{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QFJVPOIJMUDXI3GRNSQSCKQPWE","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":"8696b50cfb2e0cf41bdb2fcfe6dcd812c74dd32718f083ebeddc7b6517e50bf6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-21T12:35:04Z","title_canon_sha256":"a36ff9101e17ef292699219aad90909ce562902612f27ad64404ea19124ea7ba"},"schema_version":"1.0","source":{"id":"2607.19046","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19046","created_at":"2026-07-22T01:24:05Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19046v1","created_at":"2026-07-22T01:24:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19046","created_at":"2026-07-22T01:24:05Z"},{"alias_kind":"pith_short_12","alias_value":"QFJVPOIJMUDX","created_at":"2026-07-22T01:24:05Z"},{"alias_kind":"pith_short_16","alias_value":"QFJVPOIJMUDXI3GR","created_at":"2026-07-22T01:24:05Z"},{"alias_kind":"pith_short_8","alias_value":"QFJVPOIJ","created_at":"2026-07-22T01:24:05Z"}],"graph_snapshots":[{"event_id":"sha256:b4911ccaf3a62950f50c86976f3dfd8b0999cc39d788b31f1f89ae8e69d0e742","target":"graph","created_at":"2026-07-22T01:24:05Z","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/2607.19046/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy Distillation (OPD) supervises a student model on trajectories sampled from its own policy by minimizing the divergence between the output distributions of the teacher and student at each token position, thereby providing dense token-level supervision. Although existing OPD methods have demonstrated strong performance in improving the reasoning ability of student models, their objectives fundamentally rely on token-level distribution matching. Consequently, they lack an explicit signal for comparing a token's relative compatibility across reasoning modes and thus do not directly model","authors_text":"Dayiheng Liu, Jiacheng Ruan, Jun Tang, Shuai Bai, Ting Liu, Wenzhen Yuan, Yuzhuo Fu, Zhibo Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-21T12:35:04Z","title":"Contrastive On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19046","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":"sha256:5137a84e96e9baec732d290e471c33c733cee884ba7bd657e6176b1d44528169","target":"record","created_at":"2026-07-22T01:24:05Z","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":"8696b50cfb2e0cf41bdb2fcfe6dcd812c74dd32718f083ebeddc7b6517e50bf6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-21T12:35:04Z","title_canon_sha256":"a36ff9101e17ef292699219aad90909ce562902612f27ad64404ea19124ea7ba"},"schema_version":"1.0","source":{"id":"2607.19046","kind":"arxiv","version":1}},"canonical_sha256":"815357b9096507746cd16ca1212a0fb13adb9939e4e220b7d9a380a4a329245d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"815357b9096507746cd16ca1212a0fb13adb9939e4e220b7d9a380a4a329245d","first_computed_at":"2026-07-22T01:24:05.833366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T01:24:05.833366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3pwFN9q7sCxXD59ndd314xhuLHo0smTY765qZFIRDBTW7F96Ml4TA0yZ3mIArUeeTdj4dHK85yICnaVDaymsBQ==","signature_status":"signed_v1","signed_at":"2026-07-22T01:24:05.834184Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.19046","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5137a84e96e9baec732d290e471c33c733cee884ba7bd657e6176b1d44528169","sha256:b4911ccaf3a62950f50c86976f3dfd8b0999cc39d788b31f1f89ae8e69d0e742"],"state_sha256":"b46405965332cec039575dd9abad0a7a6c153727bf23d15e838b0790681cf1b1"}