{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:E7TRJVG7WFSS4LTONEOPP6WAPG","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":"5e331b9268ee6385809a2c580a07c23bc076f4067693a53da0d9fe9ef86f7115","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T22:31:15Z","title_canon_sha256":"0ffc4dd4fcaf1bff6690faee16eb3b34220d9faa4d73bbb20d1cd476c009c93a"},"schema_version":"1.0","source":{"id":"2606.01476","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01476","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01476v1","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01476","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"E7TRJVG7WFSS","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"E7TRJVG7WFSS4LTO","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"E7TRJVG7","created_at":"2026-06-02T02:04:34Z"}],"graph_snapshots":[{"event_id":"sha256:3d9b575bd79d29bdfa6bb9b75a2eed490e9aba60382c8ba6da03fc57e3054574","target":"graph","created_at":"2026-06-02T02:04:34Z","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/2606.01476/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-Policy Distillation (OPD) trains a student model on its own generative trajectories under dense token-level feedback from a stronger teacher, mitigating both the off-policy distribution shift of Supervised Fine-Tuning (SFT) and the sparse credit assignment of Reinforcement Learning (RL). However, standard OPD faces two coupled limitations. First, it requires direct access to the teacher's token-level logits, excluding a broad class of capable proprietary models from serving as teachers. Second, the token-level logit signal itself is brittle, depending on a narrow overlap of plausible next t","authors_text":"Jiayi Liu, Lizhu Zhang, Mingyi Wang, Peng Bo, Xiangjun Fan, Yifan Wu, Yuhang Zhou, Zhuokai Zhao","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T22:31:15Z","title":"OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01476","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":"sha256:4ea4b471c20fb33888bd9ea7d5d8fe4d4dd3d54e2486f0ce703daf684dc2346b","target":"record","created_at":"2026-06-02T02:04:34Z","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":"5e331b9268ee6385809a2c580a07c23bc076f4067693a53da0d9fe9ef86f7115","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T22:31:15Z","title_canon_sha256":"0ffc4dd4fcaf1bff6690faee16eb3b34220d9faa4d73bbb20d1cd476c009c93a"},"schema_version":"1.0","source":{"id":"2606.01476","kind":"arxiv","version":1}},"canonical_sha256":"27e714d4dfb1652e2e6e691cf7fac07991c4b8fddf15a712a9263a9521a53861","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27e714d4dfb1652e2e6e691cf7fac07991c4b8fddf15a712a9263a9521a53861","first_computed_at":"2026-06-02T02:04:34.356230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:34.356230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bnC+hsBTZe3vHfxeJZdcI55XxTkwgBCvPRJGAufkIdPmDAvzZTGoE+ONPdbqKS36h3T78ZEwTEQ1YhHL7f6jAQ==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:34.356689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01476","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ea4b471c20fb33888bd9ea7d5d8fe4d4dd3d54e2486f0ce703daf684dc2346b","sha256:3d9b575bd79d29bdfa6bb9b75a2eed490e9aba60382c8ba6da03fc57e3054574"],"state_sha256":"ee0110b935493bc3794ac10f65007c7c7ce7054fd687ed02fb82c0711524a5a2"}