{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2010:Q7APOC2KO3NP5RSJL4PYOAIUMJ","short_pith_number":"pith:Q7APOC2K","canonical_record":{"source":{"id":"1011.0686","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-11-02T17:55:55Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6529b62516bc08aba11ff6e269bc84278e988a7da857a7a4f61d59a3bf0655ed","abstract_canon_sha256":"6f379789c461e1df05e2f264a94d850b21611dcd1aa7e6c7518f749703803d89"},"schema_version":"1.0"},"canonical_sha256":"87c0f70b4a76dafec6495f1f870114626149e06da9e6dded704186a7e0c904f6","source":{"kind":"arxiv","id":"1011.0686","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1011.0686","created_at":"2026-05-18T02:23:37Z"},{"alias_kind":"arxiv_version","alias_value":"1011.0686v3","created_at":"2026-05-18T02:23:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1011.0686","created_at":"2026-05-18T02:23:37Z"},{"alias_kind":"pith_short_12","alias_value":"Q7APOC2KO3NP","created_at":"2026-05-18T12:26:12Z"},{"alias_kind":"pith_short_16","alias_value":"Q7APOC2KO3NP5RSJ","created_at":"2026-05-18T12:26:12Z"},{"alias_kind":"pith_short_8","alias_value":"Q7APOC2K","created_at":"2026-05-18T12:26:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2010:Q7APOC2KO3NP5RSJL4PYOAIUMJ","target":"record","payload":{"canonical_record":{"source":{"id":"1011.0686","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-11-02T17:55:55Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6529b62516bc08aba11ff6e269bc84278e988a7da857a7a4f61d59a3bf0655ed","abstract_canon_sha256":"6f379789c461e1df05e2f264a94d850b21611dcd1aa7e6c7518f749703803d89"},"schema_version":"1.0"},"canonical_sha256":"87c0f70b4a76dafec6495f1f870114626149e06da9e6dded704186a7e0c904f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:23:37.825613Z","signature_b64":"7EnxXH+c44L98e+qNf1wSAtCbLMS11IoOnQWO3LbWYnQftQzo2qPfIVDK8ZU0uGZA0KfXRhlaGw7TTQu/cclCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87c0f70b4a76dafec6495f1f870114626149e06da9e6dded704186a7e0c904f6","last_reissued_at":"2026-05-18T02:23:37.824921Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:23:37.824921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1011.0686","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:23:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"20Vn3iDhaUphKs/JUD7S4ic6sMF0mUBEbNK94VYwZSdFNoDojQp62Kc9OyWe8iJM8+7MqY1tYVjnNIDHIT6QBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:10:12.182452Z"},"content_sha256":"cc5b4a668a96a895900986e4e71783bad4603aaa7e7d517f47d55ddc84fd7b5b","schema_version":"1.0","event_id":"sha256:cc5b4a668a96a895900986e4e71783bad4603aaa7e7d517f47d55ddc84fd7b5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2010:Q7APOC2KO3NP5RSJL4PYOAIUMJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Geoffrey J. Gordon, J. Andrew Bagnell, Stephane Ross","submitted_at":"2010-11-02T17:55:55Z","abstract_excerpt":"Sequential prediction problems such as imitation learning, where future observations depend on previous predictions (actions), violate the common i.i.d. assumptions made in statistical learning. This leads to poor performance in theory and often in practice. Some recent approaches provide stronger guarantees in this setting, but remain somewhat unsatisfactory as they train either non-stationary or stochastic policies and require a large number of iterations. In this paper, we propose a new iterative algorithm, which trains a stationary deterministic policy, that can be seen as a no regret algo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1011.0686","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T02:23:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7vc+Ef/uwvKtZ9s7HY3OPQtYIwfQOzT0Ekdo0sGkW7SWye6r8OdYcdmBz/USkpgiM30f2GQ2nj4dFbcpc56wDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:10:12.182979Z"},"content_sha256":"a89a783816782a29e780b029ae4294142378024d37cf7839a3a110c3122f2162","schema_version":"1.0","event_id":"sha256:a89a783816782a29e780b029ae4294142378024d37cf7839a3a110c3122f2162"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q7APOC2KO3NP5RSJL4PYOAIUMJ/bundle.json","state_url":"https://pith.science/pith/Q7APOC2KO3NP5RSJL4PYOAIUMJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q7APOC2KO3NP5RSJL4PYOAIUMJ/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":"2026-05-21T09:10:12Z","links":{"resolver":"https://pith.science/pith/Q7APOC2KO3NP5RSJL4PYOAIUMJ","bundle":"https://pith.science/pith/Q7APOC2KO3NP5RSJL4PYOAIUMJ/bundle.json","state":"https://pith.science/pith/Q7APOC2KO3NP5RSJL4PYOAIUMJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q7APOC2KO3NP5RSJL4PYOAIUMJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2010:Q7APOC2KO3NP5RSJL4PYOAIUMJ","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":"6f379789c461e1df05e2f264a94d850b21611dcd1aa7e6c7518f749703803d89","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-11-02T17:55:55Z","title_canon_sha256":"6529b62516bc08aba11ff6e269bc84278e988a7da857a7a4f61d59a3bf0655ed"},"schema_version":"1.0","source":{"id":"1011.0686","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1011.0686","created_at":"2026-05-18T02:23:37Z"},{"alias_kind":"arxiv_version","alias_value":"1011.0686v3","created_at":"2026-05-18T02:23:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1011.0686","created_at":"2026-05-18T02:23:37Z"},{"alias_kind":"pith_short_12","alias_value":"Q7APOC2KO3NP","created_at":"2026-05-18T12:26:12Z"},{"alias_kind":"pith_short_16","alias_value":"Q7APOC2KO3NP5RSJ","created_at":"2026-05-18T12:26:12Z"},{"alias_kind":"pith_short_8","alias_value":"Q7APOC2K","created_at":"2026-05-18T12:26:12Z"}],"graph_snapshots":[{"event_id":"sha256:a89a783816782a29e780b029ae4294142378024d37cf7839a3a110c3122f2162","target":"graph","created_at":"2026-05-18T02:23:37Z","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"},"paper":{"abstract_excerpt":"Sequential prediction problems such as imitation learning, where future observations depend on previous predictions (actions), violate the common i.i.d. assumptions made in statistical learning. This leads to poor performance in theory and often in practice. Some recent approaches provide stronger guarantees in this setting, but remain somewhat unsatisfactory as they train either non-stationary or stochastic policies and require a large number of iterations. In this paper, we propose a new iterative algorithm, which trains a stationary deterministic policy, that can be seen as a no regret algo","authors_text":"Geoffrey J. Gordon, J. Andrew Bagnell, Stephane Ross","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-11-02T17:55:55Z","title":"A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1011.0686","kind":"arxiv","version":3},"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:cc5b4a668a96a895900986e4e71783bad4603aaa7e7d517f47d55ddc84fd7b5b","target":"record","created_at":"2026-05-18T02:23:37Z","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":"6f379789c461e1df05e2f264a94d850b21611dcd1aa7e6c7518f749703803d89","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-11-02T17:55:55Z","title_canon_sha256":"6529b62516bc08aba11ff6e269bc84278e988a7da857a7a4f61d59a3bf0655ed"},"schema_version":"1.0","source":{"id":"1011.0686","kind":"arxiv","version":3}},"canonical_sha256":"87c0f70b4a76dafec6495f1f870114626149e06da9e6dded704186a7e0c904f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87c0f70b4a76dafec6495f1f870114626149e06da9e6dded704186a7e0c904f6","first_computed_at":"2026-05-18T02:23:37.824921Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:23:37.824921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7EnxXH+c44L98e+qNf1wSAtCbLMS11IoOnQWO3LbWYnQftQzo2qPfIVDK8ZU0uGZA0KfXRhlaGw7TTQu/cclCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:23:37.825613Z","signed_message":"canonical_sha256_bytes"},"source_id":"1011.0686","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc5b4a668a96a895900986e4e71783bad4603aaa7e7d517f47d55ddc84fd7b5b","sha256:a89a783816782a29e780b029ae4294142378024d37cf7839a3a110c3122f2162"],"state_sha256":"6119c32b0a62ed8637b5a26364993d4ffa04e6048cf9267832fa1522592b1ef1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JIyQhkAuifa0t0MjgScsHZSKlezquN125NfQLQsEncuohUXnfItKpiqLnkDN8aYXir43LCrKpEOsVBYsvPuCBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T09:10:12.186033Z","bundle_sha256":"d156f5346556a0b005d8d98b9506fb4bd123517d78ead93a1962ad7912b1a4e0"}}