{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5BFJPPYRU4UEDOZRSIUPZ42W4X","short_pith_number":"pith:5BFJPPYR","canonical_record":{"source":{"id":"2606.30923","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T21:18:21Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ef7f76ab5997762fd5bffac2b37243e43aa1dd257f0f715b69d4246c3430679f","abstract_canon_sha256":"64791c5d7d3cd42b3e9cc383405c3179acb00f30809ff29311d240eb0ee4d34f"},"schema_version":"1.0"},"canonical_sha256":"e84a97bf11a72841bb319228fcf356e5ec89277f7f0d872397eeef21616109f1","source":{"kind":"arxiv","id":"2606.30923","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30923","created_at":"2026-07-01T00:17:21Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30923v1","created_at":"2026-07-01T00:17:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30923","created_at":"2026-07-01T00:17:21Z"},{"alias_kind":"pith_short_12","alias_value":"5BFJPPYRU4UE","created_at":"2026-07-01T00:17:21Z"},{"alias_kind":"pith_short_16","alias_value":"5BFJPPYRU4UEDOZR","created_at":"2026-07-01T00:17:21Z"},{"alias_kind":"pith_short_8","alias_value":"5BFJPPYR","created_at":"2026-07-01T00:17:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5BFJPPYRU4UEDOZRSIUPZ42W4X","target":"record","payload":{"canonical_record":{"source":{"id":"2606.30923","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T21:18:21Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ef7f76ab5997762fd5bffac2b37243e43aa1dd257f0f715b69d4246c3430679f","abstract_canon_sha256":"64791c5d7d3cd42b3e9cc383405c3179acb00f30809ff29311d240eb0ee4d34f"},"schema_version":"1.0"},"canonical_sha256":"e84a97bf11a72841bb319228fcf356e5ec89277f7f0d872397eeef21616109f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T00:17:21.755071Z","signature_b64":"zFmg7gflzcB6mit3eL01V8dP50AOIdGj7M+Oj1C6GAT//0c7Zp8oz7nWWAgiJIgAneKxcghzuHmSzYDv+E6vCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e84a97bf11a72841bb319228fcf356e5ec89277f7f0d872397eeef21616109f1","last_reissued_at":"2026-07-01T00:17:21.754666Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T00:17:21.754666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.30923","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":"2026-07-01T00:17:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t3vFk39LAQqCxpRbBwAhRll/ByWvh1zVCPn5We3dOYL/wmPty4Rcl3WpZ4dYasgBuMd4/eYN75YbdJPZ00u7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T21:08:37.917784Z"},"content_sha256":"5c3c80be3022b5dbd4c4bd4c01dd96088ec9cd14ef54dd1f70e62b1aea126b7e","schema_version":"1.0","event_id":"sha256:5c3c80be3022b5dbd4c4bd4c01dd96088ec9cd14ef54dd1f70e62b1aea126b7e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5BFJPPYRU4UEDOZRSIUPZ42W4X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Block, Daniel Hsu, Peihan Liu, Ved Sriraman","submitted_at":"2026-06-29T21:18:21Z","abstract_excerpt":"Imitation Learning is a natural framework for learning in sequential decision-making systems and has emerged as the dominant paradigm through which we understand language model training. A central puzzle is that, while in theory offline IL can be horizon-free and optimal, in practice online methods such as on-policy distillation often outperform offline methods such as supervised fine-tuning. We propose a noisy expert model to explain this gap, in which the learner only has access to a noisy version of the expert's policy, but wishes to compete against the reward achieved by a clean expert, mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30923","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/2606.30923/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":"2026-07-01T00:17:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jrgorrTdvwoDZlooD422slGLsoe7EVRQSt/csz0nFt72cTk8wSQmqRw26zsFTe3dhgFvtGjCEQWTpxDbjR9jBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T21:08:37.918159Z"},"content_sha256":"e9846f227b5351d075441c85e2b09d52eb2f78b71304dca340019bd60d98462b","schema_version":"1.0","event_id":"sha256:e9846f227b5351d075441c85e2b09d52eb2f78b71304dca340019bd60d98462b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5BFJPPYRU4UEDOZRSIUPZ42W4X/bundle.json","state_url":"https://pith.science/pith/5BFJPPYRU4UEDOZRSIUPZ42W4X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5BFJPPYRU4UEDOZRSIUPZ42W4X/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":"2026-07-01T21:08:37Z","links":{"resolver":"https://pith.science/pith/5BFJPPYRU4UEDOZRSIUPZ42W4X","bundle":"https://pith.science/pith/5BFJPPYRU4UEDOZRSIUPZ42W4X/bundle.json","state":"https://pith.science/pith/5BFJPPYRU4UEDOZRSIUPZ42W4X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5BFJPPYRU4UEDOZRSIUPZ42W4X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5BFJPPYRU4UEDOZRSIUPZ42W4X","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":"64791c5d7d3cd42b3e9cc383405c3179acb00f30809ff29311d240eb0ee4d34f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T21:18:21Z","title_canon_sha256":"ef7f76ab5997762fd5bffac2b37243e43aa1dd257f0f715b69d4246c3430679f"},"schema_version":"1.0","source":{"id":"2606.30923","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30923","created_at":"2026-07-01T00:17:21Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30923v1","created_at":"2026-07-01T00:17:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30923","created_at":"2026-07-01T00:17:21Z"},{"alias_kind":"pith_short_12","alias_value":"5BFJPPYRU4UE","created_at":"2026-07-01T00:17:21Z"},{"alias_kind":"pith_short_16","alias_value":"5BFJPPYRU4UEDOZR","created_at":"2026-07-01T00:17:21Z"},{"alias_kind":"pith_short_8","alias_value":"5BFJPPYR","created_at":"2026-07-01T00:17:21Z"}],"graph_snapshots":[{"event_id":"sha256:e9846f227b5351d075441c85e2b09d52eb2f78b71304dca340019bd60d98462b","target":"graph","created_at":"2026-07-01T00:17:21Z","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/2606.30923/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imitation Learning is a natural framework for learning in sequential decision-making systems and has emerged as the dominant paradigm through which we understand language model training. A central puzzle is that, while in theory offline IL can be horizon-free and optimal, in practice online methods such as on-policy distillation often outperform offline methods such as supervised fine-tuning. We propose a noisy expert model to explain this gap, in which the learner only has access to a noisy version of the expert's policy, but wishes to compete against the reward achieved by a clean expert, mo","authors_text":"Adam Block, Daniel Hsu, Peihan Liu, Ved Sriraman","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T21:18:21Z","title":"Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30923","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":"sha256:5c3c80be3022b5dbd4c4bd4c01dd96088ec9cd14ef54dd1f70e62b1aea126b7e","target":"record","created_at":"2026-07-01T00:17:21Z","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":"64791c5d7d3cd42b3e9cc383405c3179acb00f30809ff29311d240eb0ee4d34f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T21:18:21Z","title_canon_sha256":"ef7f76ab5997762fd5bffac2b37243e43aa1dd257f0f715b69d4246c3430679f"},"schema_version":"1.0","source":{"id":"2606.30923","kind":"arxiv","version":1}},"canonical_sha256":"e84a97bf11a72841bb319228fcf356e5ec89277f7f0d872397eeef21616109f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e84a97bf11a72841bb319228fcf356e5ec89277f7f0d872397eeef21616109f1","first_computed_at":"2026-07-01T00:17:21.754666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T00:17:21.754666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zFmg7gflzcB6mit3eL01V8dP50AOIdGj7M+Oj1C6GAT//0c7Zp8oz7nWWAgiJIgAneKxcghzuHmSzYDv+E6vCQ==","signature_status":"signed_v1","signed_at":"2026-07-01T00:17:21.755071Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.30923","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c3c80be3022b5dbd4c4bd4c01dd96088ec9cd14ef54dd1f70e62b1aea126b7e","sha256:e9846f227b5351d075441c85e2b09d52eb2f78b71304dca340019bd60d98462b"],"state_sha256":"f6ffa605753b0d2661e9cf06e34316739763cb7709a26779a2abb91d92c4e470"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KN94e3HCYd5mMWAvh5qMgbJ+x25oh/2Vamod75jQj2zExp1/FGclRZ13g4nK/DFpHnt5pRt8joPLLGlj6lSYAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T21:08:37.920248Z","bundle_sha256":"f9c8feae75dc5af7565c7b30aa749c80cd68c9272ea9abe8cfb717c69e824adb"}}