{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OFIBCUN2R35G6A3H5LHR7EHZYQ","short_pith_number":"pith:OFIBCUN2","canonical_record":{"source":{"id":"1811.02184","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-11-06T06:34:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2abc08df5c3e9871ed1b46df565f3e4fbf764df4a2038da1f7426fbefa3b4f1c","abstract_canon_sha256":"b1285c0277ac5834c25a0801264c6ba2a6e75eb37791514fb581ffdef63cbc22"},"schema_version":"1.0"},"canonical_sha256":"71501151ba8efa6f0367eacf1f90f9c4395930c6133d62115d0a2660a2b5bc8c","source":{"kind":"arxiv","id":"1811.02184","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.02184","created_at":"2026-05-17T23:41:12Z"},{"alias_kind":"arxiv_version","alias_value":"1811.02184v2","created_at":"2026-05-17T23:41:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02184","created_at":"2026-05-17T23:41:12Z"},{"alias_kind":"pith_short_12","alias_value":"OFIBCUN2R35G","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OFIBCUN2R35G6A3H","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OFIBCUN2","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OFIBCUN2R35G6A3H5LHR7EHZYQ","target":"record","payload":{"canonical_record":{"source":{"id":"1811.02184","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-11-06T06:34:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2abc08df5c3e9871ed1b46df565f3e4fbf764df4a2038da1f7426fbefa3b4f1c","abstract_canon_sha256":"b1285c0277ac5834c25a0801264c6ba2a6e75eb37791514fb581ffdef63cbc22"},"schema_version":"1.0"},"canonical_sha256":"71501151ba8efa6f0367eacf1f90f9c4395930c6133d62115d0a2660a2b5bc8c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:12.686731Z","signature_b64":"4m6P4Qa/DCAVp4rLNtRkWs93pTKGS9P7HR7FcLqM1R1O2EL43O3Xe5ibGvLg0uc1K//cZHzy70fN4KJllbQABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71501151ba8efa6f0367eacf1f90f9c4395930c6133d62115d0a2660a2b5bc8c","last_reissued_at":"2026-05-17T23:41:12.686223Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:12.686223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.02184","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CJH6D4HWsr2IJCXbG4U9qxCBZzP2KXn3BTtUNkY+QEayggIz+or3GMR6fEB9yyWDC2mQGPWH5v8+4cyD2bWuBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T01:50:05.670040Z"},"content_sha256":"7e07a726d7d6c98c49ae1c2cc874ee12d322854d0679c3d362b16ea6e9c42a89","schema_version":"1.0","event_id":"sha256:7e07a726d7d6c98c49ae1c2cc874ee12d322854d0679c3d362b16ea6e9c42a89"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OFIBCUN2R35G6A3H5LHR7EHZYQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Regret Convergence Analysis and an Adaptive Regularization Algorithm for On-Policy Robot Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Ajay Kumar Tanwani, Anil Aswani, Jonathan N. Lee, Ken Goldberg, Michael Laskey","submitted_at":"2018-11-06T06:34:39Z","abstract_excerpt":"On-policy imitation learning algorithms such as DAgger evolve a robot control policy by executing it, measuring performance (loss), obtaining corrective feedback from a supervisor, and generating the next policy. As the loss between iterations can vary unpredictably, a fundamental question is under what conditions this process will eventually achieve a converged policy. If one assumes the underlying trajectory distribution is static (stationary), it is possible to prove convergence for DAgger. However, in more realistic models for robotics, the underlying trajectory distribution is dynamic bec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02184","kind":"arxiv","version":2},"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":"2026-05-17T23:41:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u60AcCCvjECS5eU9ZOIRh/UEZMrHZqgmvRi8BOG0Trc+lhtLkk42W/Gh9WT4C3lUZDOaDbbh1UEz7/Cvq3xKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T01:50:05.670708Z"},"content_sha256":"843adc30714d0a44421a38e0ad2bad782c18e915f53ac5dec6ce3182314adf82","schema_version":"1.0","event_id":"sha256:843adc30714d0a44421a38e0ad2bad782c18e915f53ac5dec6ce3182314adf82"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OFIBCUN2R35G6A3H5LHR7EHZYQ/bundle.json","state_url":"https://pith.science/pith/OFIBCUN2R35G6A3H5LHR7EHZYQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OFIBCUN2R35G6A3H5LHR7EHZYQ/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":"2026-06-02T01:50:05Z","links":{"resolver":"https://pith.science/pith/OFIBCUN2R35G6A3H5LHR7EHZYQ","bundle":"https://pith.science/pith/OFIBCUN2R35G6A3H5LHR7EHZYQ/bundle.json","state":"https://pith.science/pith/OFIBCUN2R35G6A3H5LHR7EHZYQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OFIBCUN2R35G6A3H5LHR7EHZYQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OFIBCUN2R35G6A3H5LHR7EHZYQ","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":"b1285c0277ac5834c25a0801264c6ba2a6e75eb37791514fb581ffdef63cbc22","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-11-06T06:34:39Z","title_canon_sha256":"2abc08df5c3e9871ed1b46df565f3e4fbf764df4a2038da1f7426fbefa3b4f1c"},"schema_version":"1.0","source":{"id":"1811.02184","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.02184","created_at":"2026-05-17T23:41:12Z"},{"alias_kind":"arxiv_version","alias_value":"1811.02184v2","created_at":"2026-05-17T23:41:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02184","created_at":"2026-05-17T23:41:12Z"},{"alias_kind":"pith_short_12","alias_value":"OFIBCUN2R35G","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OFIBCUN2R35G6A3H","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OFIBCUN2","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:843adc30714d0a44421a38e0ad2bad782c18e915f53ac5dec6ce3182314adf82","target":"graph","created_at":"2026-05-17T23:41:12Z","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":"On-policy imitation learning algorithms such as DAgger evolve a robot control policy by executing it, measuring performance (loss), obtaining corrective feedback from a supervisor, and generating the next policy. As the loss between iterations can vary unpredictably, a fundamental question is under what conditions this process will eventually achieve a converged policy. If one assumes the underlying trajectory distribution is static (stationary), it is possible to prove convergence for DAgger. However, in more realistic models for robotics, the underlying trajectory distribution is dynamic bec","authors_text":"Ajay Kumar Tanwani, Anil Aswani, Jonathan N. Lee, Ken Goldberg, Michael Laskey","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-11-06T06:34:39Z","title":"Dynamic Regret Convergence Analysis and an Adaptive Regularization Algorithm for On-Policy Robot Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02184","kind":"arxiv","version":2},"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":"sha256:7e07a726d7d6c98c49ae1c2cc874ee12d322854d0679c3d362b16ea6e9c42a89","target":"record","created_at":"2026-05-17T23:41:12Z","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":"b1285c0277ac5834c25a0801264c6ba2a6e75eb37791514fb581ffdef63cbc22","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-11-06T06:34:39Z","title_canon_sha256":"2abc08df5c3e9871ed1b46df565f3e4fbf764df4a2038da1f7426fbefa3b4f1c"},"schema_version":"1.0","source":{"id":"1811.02184","kind":"arxiv","version":2}},"canonical_sha256":"71501151ba8efa6f0367eacf1f90f9c4395930c6133d62115d0a2660a2b5bc8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71501151ba8efa6f0367eacf1f90f9c4395930c6133d62115d0a2660a2b5bc8c","first_computed_at":"2026-05-17T23:41:12.686223Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:12.686223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4m6P4Qa/DCAVp4rLNtRkWs93pTKGS9P7HR7FcLqM1R1O2EL43O3Xe5ibGvLg0uc1K//cZHzy70fN4KJllbQABQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:12.686731Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.02184","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e07a726d7d6c98c49ae1c2cc874ee12d322854d0679c3d362b16ea6e9c42a89","sha256:843adc30714d0a44421a38e0ad2bad782c18e915f53ac5dec6ce3182314adf82"],"state_sha256":"4e7ad95c2278fe38040460b0967e8aefacc27e6b72969721189a17caee9f1eb1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3AuiDBWg39UFbpfhnwVpukdjmlzU99MWh9MW7OE+OFc19Vb1FqAMDxn1hIxvD0FhdpSqXjedlbXj1d2vm7+rDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T01:50:05.674749Z","bundle_sha256":"7f399b01a359e7fef24d61de0f67c4f55d115ce129eb477149da8f4e635826f2"}}