{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NMPFPV7BKVVNPKG5H2DVQF3IS4","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":"1d2e98e96454addd06cd055db3d84359a42d5af1b1f9df65ecaaaf811c0e2d14","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-24T17:57:34Z","title_canon_sha256":"851157b2eb5242c3d4ddb3dd5d3cb9ef5650c6042d09e0252c81ae75249b5ffa"},"schema_version":"1.0","source":{"id":"2509.20357","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.20357","created_at":"2026-08-18T01:14:00Z"},{"alias_kind":"arxiv_version","alias_value":"2509.20357v2","created_at":"2026-08-18T01:14:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.20357","created_at":"2026-08-18T01:14:00Z"},{"alias_kind":"pith_short_12","alias_value":"NMPFPV7BKVVN","created_at":"2026-08-18T01:14:00Z"},{"alias_kind":"pith_short_16","alias_value":"NMPFPV7BKVVNPKG5","created_at":"2026-08-18T01:14:00Z"},{"alias_kind":"pith_short_8","alias_value":"NMPFPV7B","created_at":"2026-08-18T01:14:00Z"}],"graph_snapshots":[{"event_id":"sha256:063ab364ca3b7d45d8526bbb0280872b38646e0f0c37de930f10c9b490820856","target":"graph","created_at":"2026-08-18T01:14:00Z","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/2509.20357/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) trains language models to use long chain-of-thought reasoning (CoT) in domains like mathematics and code with rule-based verifiers. However, long CoT learned through RLVR does not generalize well to open-ended tasks -- such as writing essay outlines or making meal plans -- where humans reason routinely. This paper establishes the benefits of long CoT for general-purpose chat capabilities and introduces RL with Model-rewarded Thinking (RLMT)1, which pushes RLVR beyond verifiable domains. Using diverse real-world prompts, RLMT requires LMs to","authors_text":"Adithya Bhaskar, Danqi Chen, Xi Ye","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-24T17:57:34Z","title":"Language Models that Think, Chat Better"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.20357","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":"sha256:1f2e1c3edbdea5c3c3278e3122b85f7d4446ab84a8a2ed283c518173eebec833","target":"record","created_at":"2026-08-18T01:14:00Z","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":"1d2e98e96454addd06cd055db3d84359a42d5af1b1f9df65ecaaaf811c0e2d14","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-24T17:57:34Z","title_canon_sha256":"851157b2eb5242c3d4ddb3dd5d3cb9ef5650c6042d09e0252c81ae75249b5ffa"},"schema_version":"1.0","source":{"id":"2509.20357","kind":"arxiv","version":2}},"canonical_sha256":"6b1e57d7e1556ad7a8dd3e87581768971f5a488f4876ccd502bf1017fb54d783","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b1e57d7e1556ad7a8dd3e87581768971f5a488f4876ccd502bf1017fb54d783","first_computed_at":"2026-08-18T01:14:00.851120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-18T01:14:00.851120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CZVIms3O7papaanh/JM2jhhvi/rFzmrEZtr0/frfXY2pzZmAA3r8p2t3fchjVio267Mgv/RbkSMHfX+VPt4GCQ==","signature_status":"signed_v1","signed_at":"2026-08-18T01:14:00.852840Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.20357","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f2e1c3edbdea5c3c3278e3122b85f7d4446ab84a8a2ed283c518173eebec833","sha256:063ab364ca3b7d45d8526bbb0280872b38646e0f0c37de930f10c9b490820856"],"state_sha256":"395f77e52a939a2f519cfcb0f4e0b1ecf28d0eec715447c36ab85304f26e05bb"}