{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IVD4CGERAE7HTU6IDS2TMQR75Z","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":"4777d46092fec732826fdfd1495f1a97800b1bd54837e0fb2e64190509249fb5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-02T03:05:52Z","title_canon_sha256":"2146663ff97eb3b5d89c5256be95a40e99616ff51411aa6a64b36086b1ee83b7"},"schema_version":"1.0","source":{"id":"2502.00640","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00640","created_at":"2026-07-05T11:45:14Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00640v3","created_at":"2026-07-05T11:45:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00640","created_at":"2026-07-05T11:45:14Z"},{"alias_kind":"pith_short_12","alias_value":"IVD4CGERAE7H","created_at":"2026-07-05T11:45:14Z"},{"alias_kind":"pith_short_16","alias_value":"IVD4CGERAE7HTU6I","created_at":"2026-07-05T11:45:14Z"},{"alias_kind":"pith_short_8","alias_value":"IVD4CGER","created_at":"2026-07-05T11:45:14Z"}],"graph_snapshots":[{"event_id":"sha256:336c03707ca3d0057bb76c920a5db0bb6e40d395d23ffcaa5c77e30c15cb40ea","target":"graph","created_at":"2026-07-05T11:45:14Z","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/2502.00640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models are typically trained with next-turn rewards, limiting their ability to optimize for long-term interaction. As a result, they often respond passively to ambiguous or open-ended user requests, failing to help users reach their ultimate intents and leading to inefficient conversations. To address these limitations, we introduce CollabLLM, a novel and general training framework that enhances multiturn human-LLM collaboration. Its key innovation is a collaborative simulation that estimates the long-term contribution of responses using Multiturn-aware Rewards. By reinforcement","authors_text":"Baolin Peng, Gavin Li, Hao Cheng, James Zou, Jianfeng Gao, Jure Leskovec, Michel Galley, Shirley Wu, Weixin Cai, Yao Dou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-02T03:05:52Z","title":"CollabLLM: From Passive Responders to Active Collaborators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00640","kind":"arxiv","version":3},"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:e622ee281202eae1346a9a9f13939f0ab1a45578ec2bf3e808d48ce4ea369467","target":"record","created_at":"2026-07-05T11:45:14Z","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":"4777d46092fec732826fdfd1495f1a97800b1bd54837e0fb2e64190509249fb5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-02T03:05:52Z","title_canon_sha256":"2146663ff97eb3b5d89c5256be95a40e99616ff51411aa6a64b36086b1ee83b7"},"schema_version":"1.0","source":{"id":"2502.00640","kind":"arxiv","version":3}},"canonical_sha256":"4547c11891013e79d3c81cb536423fee4375f1d19785e6b421805dbc92e55895","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4547c11891013e79d3c81cb536423fee4375f1d19785e6b421805dbc92e55895","first_computed_at":"2026-07-05T11:45:14.127197Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:14.127197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IQISdHUxBx92pr7iIkeWPFgJ7sM3Akrzl4kzfsHBfs0jCsGfUAIneXdsDr0kWESPV3YD7nKpeXp/ls7aLY0YAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:14.127635Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.00640","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e622ee281202eae1346a9a9f13939f0ab1a45578ec2bf3e808d48ce4ea369467","sha256:336c03707ca3d0057bb76c920a5db0bb6e40d395d23ffcaa5c77e30c15cb40ea"],"state_sha256":"70c436215f3a5b870eace9f3cb2843155a777f5bd9a132396ed09f9ba4cf464e"}