{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MPZOQXGXPNPE24I5BSFW6ZUCBW","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":"b906dbab55608dfb9f4f8867fc3f801591588ae220e8fc0a26a9ae91ab06dd54","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T13:49:37Z","title_canon_sha256":"69566d72d8cb0d6692b7d835971120360d1ebe70f6df616d08fac2c72f4885f6"},"schema_version":"1.0","source":{"id":"2605.27028","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27028","created_at":"2026-05-27T01:06:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27028v1","created_at":"2026-05-27T01:06:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27028","created_at":"2026-05-27T01:06:24Z"},{"alias_kind":"pith_short_12","alias_value":"MPZOQXGXPNPE","created_at":"2026-05-27T01:06:24Z"},{"alias_kind":"pith_short_16","alias_value":"MPZOQXGXPNPE24I5","created_at":"2026-05-27T01:06:24Z"},{"alias_kind":"pith_short_8","alias_value":"MPZOQXGX","created_at":"2026-05-27T01:06:24Z"}],"graph_snapshots":[{"event_id":"sha256:38c41e344e95c804447ac3ebd194e93e43b7ab165eebf5e27ba34e108511137e","target":"graph","created_at":"2026-05-27T01:06:24Z","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/2605.27028/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation has recently emerged as a promising alternative to standard sequence-level imitation, training a student by scoring its own rollouts with a teacher model. However, we observe ``Off-policy Teacher Decay'' problem in this paradigm: for the later tokens, with student's earlier trajectory as context that is off-policy to the teacher, the teacher's ability to produce a corrective score would decay, and may fall back to token-completion behavior learned in the pre-training stage. We empirically verify this problem, and we propose Early Stopping Rollout (ESR) to fix it: a simpl","authors_text":"Demetri Terzopoulos, Huacong Tang, Jiaqi Li, Ying Nian Wu, Zhou Ziheng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T13:49:37Z","title":"Less is More: Early Stopping Rollout for On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27028","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:a0728fe5f5858aad5ec99c4b2f4ca7c429ed62900725c500166ea21aa44c0bc7","target":"record","created_at":"2026-05-27T01:06:24Z","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":"b906dbab55608dfb9f4f8867fc3f801591588ae220e8fc0a26a9ae91ab06dd54","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T13:49:37Z","title_canon_sha256":"69566d72d8cb0d6692b7d835971120360d1ebe70f6df616d08fac2c72f4885f6"},"schema_version":"1.0","source":{"id":"2605.27028","kind":"arxiv","version":1}},"canonical_sha256":"63f2e85cd77b5e4d711d0c8b6f66820dab2c0df89743bcee1cae16559dd07e71","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63f2e85cd77b5e4d711d0c8b6f66820dab2c0df89743bcee1cae16559dd07e71","first_computed_at":"2026-05-27T01:06:24.860782Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:06:24.860782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pxgJrpfB53RnA8mlOg3NJQpNAuwY7JOim903XOkApc7jouRUHaPKoHBkSTDAIF7OZ+/pdoG9FXTyAbnaKdAUCQ==","signature_status":"signed_v1","signed_at":"2026-05-27T01:06:24.861662Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27028","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0728fe5f5858aad5ec99c4b2f4ca7c429ed62900725c500166ea21aa44c0bc7","sha256:38c41e344e95c804447ac3ebd194e93e43b7ab165eebf5e27ba34e108511137e"],"state_sha256":"35a400d2d210e799c682306dd996f5ebf7e6bcaf4cda148ac8d6133a9cf6f3bb"}