← The evidence ledger
Evidence row 307517
Observed , by probe.mcp/1.
- Kind
- mcp.tools
- About
- endpoint d2f250dc-b08d-4445-873e-b8c73bb9d882
- Recorded
- Previous row
- None: the first of its kind about this subject
- Body SHA-256
- 6bc92def171091ca6a96c799bc9abb136ade20489f866faafc519440edd92145
- Leaf
- 0x5112fe58806df0d7873b995c25772f9e95fc2ca0e3ad48160e64bad499b9cce9
What was observed
{
"count": 24,
"tools": [
{
"description": "The structured argument of one specific paper: what it actually\n asserts, the premises it assumes, the machinery connecting those\n premises to the claim, and the falsifier, as short labeled statements\n in argument order (premise, machinery, claim, falsifier). Use this for\n requests about a paper's claims, premises, assumptions, reasoning,\n logical dependencies, logical structure, argument structure, or\n conclusion. Each entry includes its text, role, type, and status.",
"inputSchema": {
"properties": {
"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.",
"title": "Arxiv Id",
"type": "string"
}
},
"required": [
"arxiv_id"
],
"title": "analyze_paper_claimsArguments",
"type": "object"
},
"name": "analyze_paper_claims"
},
{
"description": "Read the papers closest to a question and return, for each, whether its\n own abstract sentences answer yes, no or not addressed, with the deciding\n sentence quoted. Call when a user asks whether something holds across the\n literature. Candidates are chosen by meaning, so a paper that answers in\n different words can be missed. Needs a personal key; counts against a daily\n allowance.",
"inputSchema": {
"properties": {
"field": {
"default": "",
"description": "Optional arXiv category such as gr-qc or math.CO; empty for all fields.",
"title": "Field",
"type": "string"
},
"question": {
"description": "A yes-or-no question the literature could answer.",
"maxLength": 600,
"minLength": 15,
"title": "Question",
"type": "string"
}
},
"required": [
"question"
],
"title": "ask_fieldArguments",
"type": "object"
},
"name": "ask_field"
},
{
"description": "Which arXiv papers support a scientific statement, which contradict\n it, and which study it without deciding, each with the paper's own main\n claim quoted and the classifier's probability. Call this before asserting a\n scientific result, when a user asks whether something is established or\n disputed, or when two sources disagree. Candidates are papers whose title\n and abstract match the statement's words, plus papers Pith's connected\n record links to them as stating the same or a conflicting result; a paper\n that states the result in other words can be missed, so an empty answer\n is not evidence of absence. Reported supporters and contradictions agreed\n with two blind model families 110 times in 112\n (https://pith.science/connected-record).",
"inputSchema": {
"properties": {
"limit": {
"default": 16,
"description": "Candidate papers to judge. 4 to 24.",
"maximum": 24,
"minimum": 4,
"title": "Limit",
"type": "integer"
},
"statement": {
"description": "One scientific statement in plain words, for example a result a user asserts or that you are about to assert.",
"title": "Statement",
"type": "string"
}
},
"required": [
"statement"
],
"title": "check_claimArguments",
"type": "object"
},
"name": "check_claim"
},
{
"description": "Resolve each reference in a draft, flag retracted works, and for arXiv\n papers show how later papers cite them: as support, and whether any\n contest them, with the contesting sentence quoted. Call before a\n submission or when a user wants their reference list checked. Needs a\n personal key; counts against a daily allowance.",
"inputSchema": {
"properties": {
"text": {
"description": "The draft's reference list: BibTeX, a LaTeX bibliography or plain reference lines.",
"maxLength": 200000,
"minLength": 20,
"title": "Text",
"type": "string"
}
},
"required": [
"text"
],
"title": "check_my_draftArguments",
"type": "object"
},
"name": "check_my_draft"
},
{
"description": "One hop from a paper: every reference entry with its resolved work\n identity, the papers that cite it, and, where a record exists, the\n citing sentences with their labeled intent. An edge means the paper\n names the other work, not that the work supports the citing claim.",
"inputSchema": {
"properties": {
"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.",
"title": "Arxiv Id",
"type": "string"
},
"direction": {
"default": "both",
"description": "out: works this paper cites. in: papers that cite it. both.",
"title": "Direction",
"type": "string"
},
"limit": {
"default": 12,
"description": "Graph rows per side. 1 to 40.",
"maximum": 40,
"minimum": 1,
"title": "Limit",
"type": "integer"
}
},
"required": [
"arxiv_id"
],
"title": "citation_neighborsArguments",
"type": "object"
},
"name": "citation_neighbors"
},
{
"description": "Author sentences the classifier labeled with one role, across every stored\n record, each with its probability and paper. Abstract-tier records\n cover limitation, result and main_claim; full-text records add\n condition, citation and measurement.",
"inputSchema": {
"properties": {
"arxiv_id": {
"default": "",
"description": "One paper, or empty for every stored record.",
"title": "Arxiv Id",
"type": "string"
},
"limit": {
"default": 20,
"description": "1 to 50.",
"maximum": 50,
"minimum": 1,
"title": "Limit",
"type": "integer"
},
"query": {
"default": "",
"description": "Words to match in the author's sentence. Empty returns the role.",
"title": "Query",
"type": "string"
},
"role": {
"description": "limitation, condition, result, main_claim, citation, or measurement.",
"title": "Role",
"type": "string"
}
},
"required": [
"role"
],
"title": "find_passagesArguments",
"type": "object"
},
"name": "find_passages"
},
{
"description": "Alias of analyze_paper_claims: the same ledger of what the paper\n asserts, its premises, machinery, and falsifier, in argument order.",
"inputSchema": {
"properties": {
"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.",
"title": "Arxiv Id",
"type": "string"
}
},
"required": [
"arxiv_id"
],
"title": "get_claimsArguments",
"type": "object"
},
"name": "get_claims"
},
{
"description": "Alias of get_paper_falsifier: the same falsifier and watcher count.",
"inputSchema": {
"properties": {
"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.",
"title": "Arxiv Id",
"type": "string"
}
},
"required": [
"arxiv_id"
],
"title": "get_falsifierArguments",
"type": "object"
},
"name": "get_falsifier"
},
{
"description": "The falsifier for one specific paper's core claim: the concrete\n observation, experiment, or computation that would settle or disprove\n it, plus how many people are watching for that result. Use this when the\n user asks what would falsify the paper, prove it wrong, test its central\n claim, settle the claim, or show that the conclusion fails.",
"inputSchema": {
"properties": {
"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.",
"title": "Arxiv Id",
"type": "string"
}
},
"required": [
"arxiv_id"
],
"title": "get_paper_falsifierArguments",
"type": "object"
},
"name": "get_paper_falsifier"
},
{
"description": "The compiled record of one paper: the authors' own sentences, arranged\n with typed labels. It carries the main claim in the authors' words, each\n abstract sentence's role, results with the qualifications the authors\n state beside them, the conditions of the study, measurements with where\n they appear, the arXiv listing abstract compared with the manuscript's\n abstract, resources including what is not stated, the authors' own\n limitations, how the paper uses its references, and what was and was not\n examined. No sentence in it was written by a model; every label carries\n its probability. Use this for what a paper states and under what\n conditions, including papers Pith has not reviewed, where get_review\n reports no review. Accepts an arXiv id or URL, DOI, or Pith Number.",
"inputSchema": {
"properties": {
"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.",
"title": "Arxiv Id",
"type": "string"
}
},
"required": [
"arxiv_id"
],
"title": "get_recordArguments",
"type": "object"
},
"name": "get_record"
},
{
"description": "Pith's review of one specific paper, in one call: the verdict,\n confidence, novelty and correctness scores, one-line summary, weakest\n assumption, and the paper's argument as short labeled statements\n (premise, machinery, core claim, falsifier) already extracted, so the\n paper's premises and logical structure can be stated without reading\n the PDF. Use this for any question about a specific paper: what it\n asserts, what it assumes, how the argument runs, how sound it is, or\n what Pith concluded. Accepts an arXiv id or URL, DOI, or Pith Number.",
"inputSchema": {
"properties": {
"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.",
"title": "Arxiv Id",
"type": "string"
}
},
"required": [
"arxiv_id"
],
"title": "get_reviewArguments",
"type": "object"
},
"name": "get_review"
},
{
"description": "A reviewer's published signed reviews and, when present, their\n calibration record (Brier score, open predictions, positivity skew).\n Call this when the user asks about a named Pith reviewer or how\n trustworthy a reviewer's track record is.",
"inputSchema": {
"properties": {
"handle": {
"title": "Handle",
"type": "string"
}
},
"required": [
"handle"
],
"title": "get_reviewer_recordArguments",
"type": "object"
},
"name": "get_reviewer_record"
},
{
"description": "Published human signed reviews of one paper: reviewer identity, axis\n deltas against the machine review, claim verdicts, defects, predictions,\n and who paid. Call this when the user asks what human experts said about\n a paper, on top of the machine review.",
"inputSchema": {
"properties": {
"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.",
"title": "Arxiv Id",
"type": "string"
}
},
"required": [
"arxiv_id"
],
"title": "get_signed_reviewsArguments",
"type": "object"
},
"name": "get_signed_reviews"
},
{
"description": "The papers Pith reviewed most recently, newest first. Call this when\n the user asks what is new, notable, or recently reviewed in a field or\n overall. days caps how far back to look (max 90).",
"inputSchema": {
"properties": {
"category": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"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.",
"title": "Category"
},
"days": {
"default": 7,
"title": "Days",
"type": "integer"
},
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
}
},
"title": "latest_reviewsArguments",
"type": "object"
},
"name": "latest_reviews"
},
{
"description": "For the papers claimed on the account behind your key: how many\n papers cite each, whether they cite it as support, extension or\n disagreement, and the citing sentence quoted. Call when the user asks who\n is building on or disputing their work. Needs a personal key.",
"inputSchema": {
"properties": {},
"title": "my_citationsArguments",
"type": "object"
},
"name": "my_citations"
},
{
"description": "Pith's machine review verdict and the count of published signed human\n reviews for each paper claimed on the account behind your key. Needs a\n personal key.",
"inputSchema": {
"properties": {},
"title": "my_reviewsArguments",
"type": "object"
},
"name": "my_reviews"
},
{
"description": "Whether either paper cites the other, the resolved works both cite\n (on or off arXiv), and the papers that cite both.",
"inputSchema": {
"properties": {
"a": {
"description": "Any form the user gave: bare arXiv id (2401.00001), arXiv abs/pdf URL, DOI or doi.org URL, or Pith Number.",
"title": "A",
"type": "string"
},
"b": {
"description": "Any form the user gave: bare arXiv id (2401.00001), arXiv abs/pdf URL, DOI or doi.org URL, or Pith Number.",
"title": "B",
"type": "string"
},
"limit": {
"default": 12,
"description": "Shared graph neighbors per side. 1 to 40.",
"maximum": 40,
"minimum": 1,
"title": "Limit",
"type": "integer"
}
},
"required": [
"a",
"b"
],
"title": "paper_bridgeArguments",
"type": "object"
},
"name": "paper_bridge"
},
{
"description": "What other arXiv papers do with this paper, and what it does with the\n arXiv papers it cites: builds on, uses the method or tool, uses the data,\n compares with, cites as support or background, or contests. Each group\n counts distinct papers and quotes the citing authors' own sentences.\n Labels come from each citing paper's LaTeX source typed by Pith's classifier and are\n shown only at intent probability 0.8 or more (support at 0.95, contests at 0.7);\n the rest are counted as unlabelled. Measured agreement of every label with\n independent model families: https://pith.science/connected-record. Use this\n for how a result has been taken up, challenged or built on across arXiv.",
"inputSchema": {
"properties": {
"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.",
"title": "Arxiv Id",
"type": "string"
},
"quotes": {
"default": 5,
"description": "Quoted sentences per group. 1 to 20.",
"maximum": 20,
"minimum": 1,
"title": "Quotes",
"type": "integer"
}
},
"required": [
"arxiv_id"
],
"title": "paper_connectionsArguments",
"type": "object"
},
"name": "paper_connections"
},
{
"description": "One paper's compiled record, small enough to hold beside others: the\n main claim and contribution in the authors' words, each abstract\n sentence with its role and probability, paper-level labels, and, for\n full-text records, conditions, measurements, results and limitations,\n with totals so a capped list is not mistaken for the whole paper.",
"inputSchema": {
"properties": {
"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.",
"title": "Arxiv Id",
"type": "string"
},
"limit": {
"default": 8,
"description": "Items per list. 1 to 20.",
"maximum": 20,
"minimum": 1,
"title": "Limit",
"type": "integer"
}
},
"required": [
"arxiv_id"
],
"title": "paper_packetArguments",
"type": "object"
},
"name": "paper_packet"
},
{
"description": "Sources read and levels run for one paper's record, or the number of\n stored records by tier. Call before treating an empty result as a\n finding: an empty list means nothing in the examined scope matched.",
"inputSchema": {
"properties": {
"arxiv_id": {
"default": "",
"description": "One paper, or empty for the whole record store.",
"title": "Arxiv Id",
"type": "string"
}
},
"title": "record_coverageArguments",
"type": "object"
},
"name": "record_coverage"
},
{
"description": "Turn a pasted arXiv id, arXiv URL, DOI, or Pith Number into the\n arXiv id the other tools key on. ``resolved`` is false when the input\n did not become an arXiv id.",
"inputSchema": {
"properties": {
"reference": {
"description": "Any form the user gave: bare arXiv id (2401.00001), arXiv abs/pdf URL, DOI or doi.org URL, or Pith Number.",
"title": "Reference",
"type": "string"
}
},
"required": [
"reference"
],
"title": "resolve_paperArguments",
"type": "object"
},
"name": "resolve_paper"
},
{
"description": "Full-text search over every scientific claim Pith has extracted,\n across all reviewed papers. Call this when the user asks who claims\n something, whether a claim appears in the recent literature, or what\n evidence bears on a statement. Returns each matching claim with its\n paper, verdict, and review link.",
"inputSchema": {
"properties": {
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
},
"query": {
"description": "The claim or statement to look for, in plain words.",
"title": "Query",
"type": "string"
}
},
"required": [
"query"
],
"title": "search_claimsArguments",
"type": "object"
},
"name": "search_claims"
},
{
"description": "Search Pith-reviewed papers by title and abstract. Call this when the\n user names a research topic, phenomenon, method, or paper title without\n an identifier, or asks whether Pith has reviewed anything on a subject.\n Each result carries the paper's verdict, summary, and review link.",
"inputSchema": {
"properties": {
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
},
"query": {
"description": "Topic, phenomenon, method, or paper title in plain words.",
"title": "Query",
"type": "string"
}
},
"required": [
"query"
],
"title": "search_papersArguments",
"type": "object"
},
"name": "search_papers"
},
{
"description": "Whether the cited paper's own sentences support what a sentence\n attributes to it: supports, partly supports (a condition is missing),\n contradicts, or not addressed, with the single best sentence from the\n paper quoted. Call this before citing a paper for a specific claim, or to\n check a citation in a draft or an answer. It reads the paper's abstract,\n and its full text where Pith holds it; the examined field says which. On\n real citations its verdict agreed with two blind model families 139 times\n in 160, most differences being partly supported versus not addressed\n (https://pith.science/connected-record).",
"inputSchema": {
"properties": {
"cited": {
"description": "Any form the user gave: bare arXiv id (2401.00001), arXiv abs/pdf URL, DOI or doi.org URL, or Pith Number.",
"title": "Cited",
"type": "string"
},
"sentence": {
"description": "The sentence that cites the paper, as written in a draft, an answer or a paper.",
"title": "Sentence",
"type": "string"
}
},
"required": [
"sentence",
"cited"
],
"title": "verify_citationArguments",
"type": "object"
},
"name": "verify_citation"
}
]
}What the leaf hashes
{"body":"6bc92def171091ca6a96c799bc9abb136ade20489f866faafc519440edd92145","id":307517,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793057713452727,"prev":null,"subject":"d2f250dc-b08d-4445-873e-b8c73bb9d882","subject_kind":"endpoint"}Proof
Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of (296695 rows).
- 0x5112c75c05cbd9788d7e1093254da5805c0d5ff667335df24a63b8128db0664d
- 0x31f5f4b67eed7b073ca816c765d6ad34ce7e713f0e923b784f6f31a17acc1d54
- 0xc56f66387e46665b504ea9f1fdc9abb3982f91c6a5fa4c7de9614d37dbd9d274
- 0x2a9b781832797ec25c8b58289f70d764ee0d9129d97451855236bd2d1a17ff74
- 0x2d6526a9190e295a79fac62f91810e5e52c1d85f1a0b9cc9cb3d4a7df32dc41c
- 0xfa896687cbf79794c23487dad42eae04b2e2f62f3f87fee8e11921e832fa94e0
- 0x2bbab5f1a8f705f8f9ea187de8e67d15f3adcf89a717b460232698f467676f37
- 0x8b2393b9a0cca266e124c0d9cdd820c770d089235bd6a2a38090e1f9577c48f9
- 0x417ae96c21259e0ba92e9c16e22f6cdcea1d55df56b3cb0c4812519bf06e866e
- 0x1cf289732577ec7d4b7786636bf1c834b739571451a5cc67e3aac33256c9be46
- 0xfa039eb62e5d0ae9f7aaaafb0fcbceacfa661b07228233046b9a9af94e547a55
- 0xecaf47ba75097c34f2d3c4d62539dace0db8b484bf08941a9259e2d1e8ccea77
- 0xf7d2cf278e5d2768b8bdb70730c378877cf7165d8efcbec8bcd3282fdc50d177
- 0x0733993143f0230e79482cef2c38e95d98f9eafbe64a43cdc74a4545938a4167
- 0x2be1e80e065dd6b2cc75a7142be22225acd144ac975d70bf24b4f01fd76dc497
- 0x2e6a32eb32761c210560e852405e2f865f958ddbe01027894f8b9c1b3433b9f0
- 0x9a83be955a206deb65b995adfd92c58fa31c95fbbf926bd199d300e70b08b26d
- 0x20704208aa6923d6b2450ef74ede87a6e0265d46447926038fe9506e9e154b2d
- 0x9b9ce5b74b9bab5121612ef6b64920a8d453cbf311096a423eef9702747e868a
- Day root
- 0xf43e8dcc3d451a4788b26be904c55e8c4c0fa75c9666796c51db38d37e2c0df8
- Chained
- 0x702d5ac508f08b0d1accf36af25822d8e5660367494edd17a642fb61e158a57a
- Published
- On Arc Testnet, block 69251483: 0x495162f8936e19f0039918feebe6c307f327cd6bf8c37219620b1970041fa9ae