{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:B32IYG73RAGWX7ZFJYQ7D3UTCT","short_pith_number":"pith:B32IYG73","canonical_record":{"source":{"id":"2606.22600","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T17:20:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"363d7efa340a332dfd28a2619b3e579967642186df67f6c663bd0cba94538bf2","abstract_canon_sha256":"b2a52522ebcbbc16917d82a3f3eed0052c92eba046466148b4cb26923ba85b0f"},"schema_version":"1.0"},"canonical_sha256":"0ef48c1bfb880d6bff254e21f1ee9314eb85cf19b7ebad3aa561bc18fef067af","source":{"kind":"arxiv","id":"2606.22600","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22600","created_at":"2026-06-23T02:13:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22600v1","created_at":"2026-06-23T02:13:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22600","created_at":"2026-06-23T02:13:42Z"},{"alias_kind":"pith_short_12","alias_value":"B32IYG73RAGW","created_at":"2026-06-23T02:13:42Z"},{"alias_kind":"pith_short_16","alias_value":"B32IYG73RAGWX7ZF","created_at":"2026-06-23T02:13:42Z"},{"alias_kind":"pith_short_8","alias_value":"B32IYG73","created_at":"2026-06-23T02:13:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:B32IYG73RAGWX7ZFJYQ7D3UTCT","target":"record","payload":{"canonical_record":{"source":{"id":"2606.22600","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T17:20:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"363d7efa340a332dfd28a2619b3e579967642186df67f6c663bd0cba94538bf2","abstract_canon_sha256":"b2a52522ebcbbc16917d82a3f3eed0052c92eba046466148b4cb26923ba85b0f"},"schema_version":"1.0"},"canonical_sha256":"0ef48c1bfb880d6bff254e21f1ee9314eb85cf19b7ebad3aa561bc18fef067af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:42.540195Z","signature_b64":"2/xaxHLGqTiGHw4PNGQq6VzW1pAKv25Z4WmtqI+hDqoI5a42Ca5mJ41aBjVeteJbF2VXYst4tq3oIUqxuhBLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ef48c1bfb880d6bff254e21f1ee9314eb85cf19b7ebad3aa561bc18fef067af","last_reissued_at":"2026-06-23T02:13:42.539804Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:42.539804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.22600","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T02:13:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vLLA2ZxCJGhnJ0QLlgH90T+3x2Iu7u2DsvbL7QBgK6A2b0w/1WQFI0EePyR0DvfspA3zq6YM+c+TP2ybrGQrDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T20:48:44.371077Z"},"content_sha256":"a57becbe18a77808b0ae4ed66b097a3784e868de20419f6d22a305466d0929de","schema_version":"1.0","event_id":"sha256:a57becbe18a77808b0ae4ed66b097a3784e868de20419f6d22a305466d0929de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:B32IYG73RAGWX7ZFJYQ7D3UTCT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Position Bias of On-Policy Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Chen, Sijie Zhu, Tiansheng Wen, Yan Xie, Yifei Wang","submitted_at":"2026-06-21T17:20:21Z","abstract_excerpt":"On-Policy Distillation (OPD) improves the learning efficiency of standard reinforcement learning through dense, token-level supervision from teachers. In the standard KL objective of OPD, token-level losses are uniformly averaged, implying equal weights for all tokens. However, we discover that not all tokens are created equal: as student rollouts grow longer, they deviate further from the teacher's distribution, leading to degraded supervision quality at later positions. As a result, OPD using only the first 30% of tokens can perform comparably to using all tokens, whereas OPD using only the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22600","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.22600/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T02:13:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iYGa1o4UBMFd+CWlXj9A2kZHzfhvqDJ1M8ldApkzpsLUv/YEVnNl9ekmhEyKuWZCPV1S2lssSi/hh0fMTqpGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T20:48:44.371517Z"},"content_sha256":"1e66bb755b14f96d0d8b4e9bab34c251f55ab18b759908e8c1053dcba7d567a6","schema_version":"1.0","event_id":"sha256:1e66bb755b14f96d0d8b4e9bab34c251f55ab18b759908e8c1053dcba7d567a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B32IYG73RAGWX7ZFJYQ7D3UTCT/bundle.json","state_url":"https://pith.science/pith/B32IYG73RAGWX7ZFJYQ7D3UTCT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B32IYG73RAGWX7ZFJYQ7D3UTCT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-27T20:48:44Z","links":{"resolver":"https://pith.science/pith/B32IYG73RAGWX7ZFJYQ7D3UTCT","bundle":"https://pith.science/pith/B32IYG73RAGWX7ZFJYQ7D3UTCT/bundle.json","state":"https://pith.science/pith/B32IYG73RAGWX7ZFJYQ7D3UTCT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B32IYG73RAGWX7ZFJYQ7D3UTCT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:B32IYG73RAGWX7ZFJYQ7D3UTCT","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":"b2a52522ebcbbc16917d82a3f3eed0052c92eba046466148b4cb26923ba85b0f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T17:20:21Z","title_canon_sha256":"363d7efa340a332dfd28a2619b3e579967642186df67f6c663bd0cba94538bf2"},"schema_version":"1.0","source":{"id":"2606.22600","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22600","created_at":"2026-06-23T02:13:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22600v1","created_at":"2026-06-23T02:13:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22600","created_at":"2026-06-23T02:13:42Z"},{"alias_kind":"pith_short_12","alias_value":"B32IYG73RAGW","created_at":"2026-06-23T02:13:42Z"},{"alias_kind":"pith_short_16","alias_value":"B32IYG73RAGWX7ZF","created_at":"2026-06-23T02:13:42Z"},{"alias_kind":"pith_short_8","alias_value":"B32IYG73","created_at":"2026-06-23T02:13:42Z"}],"graph_snapshots":[{"event_id":"sha256:1e66bb755b14f96d0d8b4e9bab34c251f55ab18b759908e8c1053dcba7d567a6","target":"graph","created_at":"2026-06-23T02:13:42Z","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/2606.22600/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-Policy Distillation (OPD) improves the learning efficiency of standard reinforcement learning through dense, token-level supervision from teachers. In the standard KL objective of OPD, token-level losses are uniformly averaged, implying equal weights for all tokens. However, we discover that not all tokens are created equal: as student rollouts grow longer, they deviate further from the teacher's distribution, leading to degraded supervision quality at later positions. As a result, OPD using only the first 30% of tokens can perform comparably to using all tokens, whereas OPD using only the ","authors_text":"Bo Chen, Sijie Zhu, Tiansheng Wen, Yan Xie, Yifei Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T17:20:21Z","title":"On the Position Bias of On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22600","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:a57becbe18a77808b0ae4ed66b097a3784e868de20419f6d22a305466d0929de","target":"record","created_at":"2026-06-23T02:13:42Z","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":"b2a52522ebcbbc16917d82a3f3eed0052c92eba046466148b4cb26923ba85b0f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T17:20:21Z","title_canon_sha256":"363d7efa340a332dfd28a2619b3e579967642186df67f6c663bd0cba94538bf2"},"schema_version":"1.0","source":{"id":"2606.22600","kind":"arxiv","version":1}},"canonical_sha256":"0ef48c1bfb880d6bff254e21f1ee9314eb85cf19b7ebad3aa561bc18fef067af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ef48c1bfb880d6bff254e21f1ee9314eb85cf19b7ebad3aa561bc18fef067af","first_computed_at":"2026-06-23T02:13:42.539804Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:42.539804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2/xaxHLGqTiGHw4PNGQq6VzW1pAKv25Z4WmtqI+hDqoI5a42Ca5mJ41aBjVeteJbF2VXYst4tq3oIUqxuhBLDA==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:42.540195Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22600","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a57becbe18a77808b0ae4ed66b097a3784e868de20419f6d22a305466d0929de","sha256:1e66bb755b14f96d0d8b4e9bab34c251f55ab18b759908e8c1053dcba7d567a6"],"state_sha256":"8bc805c090a4406192fbc8cabcad78ae1a98d56655dda8c85dfeac2a59469ba9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cKZNdXTaOnw9ZeSnDLxkPF9qjcSpvdhDYSyM8cLNkCMNFKQGt63wwrAzKTUmSspkL1jGShx+29gbdSqWx6eoDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T20:48:44.373438Z","bundle_sha256":"fe68b7866ee5281f0ffccbae070b0cd0d4a3e63da7d156be45bbd715320c7050"}}