{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7TGMMVSJLI3FOOAINZGZYOCQDC","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":"3198d058a4fe3c1807f6a08cea0a10962534c102df7d0631dc5dc85762d69108","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T23:28:06Z","title_canon_sha256":"04829bceb7f7f453107e38e70a01e31ed3bc7dc7a6fc64423a5da441447b587c"},"schema_version":"1.0","source":{"id":"2608.02951","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02951","created_at":"2026-08-05T00:44:13Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02951v1","created_at":"2026-08-05T00:44:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02951","created_at":"2026-08-05T00:44:13Z"},{"alias_kind":"pith_short_12","alias_value":"7TGMMVSJLI3F","created_at":"2026-08-05T00:44:13Z"},{"alias_kind":"pith_short_16","alias_value":"7TGMMVSJLI3FOOAI","created_at":"2026-08-05T00:44:13Z"},{"alias_kind":"pith_short_8","alias_value":"7TGMMVSJ","created_at":"2026-08-05T00:44:13Z"}],"graph_snapshots":[{"event_id":"sha256:7669fc7eba62dd76551a06ba5922dffa25298829b1b300015524db9a77778464","target":"graph","created_at":"2026-08-05T00:44:13Z","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/2608.02951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference-based reinforcement learning (PbRL) for general stochastic MDPs often requires training a reward model. Existing reward-model-free methods are either restricted to bandits or deterministic MDPs, such as DPO or P3O, or use zeroth-order, gradient-free optimization, which in general exhibits a slower convergence rate than gradient-based algorithms. Furthermore, existing reward-model-free preference-based RL algorithms almost exclusively use trajectory-level feedback, which can require significant effort from a human evaluator when trajectories are long. On the other hand, segments are ","authors_text":"Evan Assmus, Lei Ying, Qining Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T23:28:06Z","title":"SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02951","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":"sha256:9d9abbdc0f20c764f4b0dce34668c5644caf9e259c46d452b61de1ef6bddefec","target":"record","created_at":"2026-08-05T00:44:13Z","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":"3198d058a4fe3c1807f6a08cea0a10962534c102df7d0631dc5dc85762d69108","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T23:28:06Z","title_canon_sha256":"04829bceb7f7f453107e38e70a01e31ed3bc7dc7a6fc64423a5da441447b587c"},"schema_version":"1.0","source":{"id":"2608.02951","kind":"arxiv","version":1}},"canonical_sha256":"fcccc656495a365738086e4d9c385018a37da59b24081c23c6122c486fb2eeb9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fcccc656495a365738086e4d9c385018a37da59b24081c23c6122c486fb2eeb9","first_computed_at":"2026-08-05T00:44:13.260063Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:44:13.260063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SMo74aNqwasFjxDhfkmFRYiW1g5cOrD9ctLOTyTE9qxe2pmy12VKcR0nPMt3LQN/XTjQgAp/8LvOI8xQvrvmDg==","signature_status":"signed_v1","signed_at":"2026-08-05T00:44:13.262432Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02951","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d9abbdc0f20c764f4b0dce34668c5644caf9e259c46d452b61de1ef6bddefec","sha256:7669fc7eba62dd76551a06ba5922dffa25298829b1b300015524db9a77778464"],"state_sha256":"a439c10c475d81f8efd1bc4c64ae7dcab9da655e9d397c15e9fd17e25104aa39"}