{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:MQ6YXNCUJEFQOR3366SWKBJHMT","short_pith_number":"pith:MQ6YXNCU","canonical_record":{"source":{"id":"1703.01030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-03T04:12:03Z","cross_cats_sorted":[],"title_canon_sha256":"63696ceba1529864c263ef3f8044870bcd7a29e7e3c20ef0dcd51219ab70ded2","abstract_canon_sha256":"63b23a5ac73132959bc96c958c2afc38e46b53bfb15db82e5148a3d00ab6dc58"},"schema_version":"1.0"},"canonical_sha256":"643d8bb454490b07477bf7a565052764f1a32974c78ea50bc96b5b82532395af","source":{"kind":"arxiv","id":"1703.01030","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.01030","created_at":"2026-05-18T00:49:37Z"},{"alias_kind":"arxiv_version","alias_value":"1703.01030v1","created_at":"2026-05-18T00:49:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01030","created_at":"2026-05-18T00:49:37Z"},{"alias_kind":"pith_short_12","alias_value":"MQ6YXNCUJEFQ","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MQ6YXNCUJEFQOR33","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MQ6YXNCU","created_at":"2026-05-18T12:31:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:MQ6YXNCUJEFQOR3366SWKBJHMT","target":"record","payload":{"canonical_record":{"source":{"id":"1703.01030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-03T04:12:03Z","cross_cats_sorted":[],"title_canon_sha256":"63696ceba1529864c263ef3f8044870bcd7a29e7e3c20ef0dcd51219ab70ded2","abstract_canon_sha256":"63b23a5ac73132959bc96c958c2afc38e46b53bfb15db82e5148a3d00ab6dc58"},"schema_version":"1.0"},"canonical_sha256":"643d8bb454490b07477bf7a565052764f1a32974c78ea50bc96b5b82532395af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:37.183226Z","signature_b64":"JjxR6tkDUhooXmZtvcifgG/G82akv+3HP2pDWmy+3EH8U+RNy6Vsizn4/e7f/6/sdMgwh22cqDKwTmh1cau6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"643d8bb454490b07477bf7a565052764f1a32974c78ea50bc96b5b82532395af","last_reissued_at":"2026-05-18T00:49:37.182516Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:37.182516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.01030","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":"2026-05-18T00:49:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jRcqbw8vMWeg7FN6W6WynOvLmhyDVt1+hY8lSBEAjV9pEVfzwKIPiwnsEYoNOufThRqpaNFkjse9bPBJYOtoAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T19:06:27.155219Z"},"content_sha256":"618ede815f1256a47e3aca99dd8cdecc880c139a97a04a17d55b92bad289f86d","schema_version":"1.0","event_id":"sha256:618ede815f1256a47e3aca99dd8cdecc880c139a97a04a17d55b92bad289f86d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:MQ6YXNCUJEFQOR3366SWKBJHMT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arun Venkatraman, Byron Boots, Geoffrey J. Gordon, J. Andrew Bagnell, Wen Sun","submitted_at":"2017-03-03T04:12:03Z","abstract_excerpt":"Researchers have demonstrated state-of-the-art performance in sequential decision making problems (e.g., robotics control, sequential prediction) with deep neural network models. One often has access to near-optimal oracles that achieve good performance on the task during training. We demonstrate that AggreVaTeD --- a policy gradient extension of the Imitation Learning (IL) approach of (Ross & Bagnell, 2014) --- can leverage such an oracle to achieve faster and better solutions with less training data than a less-informed Reinforcement Learning (RL) technique. Using both feedforward and recurr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01030","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":""},"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":"2026-05-18T00:49:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"doB0wHR4D2ozl5JlhCTIrPeq4I0AtAdWQjiR9+6QUedD+JkyROseeQHXweML6T4EBVlnUztC/TYtvrUUdxLeBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T19:06:27.155757Z"},"content_sha256":"11aca676ee13a32af052836d7d8f231c891e7bfeecf8569cd58c888a2fd65145","schema_version":"1.0","event_id":"sha256:11aca676ee13a32af052836d7d8f231c891e7bfeecf8569cd58c888a2fd65145"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MQ6YXNCUJEFQOR3366SWKBJHMT/bundle.json","state_url":"https://pith.science/pith/MQ6YXNCUJEFQOR3366SWKBJHMT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MQ6YXNCUJEFQOR3366SWKBJHMT/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":"2026-05-23T19:06:27Z","links":{"resolver":"https://pith.science/pith/MQ6YXNCUJEFQOR3366SWKBJHMT","bundle":"https://pith.science/pith/MQ6YXNCUJEFQOR3366SWKBJHMT/bundle.json","state":"https://pith.science/pith/MQ6YXNCUJEFQOR3366SWKBJHMT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MQ6YXNCUJEFQOR3366SWKBJHMT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:MQ6YXNCUJEFQOR3366SWKBJHMT","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":"63b23a5ac73132959bc96c958c2afc38e46b53bfb15db82e5148a3d00ab6dc58","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-03T04:12:03Z","title_canon_sha256":"63696ceba1529864c263ef3f8044870bcd7a29e7e3c20ef0dcd51219ab70ded2"},"schema_version":"1.0","source":{"id":"1703.01030","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.01030","created_at":"2026-05-18T00:49:37Z"},{"alias_kind":"arxiv_version","alias_value":"1703.01030v1","created_at":"2026-05-18T00:49:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01030","created_at":"2026-05-18T00:49:37Z"},{"alias_kind":"pith_short_12","alias_value":"MQ6YXNCUJEFQ","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MQ6YXNCUJEFQOR33","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MQ6YXNCU","created_at":"2026-05-18T12:31:31Z"}],"graph_snapshots":[{"event_id":"sha256:11aca676ee13a32af052836d7d8f231c891e7bfeecf8569cd58c888a2fd65145","target":"graph","created_at":"2026-05-18T00:49:37Z","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":"Researchers have demonstrated state-of-the-art performance in sequential decision making problems (e.g., robotics control, sequential prediction) with deep neural network models. One often has access to near-optimal oracles that achieve good performance on the task during training. We demonstrate that AggreVaTeD --- a policy gradient extension of the Imitation Learning (IL) approach of (Ross & Bagnell, 2014) --- can leverage such an oracle to achieve faster and better solutions with less training data than a less-informed Reinforcement Learning (RL) technique. Using both feedforward and recurr","authors_text":"Arun Venkatraman, Byron Boots, Geoffrey J. Gordon, J. Andrew Bagnell, Wen Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-03T04:12:03Z","title":"Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01030","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":"sha256:618ede815f1256a47e3aca99dd8cdecc880c139a97a04a17d55b92bad289f86d","target":"record","created_at":"2026-05-18T00:49:37Z","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":"63b23a5ac73132959bc96c958c2afc38e46b53bfb15db82e5148a3d00ab6dc58","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-03T04:12:03Z","title_canon_sha256":"63696ceba1529864c263ef3f8044870bcd7a29e7e3c20ef0dcd51219ab70ded2"},"schema_version":"1.0","source":{"id":"1703.01030","kind":"arxiv","version":1}},"canonical_sha256":"643d8bb454490b07477bf7a565052764f1a32974c78ea50bc96b5b82532395af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"643d8bb454490b07477bf7a565052764f1a32974c78ea50bc96b5b82532395af","first_computed_at":"2026-05-18T00:49:37.182516Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:49:37.182516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JjxR6tkDUhooXmZtvcifgG/G82akv+3HP2pDWmy+3EH8U+RNy6Vsizn4/e7f/6/sdMgwh22cqDKwTmh1cau6CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:49:37.183226Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.01030","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:618ede815f1256a47e3aca99dd8cdecc880c139a97a04a17d55b92bad289f86d","sha256:11aca676ee13a32af052836d7d8f231c891e7bfeecf8569cd58c888a2fd65145"],"state_sha256":"076e218a02ccdd476c7172d625fb6a4c01cd8a48238cdb8b815013ebb530d61a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"14EiEM8/4xLrQkRArWUJ4ybwahuoseRS9bveiiPxah0eVvtjysdxaixTpaM5YwXb1QSVELm3O2xpnGg2RzrzDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T19:06:27.160443Z","bundle_sha256":"b838947d9afa4390b8ceb8f49236028261eeba373007c1c643402ac1b4343bb7"}}