{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PQSDYDBFXW3WSCAQ3JTIAH76BW","short_pith_number":"pith:PQSDYDBF","schema_version":"1.0","canonical_sha256":"7c243c0c25bdb7690810da66801ffe0d93cd9be11484e5713ce7314e2c5d0088","source":{"kind":"arxiv","id":"2602.21265","version":2},"attestation_state":"computed","paper":{"title":"ToolMATH: A Diagnostic Benchmark for Long-Horizon Tool Use under Systematic Tool-Catalog Constraints","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.CL","authors_text":"Hyeonje Choi, Hyojun Lee, Jay-Yoon Lee, Jeongsoo Lee","submitted_at":"2026-02-24T09:23:12Z","abstract_excerpt":"We introduce \\ToolMATH, a math-grounded diagnostic benchmark for evaluating long-horizon tool use under controllable tool-catalog conditions. \\ToolMATH converts stepwise MATH solutions into reusable Python tools with natural-language descriptions and typed schemas, and pairs each problem with a tool environment requiring sequential tool use, intermediate-output reuse, and logically connected tool-call chains. \\ToolMATH controls tool availability and catalog difficulty by constructing gold tools and graded distractors with varying similarity to gold tools. \\ToolMATH also incorporates behavior-c"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2602.21265","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-24T09:23:12Z","cross_cats_sorted":["cs.LG","cs.SE"],"title_canon_sha256":"77a5556e20e70fefa1f9a35dd83e5e7382cb43ce58e91118bea6e5ae29da882d","abstract_canon_sha256":"9520d43a6c17d36d0d46346bceaea39ea45160b24ac71ba30238f8a7a35779c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:26.524074Z","signature_b64":"jnKoelIWBy7gLloszvReumSnLhyyw4EJoqU5a2zoYHideuNuKW51YXUhz2odrr0rUfRTCoqJ4mZ2pXueiS3wAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c243c0c25bdb7690810da66801ffe0d93cd9be11484e5713ce7314e2c5d0088","last_reissued_at":"2026-05-20T00:04:26.522987Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:26.522987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ToolMATH: A Diagnostic Benchmark for Long-Horizon Tool Use under Systematic Tool-Catalog Constraints","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.CL","authors_text":"Hyeonje Choi, Hyojun Lee, Jay-Yoon Lee, Jeongsoo Lee","submitted_at":"2026-02-24T09:23:12Z","abstract_excerpt":"We introduce \\ToolMATH, a math-grounded diagnostic benchmark for evaluating long-horizon tool use under controllable tool-catalog conditions. \\ToolMATH converts stepwise MATH solutions into reusable Python tools with natural-language descriptions and typed schemas, and pairs each problem with a tool environment requiring sequential tool use, intermediate-output reuse, and logically connected tool-call chains. \\ToolMATH controls tool availability and catalog difficulty by constructing gold tools and graded distractors with varying similarity to gold tools. \\ToolMATH also incorporates behavior-c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.21265","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.21265/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2602.21265","created_at":"2026-05-20T00:04:26.523152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.21265v2","created_at":"2026-05-20T00:04:26.523152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.21265","created_at":"2026-05-20T00:04:26.523152+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQSDYDBFXW3W","created_at":"2026-05-20T00:04:26.523152+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQSDYDBFXW3WSCAQ","created_at":"2026-05-20T00:04:26.523152+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQSDYDBF","created_at":"2026-05-20T00:04:26.523152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PQSDYDBFXW3WSCAQ3JTIAH76BW","json":"https://pith.science/pith/PQSDYDBFXW3WSCAQ3JTIAH76BW.json","graph_json":"https://pith.science/api/pith-number/PQSDYDBFXW3WSCAQ3JTIAH76BW/graph.json","events_json":"https://pith.science/api/pith-number/PQSDYDBFXW3WSCAQ3JTIAH76BW/events.json","paper":"https://pith.science/paper/PQSDYDBF"},"agent_actions":{"view_html":"https://pith.science/pith/PQSDYDBFXW3WSCAQ3JTIAH76BW","download_json":"https://pith.science/pith/PQSDYDBFXW3WSCAQ3JTIAH76BW.json","view_paper":"https://pith.science/paper/PQSDYDBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.21265&json=true","fetch_graph":"https://pith.science/api/pith-number/PQSDYDBFXW3WSCAQ3JTIAH76BW/graph.json","fetch_events":"https://pith.science/api/pith-number/PQSDYDBFXW3WSCAQ3JTIAH76BW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQSDYDBFXW3WSCAQ3JTIAH76BW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQSDYDBFXW3WSCAQ3JTIAH76BW/action/storage_attestation","attest_author":"https://pith.science/pith/PQSDYDBFXW3WSCAQ3JTIAH76BW/action/author_attestation","sign_citation":"https://pith.science/pith/PQSDYDBFXW3WSCAQ3JTIAH76BW/action/citation_signature","submit_replication":"https://pith.science/pith/PQSDYDBFXW3WSCAQ3JTIAH76BW/action/replication_record"}},"created_at":"2026-05-20T00:04:26.523152+00:00","updated_at":"2026-05-20T00:04:26.523152+00:00"}