{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VC554FSVABO7ESXS7AFU2JH2Z5","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":"62f8b73fe217a681360a54cddb2d118af38e26647ec9527b6442546e34140403","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T15:54:34Z","title_canon_sha256":"bfa9490422f8da460ad2d684193f88b668138ff0305ac7c974bbddf372e645c1"},"schema_version":"1.0","source":{"id":"2502.06589","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06589","created_at":"2026-07-05T10:12:09Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06589v1","created_at":"2026-07-05T10:12:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06589","created_at":"2026-07-05T10:12:09Z"},{"alias_kind":"pith_short_12","alias_value":"VC554FSVABO7","created_at":"2026-07-05T10:12:09Z"},{"alias_kind":"pith_short_16","alias_value":"VC554FSVABO7ESXS","created_at":"2026-07-05T10:12:09Z"},{"alias_kind":"pith_short_8","alias_value":"VC554FSV","created_at":"2026-07-05T10:12:09Z"}],"graph_snapshots":[{"event_id":"sha256:cd3b85b3511645dd94a486fd8feb92c28f46887a5aedfa835888cd3ccc3e5bf2","target":"graph","created_at":"2026-07-05T10:12:09Z","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/2502.06589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Due to the scarcity of agent-oriented pre-training data, LLM-based autonomous agents typically rely on complex prompting or extensive fine-tuning, which often fails to introduce new capabilities while preserving strong generalizability. We introduce Hephaestus-Forge, the first large-scale pre-training corpus designed to enhance the fundamental capabilities of LLM agents in API function calling, intrinsic reasoning and planning, and adapting to environmental feedback. Hephaestus-Forge comprises 103B agent-specific data encompassing 76,537 APIs, including both tool documentation to introduce kno","authors_text":"Bing Yin, Binxuan Huang, Chao Zhang, Haoming Jiang, Jingfeng Yang, Kewei Cheng, Nasser Zalmout, Pei Chen, Priyanka Nigam, Qing Ping, Rongzhi Zhang, Ruijie Wang, Sanket Lokegaonkar, Tianyi Liu, Xin Liu, Yifan Gao, Yuchen Zhuang, Zheng Li, Zhengyang Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T15:54:34Z","title":"Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06589","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:b1de6c4707b5e35c8855f495ceaf668ac8289f65cacedf485ae43fa6fc6f8d7f","target":"record","created_at":"2026-07-05T10:12:09Z","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":"62f8b73fe217a681360a54cddb2d118af38e26647ec9527b6442546e34140403","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T15:54:34Z","title_canon_sha256":"bfa9490422f8da460ad2d684193f88b668138ff0305ac7c974bbddf372e645c1"},"schema_version":"1.0","source":{"id":"2502.06589","kind":"arxiv","version":1}},"canonical_sha256":"a8bbde1655005df24af2f80b4d24facf45b516216f493a9143c323f0b06fed84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8bbde1655005df24af2f80b4d24facf45b516216f493a9143c323f0b06fed84","first_computed_at":"2026-07-05T10:12:09.035505Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:09.035505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WzgVthbDLpFZu6KD/V5FkP3NyaTJ9RqgJI5yZAU635FTysPcud8tVFVeqJ5uiAI3OLGAst0/QyEWFJNeA9VhBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:09.035990Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06589","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1de6c4707b5e35c8855f495ceaf668ac8289f65cacedf485ae43fa6fc6f8d7f","sha256:cd3b85b3511645dd94a486fd8feb92c28f46887a5aedfa835888cd3ccc3e5bf2"],"state_sha256":"e580e8639e4659032fb6457e854adcf532803de15aeaa2a05514ad847ca1bec0"}