{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BJ3Q4N7VZYQ2GTQI5CV7QNXWN5","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":"2a2fabc3090d96092abaa644c319e4a63277a363a6a371c2fcee98945e5b5872","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-01T21:20:57Z","title_canon_sha256":"6a5a00df9ca5f56ae095af2360682af032fec0f311d44524e1751c97f4a7eccb"},"schema_version":"1.0","source":{"id":"2607.01480","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01480","created_at":"2026-07-03T00:17:01Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01480v1","created_at":"2026-07-03T00:17:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01480","created_at":"2026-07-03T00:17:01Z"},{"alias_kind":"pith_short_12","alias_value":"BJ3Q4N7VZYQ2","created_at":"2026-07-03T00:17:01Z"},{"alias_kind":"pith_short_16","alias_value":"BJ3Q4N7VZYQ2GTQI","created_at":"2026-07-03T00:17:01Z"},{"alias_kind":"pith_short_8","alias_value":"BJ3Q4N7V","created_at":"2026-07-03T00:17:01Z"}],"graph_snapshots":[{"event_id":"sha256:26ce7799833cbe548c1dee77593e9bfa06d4b8edebc1bfafe173b0bdf1d6df40","target":"graph","created_at":"2026-07-03T00:17:01Z","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/2607.01480/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR), along with recent selfdistillation variants such as SDPO, evaluates each rollout against a verifier and updates the policy from that episode-level signal. However, the richer procedural information in the rollout is rarely retained or reused. Across episodes and epochs, the model repeatedly encounters related problems under a changing policy, producing cross-episode signals that episode-local updates cannot capture: which strategies consistently pass verification, which failure modes persist, which patterns recur. We propose Procedural Mem","authors_text":"Bo Pang, Semih Yavuz, Shafiq Joty, Srijan Bansal, Yang Li, Ye Liu, Yifei Ming, Zeyu Leo Liu, Zixuan Ke","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-01T21:20:57Z","title":"Procedural Memory Distillation: Online Reflection for Self-Improving Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01480","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":"sha256:3883758bea6167167239b58ba4943165acbcbe618e837d30043f6e1c9e09865e","target":"record","created_at":"2026-07-03T00:17:01Z","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":"2a2fabc3090d96092abaa644c319e4a63277a363a6a371c2fcee98945e5b5872","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-01T21:20:57Z","title_canon_sha256":"6a5a00df9ca5f56ae095af2360682af032fec0f311d44524e1751c97f4a7eccb"},"schema_version":"1.0","source":{"id":"2607.01480","kind":"arxiv","version":1}},"canonical_sha256":"0a770e37f5ce21a34e08e8abf836f66f77801c24ab300ed194a15d8ea70cc75e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a770e37f5ce21a34e08e8abf836f66f77801c24ab300ed194a15d8ea70cc75e","first_computed_at":"2026-07-03T00:17:01.878638Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T00:17:01.878638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vijmYlqMzZmiZCunC+mhal+VHH3iJrAERjCeiLA3h57PcY70I73gU5AtPVOiS53hKIhUdEd0t8J0jiogMqoSDQ==","signature_status":"signed_v1","signed_at":"2026-07-03T00:17:01.879037Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01480","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3883758bea6167167239b58ba4943165acbcbe618e837d30043f6e1c9e09865e","sha256:26ce7799833cbe548c1dee77593e9bfa06d4b8edebc1bfafe173b0bdf1d6df40"],"state_sha256":"6e555e6b74161d10e5048cd8e6692f6a0a5043d08270d03f133e6dfa94a39556"}