{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:44ZSHURFER6AD7MACUTBWZUCXO","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":"162fcbf9f051fa1a93475bab43d100f68f3d1c6dbc2da7fee431a086dc24900c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T11:13:01Z","title_canon_sha256":"0462c6c49ee61628613d511e84cba358fe55cf01e141e39f02fe77a27d6493ba"},"schema_version":"1.0","source":{"id":"2606.06021","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06021","created_at":"2026-06-05T01:15:30Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06021v1","created_at":"2026-06-05T01:15:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06021","created_at":"2026-06-05T01:15:30Z"},{"alias_kind":"pith_short_12","alias_value":"44ZSHURFER6A","created_at":"2026-06-05T01:15:30Z"},{"alias_kind":"pith_short_16","alias_value":"44ZSHURFER6AD7MA","created_at":"2026-06-05T01:15:30Z"},{"alias_kind":"pith_short_8","alias_value":"44ZSHURF","created_at":"2026-06-05T01:15:30Z"}],"graph_snapshots":[{"event_id":"sha256:4bd2817da2193e7c5097350a64f4031c7a129f0cd133f032504b09a53cc31627","target":"graph","created_at":"2026-06-05T01:15:30Z","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/2606.06021/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation (OPD) supervises the student only in output space by matching next-token probabilities. This output-only paradigm has two limits: (1) sampling variance from Monte Carlo KL estimates over large vocabularies (e.g., Qwen's ~150k tokens) persists throughout training, and (2) it treats the teacher as a black-box, discarding all intermediate hidden states after the LM head. We propose On-Policy Representation Distillation (OPRD), which lifts distillation into hidden-state space by aligning student and teacher representations across selected layers on the same rollouts, bypassi","authors_text":"Bowen Song, Gang Chen, Guangcheng Zhu, Haobo Wang, Mingxuan Xia, Shenzhi Yang, Weiqiang Wang, Xing Zheng, Yingfan Ma, Zhongqi Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T11:13:01Z","title":"OPRD: On-Policy Representation Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06021","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":"sha256:3ef12ef71db9071b6e98ee7f1cce6053045d7fc736010331e9883cf86e542072","target":"record","created_at":"2026-06-05T01:15:30Z","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":"162fcbf9f051fa1a93475bab43d100f68f3d1c6dbc2da7fee431a086dc24900c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T11:13:01Z","title_canon_sha256":"0462c6c49ee61628613d511e84cba358fe55cf01e141e39f02fe77a27d6493ba"},"schema_version":"1.0","source":{"id":"2606.06021","kind":"arxiv","version":1}},"canonical_sha256":"e73323d225247c01fd8015261b6682bb97ab28e5f4048eaeae510b13d7a199c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e73323d225247c01fd8015261b6682bb97ab28e5f4048eaeae510b13d7a199c0","first_computed_at":"2026-06-05T01:15:30.595962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:30.595962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XuslWn3dn8Uq8xcrXXjSFeLt05OVdCe8GQ+AWLGxyqMOS4xrcHymT4NRPXyvMkRZOHj8eajC2oldFC5DutZxCw==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:30.596375Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06021","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ef12ef71db9071b6e98ee7f1cce6053045d7fc736010331e9883cf86e542072","sha256:4bd2817da2193e7c5097350a64f4031c7a129f0cd133f032504b09a53cc31627"],"state_sha256":"901596238789202b6ed4d08386e46b18e103f2743f7533cf631302d71786c542"}