{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:L2P4S757ZPAEOW3TOZALVQZPZ6","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":"cdb4899a6ad5a029dc43705e8f54e1e0443fd297dc469d093840563cb429cde3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-13T14:43:47Z","title_canon_sha256":"fc7bc9e123e9af5cce266bca01d6cab06e7991356d33c5761ba10d67419b0f9c"},"schema_version":"1.0","source":{"id":"2604.11557","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.11557","created_at":"2026-05-26T02:04:10Z"},{"alias_kind":"arxiv_version","alias_value":"2604.11557v2","created_at":"2026-05-26T02:04:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.11557","created_at":"2026-05-26T02:04:10Z"},{"alias_kind":"pith_short_12","alias_value":"L2P4S757ZPAE","created_at":"2026-05-26T02:04:10Z"},{"alias_kind":"pith_short_16","alias_value":"L2P4S757ZPAEOW3T","created_at":"2026-05-26T02:04:10Z"},{"alias_kind":"pith_short_8","alias_value":"L2P4S757","created_at":"2026-05-26T02:04:10Z"}],"graph_snapshots":[{"event_id":"sha256:05e908089dcab22a08837b5d9343a0a1bbc6bd04403890c05981e8015d4fc69d","target":"graph","created_at":"2026-05-26T02:04:10Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"fine-tuning Qwen3-8B on our dataset substantially improves tool-use performance. Under the distractor-heavy Hybrid-20 setting, achieves 93.0% single-turn Strict Precision, outperforming commercial models including GPT, Gemini, and Claude."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That combining public datasets with structurally controlled synthetic trajectories and the Anchor Linkage mechanism produces training data that genuinely improves generalization to real tool-use scenarios without introducing artifacts or biases."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"UniToolCall unifies tool-use data and evaluation for LLM agents, enabling fine-tuned models to reach 93% single-turn precision on a challenging benchmark with distractors."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"UniToolCall standardizes tool-use data and evaluation so that a fine-tuned 8B model reaches 93 percent precision on complex agent tasks."}],"snapshot_sha256":"c856544bc8314c70c944f2a5400d02f3103cec46110c04fa5a34462f158113d9"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.11557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tool-use capability is a fundamental component of LLM agents, enabling them to interact with external systems through structured function calls. However, existing research exhibits inconsistent interaction representations, largely overlooks the structural distribution of tool-use trajectories, and relies on incompatible evaluation benchmarks. We present UniToolCall, a unified framework for tool learning that standardizes the entire pipeline from toolset construction and dataset generation to evaluation. The framework curates a large tool pool of 22k+ tools and constructs a hybrid training corp","authors_text":"Changyu Zeng, Hao Wu, Wei Xing, Xiaoyu Shen, Xinghao Chen, Yifan Ge, Yijuan Liang, Ziyi Wu","cross_cats":[],"headline":"UniToolCall standardizes tool-use data and evaluation so that a fine-tuned 8B model reaches 93 percent precision on complex agent tasks.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-13T14:43:47Z","title":"UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.11557","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T15:48:16.551695Z","id":"caa9bdf3-de7b-40ee-b5b8-8f8689cd8c6d","model_set":{"reader":"grok-4.3"},"one_line_summary":"UniToolCall unifies tool-use data and evaluation for LLM agents, enabling fine-tuned models to reach 93% single-turn precision on a challenging benchmark with distractors.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"UniToolCall standardizes tool-use data and evaluation so that a fine-tuned 8B model reaches 93 percent precision on complex agent tasks.","strongest_claim":"fine-tuning Qwen3-8B on our dataset substantially improves tool-use performance. Under the distractor-heavy Hybrid-20 setting, achieves 93.0% single-turn Strict Precision, outperforming commercial models including GPT, Gemini, and Claude.","weakest_assumption":"That combining public datasets with structurally controlled synthetic trajectories and the Anchor Linkage mechanism produces training data that genuinely improves generalization to real tool-use scenarios without introducing artifacts or biases."}},"verdict_id":"caa9bdf3-de7b-40ee-b5b8-8f8689cd8c6d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2bdb3cf7a886729e367101e52ab70b8e5ffa6f212d0eb42cc0004138996be2ae","target":"record","created_at":"2026-05-26T02:04:10Z","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":"cdb4899a6ad5a029dc43705e8f54e1e0443fd297dc469d093840563cb429cde3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-13T14:43:47Z","title_canon_sha256":"fc7bc9e123e9af5cce266bca01d6cab06e7991356d33c5761ba10d67419b0f9c"},"schema_version":"1.0","source":{"id":"2604.11557","kind":"arxiv","version":2}},"canonical_sha256":"5e9fc97fbfcbc0475b737640bac32fcfbbb2ef75e0bd05da7906d773599c3ca0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e9fc97fbfcbc0475b737640bac32fcfbbb2ef75e0bd05da7906d773599c3ca0","first_computed_at":"2026-05-26T02:04:10.595138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:10.595138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EHFKQ7GQCZSUdE7DPHWGgCjcH8J6G99lhuD8O21ydfn+nIFlGMlzoDTovt3XIg6J1RPFpLMRgorQTM6rFsOtDA==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:10.595824Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.11557","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bdb3cf7a886729e367101e52ab70b8e5ffa6f212d0eb42cc0004138996be2ae","sha256:05e908089dcab22a08837b5d9343a0a1bbc6bd04403890c05981e8015d4fc69d"],"state_sha256":"4bdd3d45e2c456d62b648a0078916a25cd115174610b8bb30db6475219c976aa"}