{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:W2X5MHSVTKQ6MHGXROEXCMAPMA","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":"2f52856de5b1cefd7b511e5f4640a8d025f84029b405fe5797143e1d41988a83","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T13:36:23Z","title_canon_sha256":"33222e390d258af0e54affb94862f982d75f527868706a2d4fa2913ac4197e99"},"schema_version":"1.0","source":{"id":"2607.19450","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19450","created_at":"2026-07-23T00:23:50Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19450v1","created_at":"2026-07-23T00:23:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19450","created_at":"2026-07-23T00:23:50Z"},{"alias_kind":"pith_short_12","alias_value":"W2X5MHSVTKQ6","created_at":"2026-07-23T00:23:50Z"},{"alias_kind":"pith_short_16","alias_value":"W2X5MHSVTKQ6MHGX","created_at":"2026-07-23T00:23:50Z"},{"alias_kind":"pith_short_8","alias_value":"W2X5MHSV","created_at":"2026-07-23T00:23:50Z"}],"graph_snapshots":[{"event_id":"sha256:56241b321cf3bef99c199a518d7e43044f52dbfd949b220d93d46de8ea005616","target":"graph","created_at":"2026-07-23T00:23:50Z","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/2607.19450/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale online reinforcement learning (RL) is the predominant means of eliciting advanced abilities including long-term reasoning and agentic tool use in large language models (LLMs). However, continuing to scale it across vast task domains of interest remains challenging in both computational infrastructure and cost, especially when considering RL as merely a one-off learning stage. Recently, a widely used technique for distilling knowledge across various domains and training stages, multi-teacher on-policy distillation (MOPD), helps to decouple the RL stage, saving costs, while maintaini","authors_text":"Fang Wang, Xiaoxin Chen, Yunjie Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T13:36:23Z","title":"REGEN: Replay-recycling for Expert-to-Generalist distillation with Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19450","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":"sha256:7d39225d48e945a727791de73d2add9386ade5e1754f1aa0e37dd24427d7a39f","target":"record","created_at":"2026-07-23T00:23:50Z","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":"2f52856de5b1cefd7b511e5f4640a8d025f84029b405fe5797143e1d41988a83","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T13:36:23Z","title_canon_sha256":"33222e390d258af0e54affb94862f982d75f527868706a2d4fa2913ac4197e99"},"schema_version":"1.0","source":{"id":"2607.19450","kind":"arxiv","version":1}},"canonical_sha256":"b6afd61e559aa1e61cd78b8971300f601c9493194843634c7e651db6e6cab0a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6afd61e559aa1e61cd78b8971300f601c9493194843634c7e651db6e6cab0a3","first_computed_at":"2026-07-23T00:23:50.404405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-23T00:23:50.404405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kDu3SrEIEnYpyhVnPocbSdX1lal4GBPzBFGS8BMGxkGzDdgS//OQM+s/JvWjuPC6jEWRDlsriFkrCgjeyInTDA==","signature_status":"signed_v1","signed_at":"2026-07-23T00:23:50.405413Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.19450","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d39225d48e945a727791de73d2add9386ade5e1754f1aa0e37dd24427d7a39f","sha256:56241b321cf3bef99c199a518d7e43044f52dbfd949b220d93d46de8ea005616"],"state_sha256":"1f4194b4f45a9dce177ca8b085369a4fef6c06de383f00fcdea4254a044d3ddd"}