{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RC7OS5FPOW35M2HAVKV2KP2VGE","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":"5c286aaecaa1995f82478e636bb84d1f925b95c2a18c58217f438a4120cedf46","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T05:47:28Z","title_canon_sha256":"f2f03f00f06407a4d7f06019c330421fe279b98f1c53b0d3619e63bf7a5077e0"},"schema_version":"1.0","source":{"id":"2504.02882","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02882","created_at":"2026-07-05T11:36:30Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02882v2","created_at":"2026-07-05T11:36:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02882","created_at":"2026-07-05T11:36:30Z"},{"alias_kind":"pith_short_12","alias_value":"RC7OS5FPOW35","created_at":"2026-07-05T11:36:30Z"},{"alias_kind":"pith_short_16","alias_value":"RC7OS5FPOW35M2HA","created_at":"2026-07-05T11:36:30Z"},{"alias_kind":"pith_short_8","alias_value":"RC7OS5FP","created_at":"2026-07-05T11:36:30Z"}],"graph_snapshots":[{"event_id":"sha256:a9ba5f74ef62701aaabeecdd621b87fa8465b37cf3a5c93898acf6d7063fa5dc","target":"graph","created_at":"2026-07-05T11:36:30Z","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/2504.02882/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tool-Augmented Larage Language Models (TA-LLMs) have shown promise in real-world applications, but face challenges in handling incomplete queries and out-of-scope requests. While existing approaches rely mainly on Supervised Fine-Tuning with expert trajectories, we propose DiaTool-DPO, a novel method that enhances TA-LLM's dialogue capabilities through Direct Preference Optimization. We model TA-LLM interactions as a Markov Decision Process with 5 distinct dialogue states and categorize user queries into 3 types based on their state transition trajectories. We automatically construct paired tr","authors_text":"Byeongil Ko, Daniel Lee, Donghun Lee, EungGyun Kim, Gaeun Seo, Junrae Cho, Kihyun Kim, Myeongcheol Shin, Shinbok Lee, Sunghee Jung","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T05:47:28Z","title":"DiaTool-DPO: Multi-Turn Direct Preference Optimization for Tool-Augmented Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02882","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":"sha256:32f112b3f0847f62e6ef867d4caedae97975902d8813571815283d8f62cb51a6","target":"record","created_at":"2026-07-05T11:36:30Z","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":"5c286aaecaa1995f82478e636bb84d1f925b95c2a18c58217f438a4120cedf46","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T05:47:28Z","title_canon_sha256":"f2f03f00f06407a4d7f06019c330421fe279b98f1c53b0d3619e63bf7a5077e0"},"schema_version":"1.0","source":{"id":"2504.02882","kind":"arxiv","version":2}},"canonical_sha256":"88bee974af75b7d668e0aaaba53f553110d5b8bb3b522c42e74a78a6b34ebca1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88bee974af75b7d668e0aaaba53f553110d5b8bb3b522c42e74a78a6b34ebca1","first_computed_at":"2026-07-05T11:36:30.302831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:30.302831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0NDpdcOfnRtLwF34yzs+W1pr3EXYfT3AaTPAVp8cC5wXwZHeLdlun5FwtJQ7S+Uyg5mUo8GR2K+pXNNbN2IYAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:30.303762Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.02882","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32f112b3f0847f62e6ef867d4caedae97975902d8813571815283d8f62cb51a6","sha256:a9ba5f74ef62701aaabeecdd621b87fa8465b37cf3a5c93898acf6d7063fa5dc"],"state_sha256":"422f301d86406b3f309d229f82b711dae29a6be20d1eb2198ba93118d0c23dd3"}