Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Changed the definition of "get_review"
⟨53 unchanged words⟩ "title":"Claim","type":"object"},"LeanStatement":{"properties":{"anchor_verdict":{"title":"Anchor Verdict","type":"string"},"decl":{"title":"Decl","type":"string"},"label":{"title":"Label","type":"string"},"lean_statement":{"title":"Lean Statement","type":"string"},"paper_claim_key":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Paper Claim Key"},"referee_judgments":{"items":{"additionalProperties":true,"type":"object"},"title":"Referee Judgments","type":"array"}},"required":["decl","label","lean_statement","paper_claim_key","anchor_verdict","referee_judgments"],"title":"LeanStatement","type":"object"},"LeanSummary":{"description":"The paper's latest Lean build on Pith and published referees' sign-offs on it.","properties":{"mathlib":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Mathlib"},"note":{"title":"Note","type":"string"},"statements":{"items":{"$ref":"#/$defs/LeanStatement"},"title":"Statements","type":"array"},"status":{"title":"Status","type":"string"},"toolchain":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Toolchain"}},"required":["status","toolchain","mathlib","statements","note"],"title":"LeanSummary","type":"object"}},"description":"One paper's full machine review.","properties":{ ⟨75 unchanged words⟩ type":"null"}],"title":"Lead"},"lean":{"anyOf":[{"$ref":"#/$defs/LeanSummary"},{"type":"null"}]},"note":{"title":"Note"," ⟨90 unchanged words⟩
Changed the definition of "paper_connections"
⟨64 unchanged words⟩ only at intent probability 0.8 or more (contestssupport at0.70.95,orcontestsmoreat 0.7); the rest are counted as unlabelled. Measured ⟨26 unchanged words⟩
Added "ask_field", "check_my_draft", "my_citations" and 1 more (20 tools before, 24 now)
Ask a yes-or-no question across a field — Read the papers closest to a question and return, for each, whether its own abstract sentences answer yes, no or not addressed, with the deciding sentence quoted. Call when a user asks whether something holds across the literature. Candidates are chosen by meaning, so a paper that answers in different words can be missed. Needs a personal key; counts against a daily allowance.
Check my draft's bibliography — Resolve each reference in a draft, flag retracted works, and for arXiv papers show how later papers cite them: as support, and whether any contest them, with the contesting sentence quoted. Call before a submission or when a user wants their reference list checked. Needs a personal key; counts against a daily allowance.
Who cites my papers, and how — For the papers claimed on the account behind your key: how many papers cite each, whether they cite it as support, extension or disagreement, and the citing sentence quoted. Call when the user asks who is building on or disputing their work. Needs a personal key.
Certificate recorded, valid to 2027-02-06
Authorization not required
Changed the definition of "check_claim", "find_passages", "paper_connections" and 2 more
⟨17 unchanged words⟩ with the paper's own main claim quoted andJev'sthe classifier's probability. Call this before asserting a scientific result, ⟨55 unchanged words⟩ 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).
Author sentencesJevthe classifier
Added "check_claim" and "verify_citation"; changed the definition of "paper_connections" (18 tools before, 20 now)
⟨74 unchanged words⟩ more); the rest are counted as unlabelled. Measured agreement of every label with independent model families: https://pith.science/connected-record. Use thisfor how a result has beentaken up, challenged or built on across arXiv.
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 Jev'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 …
Added "paper_connections" (17 tools before, 18 now)
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 Jev and are shown only at intent probability 0.8 or more (contests at 0.7 or more); the rest are counted as unlabelled. Use this for how a result has been taken up, challenged or built on across arXiv.
Unknown → Live
First tool surface recorded: 17 tools (server version 1.1.0)
https://pith.science/mcp (mcp_streamable_http) — from mcp_registry, with the record
Showing the latest 11 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
Reviews of my papers — Pith's machine review verdict and the count of published signed human reviews for each paper claimed on the account behind your key. Needs a personal key.
{"description":"Author sentences of one role withJev'sthe classifier's probabilities.","properties":{"arxiv_id":{"title ⟨71 unchanged words⟩
⟨51 unchanged words⟩ from each citing paper's LaTeX source typed byJevPith's classifier and are shown only at intent probability 0.8 ⟨41 unchanged words⟩
{"description":"One paper's compiled record: authors' sentences withJev'sthe classifier's labels and probabilities.","properties":{"abstract" ⟨141 unchanged words⟩
⟨64 unchanged words⟩ 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).
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.