{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NSOQQE427R7XHA44AF7NLZACPV","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":"4aa7940c5a9d33c0e59209d537ddcaf52aa0d122380c43612046425aa4f9f44a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T03:52:20Z","title_canon_sha256":"e501ce8b74559ae2de081c9358563de6c18aee7515e54bff90c926c97f2423bd"},"schema_version":"1.0","source":{"id":"2506.03541","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03541","created_at":"2026-07-05T11:15:29Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03541v1","created_at":"2026-07-05T11:15:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03541","created_at":"2026-07-05T11:15:29Z"},{"alias_kind":"pith_short_12","alias_value":"NSOQQE427R7X","created_at":"2026-07-05T11:15:29Z"},{"alias_kind":"pith_short_16","alias_value":"NSOQQE427R7XHA44","created_at":"2026-07-05T11:15:29Z"},{"alias_kind":"pith_short_8","alias_value":"NSOQQE42","created_at":"2026-07-05T11:15:29Z"}],"graph_snapshots":[{"event_id":"sha256:3c585f746fdb37eb5c3c9744eef0cdabd829bfaad5d7118242452a0fa9858943","target":"graph","created_at":"2026-07-05T11:15:29Z","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/2506.03541/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) continue to set new standards in knowledge-intensive and complex reasoning tasks, yet their high computational demands limit widespread adoption. While distilling large models into smaller ones offers a sustainable solution, current techniques--such as static knowledge distillation, resource-intensive reinforcement learning from human feedback, or limited self-reflection--struggle to yield substantial and lasting performance gains. In this paper, we present a novel Debate and Reflect (D&R) framework that orchestrates multi-turn debates between smaller models and st","authors_text":"Heyan Huang, Lizi Liao, Xiaofeng Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T03:52:20Z","title":"Debate, Reflect, and Distill: Multi-Agent Feedback with Tree-Structured Preference Optimization for Efficient Language Model Enhancement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03541","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":"sha256:7d06ca15b69704966f7e17ea41f357262dab9cc69eacc504d4640d160ba63976","target":"record","created_at":"2026-07-05T11:15:29Z","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":"4aa7940c5a9d33c0e59209d537ddcaf52aa0d122380c43612046425aa4f9f44a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T03:52:20Z","title_canon_sha256":"e501ce8b74559ae2de081c9358563de6c18aee7515e54bff90c926c97f2423bd"},"schema_version":"1.0","source":{"id":"2506.03541","kind":"arxiv","version":1}},"canonical_sha256":"6c9d08139afc7f73839c017ed5e4027d6619796ea2b736316eb4da6bf63d1774","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c9d08139afc7f73839c017ed5e4027d6619796ea2b736316eb4da6bf63d1774","first_computed_at":"2026-07-05T11:15:29.385845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:29.385845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KJZZmF3rZpz0O45wtmU2PN5IbPKLmGeMtFEjAdhuxbDRM5Ug3mHKCnNM9utNpu7hRlb00iqt3qxBvQStmh/4Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:29.386415Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03541","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d06ca15b69704966f7e17ea41f357262dab9cc69eacc504d4640d160ba63976","sha256:3c585f746fdb37eb5c3c9744eef0cdabd829bfaad5d7118242452a0fa9858943"],"state_sha256":"e2a925a51873ed7ae385edc2b1ef8a0e5682e34e66eed066e1856b1def3008ba"}