,
with totals so a capped list is not mistaken for the whole paper.
只读
幂等
输入模式
{'type': 'object', 'title': 'paper_packetArguments', 'required': ['arxiv_id'], 'properties': {'limit': {'type': 'integer', 'title': 'Limit', 'default': 8, 'maximum': 20, 'minimum': 1, 'description': 'Items per list. 1 to 20.'}, 'arxiv_id': {'type': 'string', 'title': 'Arxiv Id', 'description': 'Any form the user gave: bare arXiv id (2401.00001), arXiv abs/pdf URL, DOI or doi.org URL, or Pith Number.'}}}
输出模式
{'type': 'object', 'title': 'PaperPacket', 'required': ['ok'], 'properties': {'ok': {'type': 'boolean', 'title': 'Ok'}, 'doi': {'title': 'Doi'}, 'error': {'type': 'string', 'title': 'Error'}, 'found': {'type': 'boolean', 'title': 'Found'}, 'input': {'type': 'string', 'title': 'Input'}, 'title': {'title': 'Title'}, 'counts': {'type': 'object', 'title': 'Counts', 'additionalProperties': True}, 'packet': {'title': 'Packet'}, 'results': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'title': 'Results'}, 'abstract': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'title': 'Abstract'}, 'arxiv_id': {'title': 'Arxiv Id'}, 'coverage': {'type': 'object', 'title': 'Coverage', 'additionalProperties': True}, 'resolved': {'type': 'boolean', 'title': 'Resolved'}, 'resources': {'type': 'object', 'title': 'Resources', 'additionalProperties': True}, 'conditions': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'title': 'Conditions'}, 'main_claim': {'title': 'Main Claim'}, 'record_url': {'type': 'string', 'title': 'Record Url'}, 'empty_means': {'type': 'string', 'title': 'Empty Means'}, 'limitations': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'title': 'Limitations'}, 'contribution': {'title': 'Contribution'}, 'measurements': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'title': 'Measurements'}, 'paper_labels': {'type': 'object', 'title': 'Paper Labels', 'additionalProperties': True}}, 'description': "One paper's compiled record: authors' sentences with the classifier's labels and probabilities."}
record_coverage
What was examined
Sources read and levels run for one paper's record, or the number of
stored records by tier. Call before treating an empty result as a
finding: an empty list means nothing in the examined scope matched.
只读
幂等
输入模式
{'type': 'object', 'title': 'record_coverageArguments', 'properties': {'arxiv_id': {'type': 'string', 'title': 'Arxiv Id', 'default': '', 'description': 'One paper, or empty for the whole record store.'}}}
输出模式
{'type': 'object', 'title': 'RecordCoverage', 'required': ['ok'], 'properties': {'ok': {'type': 'boolean', 'title': 'Ok'}, 'tier': {'title': 'Tier'}, 'error': {'type': 'string', 'title': 'Error'}, 'found': {'type': 'boolean', 'title': 'Found'}, 'input': {'type': 'string', 'title': 'Input'}, 'papers': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'title': 'Papers'}, 'arxiv_id': {'title': 'Arxiv Id'}, 'coverage': {'type': 'object', 'title': 'Coverage', 'additionalProperties': True}, 'resolved': {'type': 'boolean', 'title': 'Resolved'}, 'levels_run': {'type': 'array', 'items': {}, 'title': 'Levels Run'}, 'empty_means': {'type': 'string', 'title': 'Empty Means'}, 'not_examined': {'type': 'array', 'items': {}, 'title': 'Not Examined'}, 'sources_read': {'type': 'array', 'items': {}, 'title': 'Sources Read'}, 'levels_not_run': {'type': 'array', 'items': {}, 'title': 'Levels Not Run'}, 'citations_total': {'title': 'Citations Total'}, 'compiled_records': {'type': 'integer', 'title': 'Compiled Records'}, 'relation_candidates': {'title': 'Relation Candidates'}, 'stored_records_total': {'title': 'Stored Records Total'}, 'citations_with_intent': {'title': 'Citations With Intent'}, 'stored_records_by_tier': {'title': 'Stored Records By Tier'}, 'relation_candidates_judged': {'title': 'Relation Candidates Judged'}}, 'description': 'What a record examined, or how many records are stored.'}
resolve_paper
Resolve a paper reference
Turn a pasted arXiv id, arXiv URL, DOI, or Pith Number into the
arXiv id the other tools key on. ``resolved`` is false when the input
did not become an arXiv id.
只读
幂等
输入模式
{'type': 'object', 'title': 'resolve_paperArguments', 'required': ['reference'], 'properties': {'reference': {'type': 'string', 'title': 'Reference', 'description': 'Any form the user gave: bare arXiv id (2401.00001), arXiv abs/pdf URL, DOI or doi.org URL, or Pith Number.'}}}
输出模式
{'type': 'object', 'title': 'ResolvedPaper', 'required': ['ok'], 'properties': {'ok': {'type': 'boolean', 'title': 'Ok'}, 'error': {'type': 'string', 'title': 'Error'}, 'input': {'type': 'string', 'title': 'Input'}, 'arxiv_id': {'title': 'Arxiv Id'}, 'resolved': {'type': 'boolean', 'title': 'Resolved'}, 'empty_means': {'type': 'string', 'title': 'Empty Means'}}, 'description': 'A pasted reference turned into the arXiv id the other tools key on.'}
search_claims
Search extracted claims
Full-text search over every scientific claim Pith has extracted,
across all reviewed papers. Call this when the user asks who claims
something, whether a claim appears in the recent literature, or what
evidence bears on a statement. Returns each matching claim with its
paper, verdict, and review link.
只读
幂等
输入模式
{'type': 'object', 'title': 'search_claimsArguments', 'required': ['query'], 'properties': {'limit': {'type': 'integer', 'title': 'Limit', 'default': 10}, 'query': {'type': 'string', 'title': 'Query', 'description': 'The claim or statement to look for, in plain words.'}}}
输出模式
{'type': 'object', '$defs': {'ClaimHit': {'type': 'object', 'title': 'ClaimHit', 'required': ['arxiv_id', 'claim_role', 'claim_text', 'title', 'verdict', 'url', 'source_name', 'citation_url'], 'properties': {'url': {'type': 'string', 'title': 'Url'}, 'title': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Title'}, 'verdict': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Verdict'}, 'arxiv_id': {'type': 'string', 'title': 'Arxiv Id'}, 'claim_role': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Claim Role'}, 'claim_text': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Claim Text'}, 'source_name': {'type': 'string', 'title': 'Source Name'}, 'citation_url': {'type': 'string', 'title': 'Citation Url'}}}}, 'title': 'ClaimSearchResults', 'required': ['query', 'count', 'results'], 'properties': {'note': {'type': 'string', 'title': 'Note'}, 'count': {'type': 'integer', 'title': 'Count'}, 'query': {'type': 'string', 'title': 'Query'}, 'results': {'type': 'array', 'items': {'$ref': '#/$defs/ClaimHit'}, 'title': 'Results'}}}
search_papers
Search reviewed papers
Search Pith-reviewed papers by title and abstract. Call this when the
user names a research topic, phenomenon, method, or paper title without
an identifier, or asks whether Pith has reviewed anything on a subject.
Each result carries the paper's verdict, summary, and review link.
只读
幂等
输入模式
{'type': 'object', 'title': 'search_papersArguments', 'required': ['query'], 'properties': {'limit': {'type': 'integer', 'title': 'Limit', 'default': 10}, 'query': {'type': 'string', 'title': 'Query', 'description': 'Topic, phenomenon, method, or paper title in plain words.'}}}
输出模式
{'type': 'object', '$defs': {'PaperHit': {'type': 'object', 'title': 'PaperHit', 'required': ['arxiv_id', 'title', 'primary_cat', 'submitted_at', 'verdict', 'one_line_summary', 'url', 'source_name', 'citation_url'], 'properties': {'url': {'type': 'string', 'title': 'Url'}, 'title': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Title'}, 'verdict': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Verdict'}, 'arxiv_id': {'type': 'string', 'title': 'Arxiv Id'}, 'primary_cat': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Primary Cat'}, 'source_name': {'type': 'string', 'title': 'Source Name'}, 'citation_url': {'type': 'string', 'title': 'Citation Url'}, 'submitted_at': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Submitted At'}, 'one_line_summary': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'One Line Summary'}}}}, 'title': 'PaperSearchResults', 'required': ['query', 'count', 'results'], 'properties': {'note': {'type': 'string', 'title': 'Note'}, 'count': {'type': 'integer', 'title': 'Count'}, 'query': {'type': 'string', 'title': 'Query'}, 'results': {'type': 'array', 'items': {'$ref': '#/$defs/PaperHit'}, 'title': 'Results'}}}
verify_citation
Verify that a paper supports a sentence
Whether the cited paper's own sentences support what a sentence
attributes to it: supports, partly supports (a condition is missing),
contradicts, or not addressed, with the single best sentence from the
paper quoted. Call this before citing a paper for a specific claim, or to
check a citation in a draft or an answer. It reads the paper's abstract,
and its full text where Pith holds it; the examined field says which. On
real citations its verdict agreed with two blind model families 139 times
in 160, most differences being partly supported versus not addressed
(https://pith.science/connected-record).
只读
可访问外部资源
幂等
输入模式
{'type': 'object', 'title': 'verify_citationArguments', 'required': ['sentence', 'cited'], 'properties': {'cited': {'type': 'string', 'title': 'Cited', 'description': 'Any form the user gave: bare arXiv id (2401.00001), arXiv abs/pdf URL, DOI or doi.org URL, or Pith Number.'}, 'sentence': {'type': 'string', 'title': 'Sentence', 'description': 'The sentence that cites the paper, as written in a draft, an answer or a paper.'}}}
输出模式
{'type': 'object', 'title': 'CitationCheck', 'properties': {'url': {'type': 'string', 'title': 'Url'}, 'bank': {'type': 'string', 'title': 'Bank'}, 'note': {'type': 'string', 'title': 'Note'}, 'cited': {'type': 'string', 'title': 'Cited'}, 'found': {'type': 'boolean', 'title': 'Found'}, 'model': {'type': 'string', 'title': 'Model'}, 'method': {'type': 'string', 'title': 'Method'}, 'verdict': {'type': 'string', 'title': 'Verdict'}, 'arxiv_id': {'type': 'string', 'title': 'Arxiv Id'}, 'examined': {'type': 'string', 'title': 'Examined'}, 'sentence': {'type': 'string', 'title': 'Sentence'}, 'best_evidence': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Best Evidence'}, 'probabilities': {'type': 'object', 'title': 'Probabilities', 'additionalProperties': {'type': 'number'}}, 'best_evidence_p': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Best Evidence P'}, 'evidence_sentences': {'type': 'integer', 'title': 'Evidence Sentences'}}, 'description': "Whether a cited paper's own sentences support a sentence."}
历史
近期工具变更
已更改
find_passages
2026年9月27日 02:41
已添加
verify_citation
2026年9月27日 02:41
已添加
check_claim
2026年9月27日 02:41
已添加
paper_connections
2026年9月27日 02:41
已更改
paper_packet
2026年9月27日 02:41
已添加
record_coverage
2026年9月25日 02:40
已添加
find_passages
2026年9月25日 02:40
已添加
paper_bridge
2026年9月25日 02:40
已添加
citation_neighbors
2026年9月25日 02:40
已添加
paper_packet
2026年9月25日 02:40
已添加
resolve_paper
2026年9月25日 02:40
已添加
get_record
2026年9月25日 02:40
已添加
get_reviewer_record
2026年9月25日 02:40
已添加
get_signed_reviews
2026年9月25日 02:40
已添加
get_falsifier
2026年9月25日 02:40
已添加
get_paper_falsifier
2026年9月25日 02:40
已添加
search_claims
2026年9月25日 02:40
已添加
get_claims
2026年9月25日 02:40
已添加
analyze_paper_claims
2026年9月25日 02:40
已添加
latest_reviews
2026年9月25日 02:40
已添加
search_papers
2026年9月25日 02:40
已添加
get_review
2026年9月25日 02:40
发现
类似的 MCP 服务器
osint
build.exascale/osint
Provides source-cited US data and schemas for power systems, AI infrastructure, semiconductor production and trade, robotics, and…
Pubmed
io.github.pipeworx-io/pubmed
Provides PubMed biomedical literature search and retrieval, including abstracts, full text where available, citation metadata, re…
Europepmc
io.github.pipeworx-io/europepmc
Searches and retrieves biomedical literature from Europe PMC, including abstracts, full records, citations, publication metadata,…
Nasa
io.github.pipeworx-io/nasa
Provides NASA data and imagery for astronomy, asteroids, Mars rover photos, solar flares, coronal mass ejections, geomagnetic sto…
Nih Reporter
io.github.pipeworx-io/nih-reporter
Searches and analyzes NIH-funded research projects, awards, publications, funding trends, expirations, investigators, organizatio…
Catalogueoflife
io.github.pipeworx-io/catalogueoflife
Provides taxonomic search and classification for species and higher taxa using the Catalogue of Life.
Chembl
io.github.pipeworx-io/chembl
Queries the ChEMBL drug-discovery database for molecules, mechanisms of action, indications, targets, and small-molecule bioactiv…
Biorxiv
io.github.pipeworx-io/biorxiv
Provides bioRxiv and medRxiv preprint metadata, publication status, and publisher lookups, alongside broader structured research …