{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VCFS2ZGNFCG4C6AKQ2TSLLZ3HZ","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":"d3e1f20fb786842b4ae00af71f121ed8b762d2534c2ec10f3153a216763ac812","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-29T09:56:15Z","title_canon_sha256":"0cb3c6102e1868607be38be2de785ac4c95a26dda53a60e6547bbb2a35429043"},"schema_version":"1.0","source":{"id":"2601.21476","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21476","created_at":"2026-07-09T01:19:51Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21476v2","created_at":"2026-07-09T01:19:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21476","created_at":"2026-07-09T01:19:51Z"},{"alias_kind":"pith_short_12","alias_value":"VCFS2ZGNFCG4","created_at":"2026-07-09T01:19:51Z"},{"alias_kind":"pith_short_16","alias_value":"VCFS2ZGNFCG4C6AK","created_at":"2026-07-09T01:19:51Z"},{"alias_kind":"pith_short_8","alias_value":"VCFS2ZGN","created_at":"2026-07-09T01:19:51Z"}],"graph_snapshots":[{"event_id":"sha256:ddcbac4148f1d4d2a1e3c05efe047410d5c43a13cb59dccb3ff3b73a81d8bb21","target":"graph","created_at":"2026-07-09T01:19:51Z","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/2601.21476/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy reinforcement learning (RL) for language model post-training suffers from a fundamental tension: as training progresses, policy entropy collapses and sampling diversity diminishes, causing the model to ``forget'' its own earlier exploratory capacity. While off-policy data can restore diversity, existing methods mix entire trajectories at the sequence level, introducing severe policy mismatch and training instability. We argue that the core question is not \\emph{whether} to use off-policy data, but \\emph{where} in the sequence it should appear. Based on this insight, we propose \\textb","authors_text":"Chenxi Sun, Deyi Xiong, Lei Yang, Renren Jin, Wei Bi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-29T09:56:15Z","title":"Thinking Seeds: Leveraging Historical Diversity for Position-Aware RL in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21476","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":"sha256:3a4a6d6734534e7d0cd2379cf1eb7cec4190e63872148b07cc99f9c5a3405895","target":"record","created_at":"2026-07-09T01:19:51Z","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":"d3e1f20fb786842b4ae00af71f121ed8b762d2534c2ec10f3153a216763ac812","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-29T09:56:15Z","title_canon_sha256":"0cb3c6102e1868607be38be2de785ac4c95a26dda53a60e6547bbb2a35429043"},"schema_version":"1.0","source":{"id":"2601.21476","kind":"arxiv","version":2}},"canonical_sha256":"a88b2d64cd288dc1780a86a725af3b3e67e315d646b330eb4d17b84cdc1c2844","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a88b2d64cd288dc1780a86a725af3b3e67e315d646b330eb4d17b84cdc1c2844","first_computed_at":"2026-07-09T01:19:51.560813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T01:19:51.560813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rgVW3vlhIVE2PVl3uSDCzxptS5Nt07E4t1OAdcapGEHkL78udUtkFomacj91wQz0yjvFetHK0mZs4+xrx3tMBQ==","signature_status":"signed_v1","signed_at":"2026-07-09T01:19:51.561268Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.21476","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a4a6d6734534e7d0cd2379cf1eb7cec4190e63872148b07cc99f9c5a3405895","sha256:ddcbac4148f1d4d2a1e3c05efe047410d5c43a13cb59dccb3ff3b73a81d8bb21"],"state_sha256":"3ee5082754820c02cda1eba71f53b2ef0e00ddbe283921552805939d748aab4b"}