{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EC3OWX5MMY7AA7GXAWARIUN355","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":"1053b33f7268a37419b1673fb79a0600e845c86880f309c7f893ff3c88b6cc95","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T14:06:02Z","title_canon_sha256":"c179ec60030e1d08e7dc7fe38a10040a4fcd70630d5ad2b0225bff613ba4801a"},"schema_version":"1.0","source":{"id":"2505.20016","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20016","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20016v1","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20016","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_12","alias_value":"EC3OWX5MMY7A","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_16","alias_value":"EC3OWX5MMY7AA7GX","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_8","alias_value":"EC3OWX5M","created_at":"2026-07-05T11:09:51Z"}],"graph_snapshots":[{"event_id":"sha256:b9993cbda293466b4e075e6aff6f24a51a6bef120e503173ea91423b3fdac084","target":"graph","created_at":"2026-07-05T11:09:51Z","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/2505.20016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing tool-learning methods usually rely on supervised fine-tuning, they often overlook fine-grained optimization of internal tool call details, leading to limitations in preference alignment and error discrimination. To overcome these challenges, we propose Token-level Tool-use Preference Alignment Training Framework (TTPA), a training paradigm for constructing token-level tool-use preference datasets that align LLMs with fine-grained preferences using a novel error-oriented scoring mechanism. TTPA first introduces reversed dataset construction, a method for creating high-quality, multi-tu","authors_text":"Chengrui Huang, Dongsheng Wang, Shen Gao, Shuo Shang, Zhengliang Shi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T14:06:02Z","title":"TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20016","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":"sha256:0578efb6b56f3098b1f3a7ef7e021b18d4c7a07623a2c7b8562ea4ea5bdf63c3","target":"record","created_at":"2026-07-05T11:09:51Z","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":"1053b33f7268a37419b1673fb79a0600e845c86880f309c7f893ff3c88b6cc95","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T14:06:02Z","title_canon_sha256":"c179ec60030e1d08e7dc7fe38a10040a4fcd70630d5ad2b0225bff613ba4801a"},"schema_version":"1.0","source":{"id":"2505.20016","kind":"arxiv","version":1}},"canonical_sha256":"20b6eb5fac663e007cd705811451bbef68daf15131f36fd46828d7c54f82a8e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20b6eb5fac663e007cd705811451bbef68daf15131f36fd46828d7c54f82a8e9","first_computed_at":"2026-07-05T11:09:51.211654Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:51.211654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pDIeAE9/h3Nx8F7zISPT2A1NrAgZL3TKq4YCC438qaCoL5VbhvF1/xsgShkqj1pPWcYJXTFEjFHab01R13HWCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:51.212068Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20016","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0578efb6b56f3098b1f3a7ef7e021b18d4c7a07623a2c7b8562ea4ea5bdf63c3","sha256:b9993cbda293466b4e075e6aff6f24a51a6bef120e503173ea91423b3fdac084"],"state_sha256":"726a0f5438bd86c0e23ace521b5548ad0646b24bc8b1c6d5e2f83892906131fe"}