{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:C7HZCGQ4XG57XBILJLQGM22JGT","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":"34559ac862a9d2dd7f05ea57a841d1b9edb2578eee30801645f2da1dc7e2ab01","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-22T20:21:00Z","title_canon_sha256":"0efee914fc0befe87bd6e07753c441235a4d74e95c9ff907e40ae0fbf1b73560"},"schema_version":"1.0","source":{"id":"2602.19327","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.19327","created_at":"2026-06-05T01:15:22Z"},{"alias_kind":"arxiv_version","alias_value":"2602.19327v3","created_at":"2026-06-05T01:15:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.19327","created_at":"2026-06-05T01:15:22Z"},{"alias_kind":"pith_short_12","alias_value":"C7HZCGQ4XG57","created_at":"2026-06-05T01:15:22Z"},{"alias_kind":"pith_short_16","alias_value":"C7HZCGQ4XG57XBIL","created_at":"2026-06-05T01:15:22Z"},{"alias_kind":"pith_short_8","alias_value":"C7HZCGQ4","created_at":"2026-06-05T01:15:22Z"}],"graph_snapshots":[{"event_id":"sha256:6bb622a8a35cec99010a678c82a3303b8ea5327a79a1e1ec6fc92ea4243e84d4","target":"graph","created_at":"2026-06-05T01:15:22Z","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/2602.19327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A significant portion of recent research on Large Language Model (LLM) alignment focuses on developing new policy optimization methods based on Group Relative Policy Optimization (GRPO). Two prominent directions have emerged: (i) a shift toward sequence-level importance sampling weights that better align with the sequence-level rewards used in many tasks, and (ii) alternatives to the PPO-style clipping that aim to avoid the associated loss of training signal and entropy collapse. We introduce Soft Sequence Policy Optimization, an off-policy reinforcement learning objective that incorporates so","authors_text":"Maksim Kryzhanovskiy, Roman Ischenko, Svetlana Glazyrina","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-22T20:21:00Z","title":"Soft Sequence Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.19327","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":"sha256:7c440965b8c6e72b46f104d3dc83ad4399b559edfaba031b27b03d1b1fc1e3f4","target":"record","created_at":"2026-06-05T01:15:22Z","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":"34559ac862a9d2dd7f05ea57a841d1b9edb2578eee30801645f2da1dc7e2ab01","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-22T20:21:00Z","title_canon_sha256":"0efee914fc0befe87bd6e07753c441235a4d74e95c9ff907e40ae0fbf1b73560"},"schema_version":"1.0","source":{"id":"2602.19327","kind":"arxiv","version":3}},"canonical_sha256":"17cf911a1cb9bbfb850b4ae0666b4934d35c5d5e2690eb2ca3861c3bb34aa361","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17cf911a1cb9bbfb850b4ae0666b4934d35c5d5e2690eb2ca3861c3bb34aa361","first_computed_at":"2026-06-05T01:15:22.160802Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:22.160802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U7anXg/W7CAbb8EGkcd03EvtV5Y7m6OJpYouSG2cwV/3EZvcTet4t6bF/2ngELsnn3k9c9HSVtwsrNCfaelPBg==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:22.161354Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.19327","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c440965b8c6e72b46f104d3dc83ad4399b559edfaba031b27b03d1b1fc1e3f4","sha256:6bb622a8a35cec99010a678c82a3303b8ea5327a79a1e1ec6fc92ea4243e84d4"],"state_sha256":"497c1e93c22c195dbd568a8d908591e773ea47dd036aa85686271c4da3ae41ae"}