{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LP2MQEYNGEGACGEBS3TYWG5UY2","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":"72f2949291cfa6899cc70238d10f9e68d0ea5a5f2126bd07017398f5bcdf46c7","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T10:47:27Z","title_canon_sha256":"0cbaedbc4229e95ae9ae59d72b344963c09f9aeaf0e4f47656547dea7524f285"},"schema_version":"1.0","source":{"id":"2607.18955","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18955","created_at":"2026-07-22T01:23:21Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18955v1","created_at":"2026-07-22T01:23:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18955","created_at":"2026-07-22T01:23:21Z"},{"alias_kind":"pith_short_12","alias_value":"LP2MQEYNGEGA","created_at":"2026-07-22T01:23:21Z"},{"alias_kind":"pith_short_16","alias_value":"LP2MQEYNGEGACGEB","created_at":"2026-07-22T01:23:21Z"},{"alias_kind":"pith_short_8","alias_value":"LP2MQEYN","created_at":"2026-07-22T01:23:21Z"}],"graph_snapshots":[{"event_id":"sha256:d8a6d20a4b61459e3ab6a3d3d74d5e3294ecd03da072a644de9bcff64dea16b0","target":"graph","created_at":"2026-07-22T01:23:21Z","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/2607.18955/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models on tasks such as mathematical reasoning and code generation. However, most RLVR methods assign a scalar outcome reward to an entire trajectory, resulting in sparse supervision and limited token-level credit assignment. On-policy distillation (OPD) provides denser supervision by distilling token-level distributions from a stronger teacher model, but requires an additional teacher and typically assumes a shared vocabulary. On-policy self-distillation (OPSD) removes","authors_text":"Bing Qin, Linyang Li, Peiji Li, Qipeng Guo, Qiye Cai, Tao Gui, Xiaocheng Feng, Yicheng Zou, Yichuan Ma, Yongkang Chen","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T10:47:27Z","title":"H$^2$SD: Hybrid Hindsight Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18955","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:b73b17167e2563288f18579fbcfae062c09f2901c1d24d1879f2328ea856d4a2","target":"record","created_at":"2026-07-22T01:23:21Z","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":"72f2949291cfa6899cc70238d10f9e68d0ea5a5f2126bd07017398f5bcdf46c7","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T10:47:27Z","title_canon_sha256":"0cbaedbc4229e95ae9ae59d72b344963c09f9aeaf0e4f47656547dea7524f285"},"schema_version":"1.0","source":{"id":"2607.18955","kind":"arxiv","version":1}},"canonical_sha256":"5bf4c8130d310c01188196e78b1bb4c6b10b381b1bbfda3a90c3f6eec64b6d24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bf4c8130d310c01188196e78b1bb4c6b10b381b1bbfda3a90c3f6eec64b6d24","first_computed_at":"2026-07-22T01:23:21.660940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T01:23:21.660940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WwISb91sz68cfb1ucawZnmFgomQmZyUL0Pxxrgh+AT7gGL2IUBhWaHl7Z6KZqeUargaH/4kg4cfOWzDgy5GJDQ==","signature_status":"signed_v1","signed_at":"2026-07-22T01:23:21.661741Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18955","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b73b17167e2563288f18579fbcfae062c09f2901c1d24d1879f2328ea856d4a2","sha256:d8a6d20a4b61459e3ab6a3d3d74d5e3294ecd03da072a644de9bcff64dea16b0"],"state_sha256":"6cfb6a2092cb84281df82e3f69274b3dde55d020b698b02bdb509d0f2ca39e14"}