{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5BFNLN7C4LC4HESE3CFA5YC2KY","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":"23977264749dc4bbcff2594012f796ddb2550b06b2f0f3449e304b395aa350fc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T07:19:47Z","title_canon_sha256":"0e134535d8327a7234acd8a84df314fb28a8a41dc8584a0f6f32d37d9f3d8a40"},"schema_version":"1.0","source":{"id":"2605.29495","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29495","created_at":"2026-05-29T01:05:42Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29495v1","created_at":"2026-05-29T01:05:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29495","created_at":"2026-05-29T01:05:42Z"},{"alias_kind":"pith_short_12","alias_value":"5BFNLN7C4LC4","created_at":"2026-05-29T01:05:42Z"},{"alias_kind":"pith_short_16","alias_value":"5BFNLN7C4LC4HESE","created_at":"2026-05-29T01:05:42Z"},{"alias_kind":"pith_short_8","alias_value":"5BFNLN7C","created_at":"2026-05-29T01:05:42Z"}],"graph_snapshots":[{"event_id":"sha256:9d4b587e13aec9fc825e724d5a5d215c5f651db61ce30454bb81bf881d2ced7b","target":"graph","created_at":"2026-05-29T01:05:42Z","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/2605.29495/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continual supervised fine-tuning (SFT) is the de facto recipe for adapting large language models (LLMs) to a stream of downstream tasks, but it suffers from catastrophic forgetting of earlier capabilities. Recent work shows that on-policy signals -- training on the model's own outputs -- reduce forgetting more reliably than off-policy supervision. Existing on-policy methods route this signal through a new training objective (e.g., self-distillation losses with a teacher copy), inheriting an extra forward pass, schedule sensitivity, and stylistic drift from the teacher.We instead route the on-p","authors_text":"Dongyang Xu, Jiaqi Huang, Meng Zhang, Taojie Zhu, Xin Chen, Yan Chen, Yizhi Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T07:19:47Z","title":"On-Policy Replay for Continual Supervised Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29495","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":"sha256:69ee968b3a91b7de5c32776a762c2bf38ef5693289cd48f1d3ab779667fdbb8f","target":"record","created_at":"2026-05-29T01:05:42Z","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":"23977264749dc4bbcff2594012f796ddb2550b06b2f0f3449e304b395aa350fc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T07:19:47Z","title_canon_sha256":"0e134535d8327a7234acd8a84df314fb28a8a41dc8584a0f6f32d37d9f3d8a40"},"schema_version":"1.0","source":{"id":"2605.29495","kind":"arxiv","version":1}},"canonical_sha256":"e84ad5b7e2e2c5c39244d88a0ee05a561f26962d1eb6b585ed30fe710cd7d0dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e84ad5b7e2e2c5c39244d88a0ee05a561f26962d1eb6b585ed30fe710cd7d0dc","first_computed_at":"2026-05-29T01:05:42.750328Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:42.750328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oqkIAJXt7q1k62Z08tBfFU4L3HL9i2O9yHqTY7RoL6Z+SxDuahY021Yd8bWOuSNuZ9Fc2tDnpj0y1+Lh2W0vCA==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:42.750852Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29495","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69ee968b3a91b7de5c32776a762c2bf38ef5693289cd48f1d3ab779667fdbb8f","sha256:9d4b587e13aec9fc825e724d5a5d215c5f651db61ce30454bb81bf881d2ced7b"],"state_sha256":"930594e051aafa3e00295330c9934c8b208f648905d542b7927d24bc40d3a6f3"}