{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PQSDYDBFXW3WSCAQ3JTIAH76BW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9520d43a6c17d36d0d46346bceaea39ea45160b24ac71ba30238f8a7a35779c9","cross_cats_sorted":["cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-24T09:23:12Z","title_canon_sha256":"77a5556e20e70fefa1f9a35dd83e5e7382cb43ce58e91118bea6e5ae29da882d"},"schema_version":"1.0","source":{"id":"2602.21265","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.21265","created_at":"2026-05-20T00:04:26Z"},{"alias_kind":"arxiv_version","alias_value":"2602.21265v2","created_at":"2026-05-20T00:04:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.21265","created_at":"2026-05-20T00:04:26Z"},{"alias_kind":"pith_short_12","alias_value":"PQSDYDBFXW3W","created_at":"2026-05-20T00:04:26Z"},{"alias_kind":"pith_short_16","alias_value":"PQSDYDBFXW3WSCAQ","created_at":"2026-05-20T00:04:26Z"},{"alias_kind":"pith_short_8","alias_value":"PQSDYDBF","created_at":"2026-05-20T00:04:26Z"}],"graph_snapshots":[{"event_id":"sha256:187580c202f87aaa55ec311210993dfb1eb19e191b988dd9783cd8f3252276b7","target":"graph","created_at":"2026-05-20T00:04:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.21265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hyeonje Choi, Hyojun Lee, Jay-Yoon Lee, Jeongsoo Lee","cross_cats":["cs.LG","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-24T09:23:12Z","title":"ToolMATH: A Diagnostic Benchmark for Long-Horizon Tool Use under Systematic Tool-Catalog Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.21265","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b346922c074af1d4a48a37547a58c0a9719a540559acf6b58e07e2e888b81334","target":"record","created_at":"2026-05-20T00:04:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9520d43a6c17d36d0d46346bceaea39ea45160b24ac71ba30238f8a7a35779c9","cross_cats_sorted":["cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-24T09:23:12Z","title_canon_sha256":"77a5556e20e70fefa1f9a35dd83e5e7382cb43ce58e91118bea6e5ae29da882d"},"schema_version":"1.0","source":{"id":"2602.21265","kind":"arxiv","version":2}},"canonical_sha256":"7c243c0c25bdb7690810da66801ffe0d93cd9be11484e5713ce7314e2c5d0088","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c243c0c25bdb7690810da66801ffe0d93cd9be11484e5713ce7314e2c5d0088","first_computed_at":"2026-05-20T00:04:26.522987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:26.522987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jnKoelIWBy7gLloszvReumSnLhyyw4EJoqU5a2zoYHideuNuKW51YXUhz2odrr0rUfRTCoqJ4mZ2pXueiS3wAQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:26.524074Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.21265","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b346922c074af1d4a48a37547a58c0a9719a540559acf6b58e07e2e888b81334","sha256:187580c202f87aaa55ec311210993dfb1eb19e191b988dd9783cd8f3252276b7"],"state_sha256":"bb325db470750dbb395d9f5b07866bd38b546268b460e12f7ea8cfd972f4c530"}