{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PBNEBYWPMSLX6CLPF476XANXS5","merge_version":"pith-open-graph-merge-v1","event_count":12,"valid_event_count":12,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"89596fb6158cd2a271a48191ed152a4f6153d9db1f8e2fd9f13380fbfb3017b4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T17:03:22Z","title_canon_sha256":"45dbced9692e7ff704acf77c8b0dc4c121d1c450fa1e185bd974aa4a934e266e"},"schema_version":"1.0","source":{"id":"2605.22731","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22731","created_at":"2026-05-22T02:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22731v1","created_at":"2026-05-22T02:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22731","created_at":"2026-05-22T02:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"PBNEBYWPMSLX","created_at":"2026-05-22T02:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"PBNEBYWPMSLX6CLP","created_at":"2026-05-22T02:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"PBNEBYWP","created_at":"2026-05-22T02:04:52Z"}],"graph_snapshots":[{"event_id":"sha256:e75756da93b578e9edfaea57d33fa8b4a9a8c5a7479b1db43e16ca199a8ce6d2","target":"graph","created_at":"2026-05-22T02:04:52Z","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/2605.22731/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model post-training methods such as supervised fine-tuning (SFT), reinforcement learning (RL), and distillation are often analyzed through their loss functions: maximum likelihood, policy gradients, forward KL, reverse KL, or related objective-level variants. We study a complementary factor: the state distribution on which supervision is applied. For an autoregressive policy, a state is a prompt plus generated prefix. SFT trains on fixed dataset states, while RL and on-policy distillation (OPD) train on states induced by the current learner. We formalize post-training as state-d","authors_text":"Dong Nie","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T17:03:22Z","title":"Post-Training is About States, Not Tokens: A State Distribution View of SFT, RL, and On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22731","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:bf0fd065d4061d040cb3a027c44f3b32442f79b9d448457f9ce5e53c12dc4890","target":"record","created_at":"2026-05-22T02:04:52Z","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":"89596fb6158cd2a271a48191ed152a4f6153d9db1f8e2fd9f13380fbfb3017b4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T17:03:22Z","title_canon_sha256":"45dbced9692e7ff704acf77c8b0dc4c121d1c450fa1e185bd974aa4a934e266e"},"schema_version":"1.0","source":{"id":"2605.22731","kind":"arxiv","version":1}},"canonical_sha256":"785a40e2cf64977f096f2f3feb81b7977f647b2244a1fe925e4aa6d1caf252c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"785a40e2cf64977f096f2f3feb81b7977f647b2244a1fe925e4aa6d1caf252c1","first_computed_at":"2026-05-22T02:04:52.346443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T02:04:52.346443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XKxfrKjHhR1EHyWkZ5g4gkwk4EnSPKPuw9O5AHX7f0FRrxfNB+TtHCFvc/03E9WkqD+UdQ+umxAzkZWkiroHDg==","signature_status":"signed_v1","signed_at":"2026-05-22T02:04:52.347226Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22731","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:1aa153f7171bf77d4e6312f128583e3e83395798f32402195f9cf513653d2c5d","sha256:3228e0388ebc1baa422d097462d024e2763e4d670fc1de9daa5232b5e9f170e4","sha256:33f7c1116fa9633469ebf32b25b7dd50c09e7a0162f8e17f4c67eba614d8f3bf","sha256:6fb47cd916e82936456bc38ddfd505d234e2fbe6b1d4ecefb6630089fd5262d0","sha256:8c1907d4fab08ae9cd9615d0f9fac56f786d9d06555e617de2f83360e9f9b6b4","sha256:ca5a34179868447ca07eec6858556734c1c2a77665fc03ad41d396caff7625ca","sha256:d9c6a643ea4e9a7f389ece8deda1c28c169ca5205f4704f704b423ec6ce717db","sha256:ddb3af0488bedb4744a915ea52d84a1463c553acbb4cd35ce910865c1fe761d5","sha256:df10573603517da871665ce8647516beca91d91347bc8350f05cf8825cac7c0f","sha256:ebac33cee1a6d1af39fa00432187fbdca9433b413e43d30e9b3de4e8c7a08ede"]}],"invalid_events":[],"applied_event_ids":["sha256:bf0fd065d4061d040cb3a027c44f3b32442f79b9d448457f9ce5e53c12dc4890","sha256:e75756da93b578e9edfaea57d33fa8b4a9a8c5a7479b1db43e16ca199a8ce6d2"],"state_sha256":"24a9f94bdfe49f85cab06ddbf8350a108eaa18cd660fba62d9aa53a6963385ed"}