{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FYUJEEJCGRMRHE6KOQRP6UJT3F","short_pith_number":"pith:FYUJEEJC","canonical_record":{"source":{"id":"2501.01290","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-02T15:10:52Z","cross_cats_sorted":[],"title_canon_sha256":"c9e6f598a357ffa20cf0175b10e8f32a375a606fdca9a32eab3a215b93fc4c10","abstract_canon_sha256":"725b61e5934f912bd2b86c361b12a1303fdc417c9d556c93c9f0c7952f74b970"},"schema_version":"1.0"},"canonical_sha256":"2e2892112234591393ca7422ff5133d9713796c66145710a49e028175718274b","source":{"kind":"arxiv","id":"2501.01290","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01290","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01290v1","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01290","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"pith_short_12","alias_value":"FYUJEEJCGRMR","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"pith_short_16","alias_value":"FYUJEEJCGRMRHE6K","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"pith_short_8","alias_value":"FYUJEEJC","created_at":"2026-07-05T09:56:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FYUJEEJCGRMRHE6KOQRP6UJT3F","target":"record","payload":{"canonical_record":{"source":{"id":"2501.01290","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-02T15:10:52Z","cross_cats_sorted":[],"title_canon_sha256":"c9e6f598a357ffa20cf0175b10e8f32a375a606fdca9a32eab3a215b93fc4c10","abstract_canon_sha256":"725b61e5934f912bd2b86c361b12a1303fdc417c9d556c93c9f0c7952f74b970"},"schema_version":"1.0"},"canonical_sha256":"2e2892112234591393ca7422ff5133d9713796c66145710a49e028175718274b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:17.553773Z","signature_b64":"BWftrCGm7sKetiRXs0v6i3NWzM4GfdQigJSOuHBorQJ49FWPat9TFpRKCnDwlZYs0o+PsX3EFVFo719LKPVPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e2892112234591393ca7422ff5133d9713796c66145710a49e028175718274b","last_reissued_at":"2026-07-05T09:56:17.553292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:17.553292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.01290","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:56:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fInKv1HuqNvl0luiRuZHBoK+5tdV5GQOpNYC7atgTyN0yOWcrriGZxAq3HR1zvuIrMo0bqQ7GtkEW1dCqf/VDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:20:24.944613Z"},"content_sha256":"63dc32bc2a62c20f2470630b4d6aff5cf0264054549c78b3cd6e55c593d99047","schema_version":"1.0","event_id":"sha256:63dc32bc2a62c20f2470630b4d6aff5cf0264054549c78b3cd6e55c593d99047"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FYUJEEJCGRMRHE6KOQRP6UJT3F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ToolComp: A Multi-Tool Reasoning & Process Supervision Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Claire Yoon, Pranav Raja, Sean Hendryx, Vaskar Nath","submitted_at":"2025-01-02T15:10:52Z","abstract_excerpt":"Despite recent advances in AI, the development of systems capable of executing complex, multi-step reasoning tasks involving multiple tools remains a significant challenge. Current benchmarks fall short in capturing the real-world complexity of tool-use reasoning, where verifying the correctness of not only the final answer but also the intermediate steps is important for evaluation, development, and identifying failures during inference time. To bridge this gap, we introduce ToolComp, a comprehensive benchmark designed to evaluate multi-step tool-use reasoning. ToolComp is developed through a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01290","kind":"arxiv","version":1},"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/2501.01290/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:56:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I+j06kjfQ2nJsyzms7hpRwcU+DGkI0TpOwdpdRvSOW5mZGJjaW3uPqeZ9yUhp4TcqXwMV1iLuGt6Vj9yZoDVBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:20:24.945154Z"},"content_sha256":"a69d045124827b3a7f27722b7d0e15edbdac6e839ce3119e6bdd91b0a86d9531","schema_version":"1.0","event_id":"sha256:a69d045124827b3a7f27722b7d0e15edbdac6e839ce3119e6bdd91b0a86d9531"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FYUJEEJCGRMRHE6KOQRP6UJT3F/bundle.json","state_url":"https://pith.science/pith/FYUJEEJCGRMRHE6KOQRP6UJT3F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FYUJEEJCGRMRHE6KOQRP6UJT3F/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T01:20:24Z","links":{"resolver":"https://pith.science/pith/FYUJEEJCGRMRHE6KOQRP6UJT3F","bundle":"https://pith.science/pith/FYUJEEJCGRMRHE6KOQRP6UJT3F/bundle.json","state":"https://pith.science/pith/FYUJEEJCGRMRHE6KOQRP6UJT3F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FYUJEEJCGRMRHE6KOQRP6UJT3F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FYUJEEJCGRMRHE6KOQRP6UJT3F","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":"725b61e5934f912bd2b86c361b12a1303fdc417c9d556c93c9f0c7952f74b970","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-02T15:10:52Z","title_canon_sha256":"c9e6f598a357ffa20cf0175b10e8f32a375a606fdca9a32eab3a215b93fc4c10"},"schema_version":"1.0","source":{"id":"2501.01290","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01290","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01290v1","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01290","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"pith_short_12","alias_value":"FYUJEEJCGRMR","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"pith_short_16","alias_value":"FYUJEEJCGRMRHE6K","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"pith_short_8","alias_value":"FYUJEEJC","created_at":"2026-07-05T09:56:17Z"}],"graph_snapshots":[{"event_id":"sha256:a69d045124827b3a7f27722b7d0e15edbdac6e839ce3119e6bdd91b0a86d9531","target":"graph","created_at":"2026-07-05T09:56:17Z","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/2501.01290/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent advances in AI, the development of systems capable of executing complex, multi-step reasoning tasks involving multiple tools remains a significant challenge. Current benchmarks fall short in capturing the real-world complexity of tool-use reasoning, where verifying the correctness of not only the final answer but also the intermediate steps is important for evaluation, development, and identifying failures during inference time. To bridge this gap, we introduce ToolComp, a comprehensive benchmark designed to evaluate multi-step tool-use reasoning. ToolComp is developed through a","authors_text":"Claire Yoon, Pranav Raja, Sean Hendryx, Vaskar Nath","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-02T15:10:52Z","title":"ToolComp: A Multi-Tool Reasoning & Process Supervision Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01290","kind":"arxiv","version":1},"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":"sha256:63dc32bc2a62c20f2470630b4d6aff5cf0264054549c78b3cd6e55c593d99047","target":"record","created_at":"2026-07-05T09:56:17Z","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":"725b61e5934f912bd2b86c361b12a1303fdc417c9d556c93c9f0c7952f74b970","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-02T15:10:52Z","title_canon_sha256":"c9e6f598a357ffa20cf0175b10e8f32a375a606fdca9a32eab3a215b93fc4c10"},"schema_version":"1.0","source":{"id":"2501.01290","kind":"arxiv","version":1}},"canonical_sha256":"2e2892112234591393ca7422ff5133d9713796c66145710a49e028175718274b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e2892112234591393ca7422ff5133d9713796c66145710a49e028175718274b","first_computed_at":"2026-07-05T09:56:17.553292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:17.553292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BWftrCGm7sKetiRXs0v6i3NWzM4GfdQigJSOuHBorQJ49FWPat9TFpRKCnDwlZYs0o+PsX3EFVFo719LKPVPCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:17.553773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01290","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63dc32bc2a62c20f2470630b4d6aff5cf0264054549c78b3cd6e55c593d99047","sha256:a69d045124827b3a7f27722b7d0e15edbdac6e839ce3119e6bdd91b0a86d9531"],"state_sha256":"f22dd752d819075b7ee2427e4971a2073f91f229f8defebb3155d160c58b918f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eKo56NMQU3mDZ+rrEoiuJdyGxD13EVZqmLYRX5JYZ2siSdzMXDuZiDrUUCgvF3sF6D3ouKuyXeB6bSDKTcihBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:20:24.950019Z","bundle_sha256":"7ae6ef734aa87a4e8ad9e9bb8240098f45aa514008779af8ee9d593c2686474b"}}