{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:B6FNNQCXTD7S7WDJJ4BJZ5726R","short_pith_number":"pith:B6FNNQCX","canonical_record":{"source":{"id":"2103.08070","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-03-15T00:04:13Z","cross_cats_sorted":[],"title_canon_sha256":"92a13b50e28690d94e485c066b62809ad9072f70664fe6ce565e19f6e52d92d1","abstract_canon_sha256":"27cb13829e5ba0581c24008203c646876125d53e55b72efc272c3ab79bd45cdf"},"schema_version":"1.0"},"canonical_sha256":"0f8ad6c05798ff2fd8694f029cf7faf47702179de073379d5a812afd37144e02","source":{"kind":"arxiv","id":"2103.08070","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.08070","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"arxiv_version","alias_value":"2103.08070v1","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.08070","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"pith_short_12","alias_value":"B6FNNQCXTD7S","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"pith_short_16","alias_value":"B6FNNQCXTD7S7WDJ","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"pith_short_8","alias_value":"B6FNNQCX","created_at":"2026-07-05T02:22:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:B6FNNQCXTD7S7WDJJ4BJZ5726R","target":"record","payload":{"canonical_record":{"source":{"id":"2103.08070","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-03-15T00:04:13Z","cross_cats_sorted":[],"title_canon_sha256":"92a13b50e28690d94e485c066b62809ad9072f70664fe6ce565e19f6e52d92d1","abstract_canon_sha256":"27cb13829e5ba0581c24008203c646876125d53e55b72efc272c3ab79bd45cdf"},"schema_version":"1.0"},"canonical_sha256":"0f8ad6c05798ff2fd8694f029cf7faf47702179de073379d5a812afd37144e02","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:47.556348Z","signature_b64":"J+5tj4M2YDOrKCEHrZU713AgINNWMl0vGkvEc5oSF9fB+w+dEYwQBjj8s2dGCtwB82xC/98b5VgCXguH/1pSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f8ad6c05798ff2fd8694f029cf7faf47702179de073379d5a812afd37144e02","last_reissued_at":"2026-07-05T02:22:47.555798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:47.555798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.08070","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":"2026-07-05T02:22:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q4QxYxMwRmEJNNIyEzhHoUO68mliiFm1FVak8iv9cP02ogZjfz7Dbq/PAKgSNSVhVVQUf423LpOAVJR2DNa/Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T12:57:18.418917Z"},"content_sha256":"996c7ff8f63029d0862d0e8d7b2900f1fd784633f135db6a2005542c6f247c8e","schema_version":"1.0","event_id":"sha256:996c7ff8f63029d0862d0e8d7b2900f1fd784633f135db6a2005542c6f247c8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:B6FNNQCXTD7S7WDJJ4BJZ5726R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning robust driving policies without online exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Daniel Graves, Jun Jin, Jun Luo, Kimia Hassanzadeh, Nhat M. Nguyen","submitted_at":"2021-03-15T00:04:13Z","abstract_excerpt":"We propose a multi-time-scale predictive representation learning method to efficiently learn robust driving policies in an offline manner that generalize well to novel road geometries, and damaged and distracting lane conditions which are not covered in the offline training data. We show that our proposed representation learning method can be applied easily in an offline (batch) reinforcement learning setting demonstrating the ability to generalize well and efficiently under novel conditions compared to standard batch RL methods. Our proposed method utilizes training data collected entirely of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.08070","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/2103.08070/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":"2026-07-05T02:22:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vq2Nrl1e68tW2SshzYYWrXTh+pfBtgjmoBW8wpILvI++iFZkB5gTB7TPT8nxzKYrxPzzpOFkCdn0rQoJUG6DDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T12:57:18.419685Z"},"content_sha256":"dafd6c09382086735c9f37884bb6af5fc76905ff6373c57727f475ac1ed5bd7f","schema_version":"1.0","event_id":"sha256:dafd6c09382086735c9f37884bb6af5fc76905ff6373c57727f475ac1ed5bd7f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B6FNNQCXTD7S7WDJJ4BJZ5726R/bundle.json","state_url":"https://pith.science/pith/B6FNNQCXTD7S7WDJJ4BJZ5726R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B6FNNQCXTD7S7WDJJ4BJZ5726R/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":"2026-07-05T12:57:18Z","links":{"resolver":"https://pith.science/pith/B6FNNQCXTD7S7WDJJ4BJZ5726R","bundle":"https://pith.science/pith/B6FNNQCXTD7S7WDJJ4BJZ5726R/bundle.json","state":"https://pith.science/pith/B6FNNQCXTD7S7WDJJ4BJZ5726R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B6FNNQCXTD7S7WDJJ4BJZ5726R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:B6FNNQCXTD7S7WDJJ4BJZ5726R","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":"27cb13829e5ba0581c24008203c646876125d53e55b72efc272c3ab79bd45cdf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-03-15T00:04:13Z","title_canon_sha256":"92a13b50e28690d94e485c066b62809ad9072f70664fe6ce565e19f6e52d92d1"},"schema_version":"1.0","source":{"id":"2103.08070","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.08070","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"arxiv_version","alias_value":"2103.08070v1","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.08070","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"pith_short_12","alias_value":"B6FNNQCXTD7S","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"pith_short_16","alias_value":"B6FNNQCXTD7S7WDJ","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"pith_short_8","alias_value":"B6FNNQCX","created_at":"2026-07-05T02:22:47Z"}],"graph_snapshots":[{"event_id":"sha256:dafd6c09382086735c9f37884bb6af5fc76905ff6373c57727f475ac1ed5bd7f","target":"graph","created_at":"2026-07-05T02:22:47Z","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/2103.08070/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a multi-time-scale predictive representation learning method to efficiently learn robust driving policies in an offline manner that generalize well to novel road geometries, and damaged and distracting lane conditions which are not covered in the offline training data. We show that our proposed representation learning method can be applied easily in an offline (batch) reinforcement learning setting demonstrating the ability to generalize well and efficiently under novel conditions compared to standard batch RL methods. Our proposed method utilizes training data collected entirely of","authors_text":"Daniel Graves, Jun Jin, Jun Luo, Kimia Hassanzadeh, Nhat M. Nguyen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-03-15T00:04:13Z","title":"Learning robust driving policies without online exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.08070","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":"sha256:996c7ff8f63029d0862d0e8d7b2900f1fd784633f135db6a2005542c6f247c8e","target":"record","created_at":"2026-07-05T02:22:47Z","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":"27cb13829e5ba0581c24008203c646876125d53e55b72efc272c3ab79bd45cdf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-03-15T00:04:13Z","title_canon_sha256":"92a13b50e28690d94e485c066b62809ad9072f70664fe6ce565e19f6e52d92d1"},"schema_version":"1.0","source":{"id":"2103.08070","kind":"arxiv","version":1}},"canonical_sha256":"0f8ad6c05798ff2fd8694f029cf7faf47702179de073379d5a812afd37144e02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f8ad6c05798ff2fd8694f029cf7faf47702179de073379d5a812afd37144e02","first_computed_at":"2026-07-05T02:22:47.555798Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:22:47.555798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J+5tj4M2YDOrKCEHrZU713AgINNWMl0vGkvEc5oSF9fB+w+dEYwQBjj8s2dGCtwB82xC/98b5VgCXguH/1pSAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:22:47.556348Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.08070","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:996c7ff8f63029d0862d0e8d7b2900f1fd784633f135db6a2005542c6f247c8e","sha256:dafd6c09382086735c9f37884bb6af5fc76905ff6373c57727f475ac1ed5bd7f"],"state_sha256":"44ffb2b45fb75a3e16be75e287f47269fe7cc94c9c1e793192c7c863849a2c3c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/v8R9LRp95okXGotOxXDAbRnGYLd3WXVOSSw+qeSKCoBD9CFeUlvnPMpDdVhG5E1j4OolY+nt431x7JlKm72Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T12:57:18.424487Z","bundle_sha256":"f01485ccb93e0c63a2839b19dc657413d087ed81ed334a2ac19bef77eb8c7626"}}