{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:PJXOUXDESEXIZE5NOYVXOTEQME","short_pith_number":"pith:PJXOUXDE","canonical_record":{"source":{"id":"2005.02575","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-05-06T03:29:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a2b081768e8b491c1a0fa828519199401ec75cc468ae5c3e347d31a9a6cbd619","abstract_canon_sha256":"edf1c6c32f6d2d2c4af96e015debc23c6bb927a0b871f9abcf2e9b807751537c"},"schema_version":"1.0"},"canonical_sha256":"7a6eea5c64912e8c93ad762b774c90612f01074ebbd28249e4f8e58e3b246684","source":{"kind":"arxiv","id":"2005.02575","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.02575","created_at":"2026-07-05T01:07:53Z"},{"alias_kind":"arxiv_version","alias_value":"2005.02575v2","created_at":"2026-07-05T01:07:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.02575","created_at":"2026-07-05T01:07:53Z"},{"alias_kind":"pith_short_12","alias_value":"PJXOUXDESEXI","created_at":"2026-07-05T01:07:53Z"},{"alias_kind":"pith_short_16","alias_value":"PJXOUXDESEXIZE5N","created_at":"2026-07-05T01:07:53Z"},{"alias_kind":"pith_short_8","alias_value":"PJXOUXDE","created_at":"2026-07-05T01:07:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:PJXOUXDESEXIZE5NOYVXOTEQME","target":"record","payload":{"canonical_record":{"source":{"id":"2005.02575","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-05-06T03:29:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a2b081768e8b491c1a0fa828519199401ec75cc468ae5c3e347d31a9a6cbd619","abstract_canon_sha256":"edf1c6c32f6d2d2c4af96e015debc23c6bb927a0b871f9abcf2e9b807751537c"},"schema_version":"1.0"},"canonical_sha256":"7a6eea5c64912e8c93ad762b774c90612f01074ebbd28249e4f8e58e3b246684","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:07:53.893680Z","signature_b64":"HXXnIXfAJI5wbuA88MpCfd0U4pixx2BRYjd6OIhsXKDYBKj9k0RyfRMWOX9pchlPLnYAymd1xxZ8C14w01ejBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a6eea5c64912e8c93ad762b774c90612f01074ebbd28249e4f8e58e3b246684","last_reissued_at":"2026-07-05T01:07:53.893139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:07:53.893139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.02575","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":"2026-07-05T01:07:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PPFNLOYOauADDB1IhAZlfEuFgjsI7sHkPXAbQzr/jigQzbMlu2idwCv5pBfm6XWDHH+3rnsNBTO3vzCSPl3iCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:41:22.285494Z"},"content_sha256":"d5980d9d1fba02caa3933a723339f26e3e1307aa24b0a661740c0c2398fdb0e9","schema_version":"1.0","event_id":"sha256:d5980d9d1fba02caa3933a723339f26e3e1307aa24b0a661740c0c2398fdb0e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:PJXOUXDESEXIZE5NOYVXOTEQME","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Active Preference-Based Gaussian Process Regression for Reward Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Dorsa Sadigh, Erdem B{\\i}y{\\i}k, Mykel J. Kochenderfer, Nicolas Huynh","submitted_at":"2020-05-06T03:29:27Z","abstract_excerpt":"Designing reward functions is a challenging problem in AI and robotics. Humans usually have a difficult time directly specifying all the desirable behaviors that a robot needs to optimize. One common approach is to learn reward functions from collected expert demonstrations. However, learning reward functions from demonstrations introduces many challenges: some methods require highly structured models, e.g. reward functions that are linear in some predefined set of features, while others adopt less structured reward functions that on the other hand require tremendous amount of data. In additio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.02575","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.02575/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":"2026-07-05T01:07:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8e0HGIrgQVfTUYUiMdrf/z0UcUD3w/EdPYLbkulY1hQwVxyyJZF8DLkUuxCYd87JD0sMxjrDst/ju93qSyTjCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:41:22.285884Z"},"content_sha256":"5663a1bc9afa868f213dda4acef0173bee55b8e756808be0da3ae4b7a9702ba0","schema_version":"1.0","event_id":"sha256:5663a1bc9afa868f213dda4acef0173bee55b8e756808be0da3ae4b7a9702ba0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PJXOUXDESEXIZE5NOYVXOTEQME/bundle.json","state_url":"https://pith.science/pith/PJXOUXDESEXIZE5NOYVXOTEQME/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PJXOUXDESEXIZE5NOYVXOTEQME/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":"2026-07-07T08:41:22Z","links":{"resolver":"https://pith.science/pith/PJXOUXDESEXIZE5NOYVXOTEQME","bundle":"https://pith.science/pith/PJXOUXDESEXIZE5NOYVXOTEQME/bundle.json","state":"https://pith.science/pith/PJXOUXDESEXIZE5NOYVXOTEQME/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PJXOUXDESEXIZE5NOYVXOTEQME/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PJXOUXDESEXIZE5NOYVXOTEQME","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":"edf1c6c32f6d2d2c4af96e015debc23c6bb927a0b871f9abcf2e9b807751537c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-05-06T03:29:27Z","title_canon_sha256":"a2b081768e8b491c1a0fa828519199401ec75cc468ae5c3e347d31a9a6cbd619"},"schema_version":"1.0","source":{"id":"2005.02575","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.02575","created_at":"2026-07-05T01:07:53Z"},{"alias_kind":"arxiv_version","alias_value":"2005.02575v2","created_at":"2026-07-05T01:07:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.02575","created_at":"2026-07-05T01:07:53Z"},{"alias_kind":"pith_short_12","alias_value":"PJXOUXDESEXI","created_at":"2026-07-05T01:07:53Z"},{"alias_kind":"pith_short_16","alias_value":"PJXOUXDESEXIZE5N","created_at":"2026-07-05T01:07:53Z"},{"alias_kind":"pith_short_8","alias_value":"PJXOUXDE","created_at":"2026-07-05T01:07:53Z"}],"graph_snapshots":[{"event_id":"sha256:5663a1bc9afa868f213dda4acef0173bee55b8e756808be0da3ae4b7a9702ba0","target":"graph","created_at":"2026-07-05T01:07:53Z","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/2005.02575/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing reward functions is a challenging problem in AI and robotics. Humans usually have a difficult time directly specifying all the desirable behaviors that a robot needs to optimize. One common approach is to learn reward functions from collected expert demonstrations. However, learning reward functions from demonstrations introduces many challenges: some methods require highly structured models, e.g. reward functions that are linear in some predefined set of features, while others adopt less structured reward functions that on the other hand require tremendous amount of data. In additio","authors_text":"Dorsa Sadigh, Erdem B{\\i}y{\\i}k, Mykel J. Kochenderfer, Nicolas Huynh","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-05-06T03:29:27Z","title":"Active Preference-Based Gaussian Process Regression for Reward Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.02575","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:d5980d9d1fba02caa3933a723339f26e3e1307aa24b0a661740c0c2398fdb0e9","target":"record","created_at":"2026-07-05T01:07:53Z","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":"edf1c6c32f6d2d2c4af96e015debc23c6bb927a0b871f9abcf2e9b807751537c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-05-06T03:29:27Z","title_canon_sha256":"a2b081768e8b491c1a0fa828519199401ec75cc468ae5c3e347d31a9a6cbd619"},"schema_version":"1.0","source":{"id":"2005.02575","kind":"arxiv","version":2}},"canonical_sha256":"7a6eea5c64912e8c93ad762b774c90612f01074ebbd28249e4f8e58e3b246684","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a6eea5c64912e8c93ad762b774c90612f01074ebbd28249e4f8e58e3b246684","first_computed_at":"2026-07-05T01:07:53.893139Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:07:53.893139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HXXnIXfAJI5wbuA88MpCfd0U4pixx2BRYjd6OIhsXKDYBKj9k0RyfRMWOX9pchlPLnYAymd1xxZ8C14w01ejBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:07:53.893680Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.02575","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5980d9d1fba02caa3933a723339f26e3e1307aa24b0a661740c0c2398fdb0e9","sha256:5663a1bc9afa868f213dda4acef0173bee55b8e756808be0da3ae4b7a9702ba0"],"state_sha256":"eb7ae46dbaeb3f11acb6985d0e031a0e28896ba128d1fb9e1b71c19db3a4b46c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t+lj036wUP+2Q+cV1rbzTMo/qmCjx0EKJtyPjbtE+trjiYXfEqf86Feh6/rSeWpdwLhctoKnXYzo8wQKY2K+DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:41:22.287826Z","bundle_sha256":"caba3739ed17252d960380aad929dd1ca7962a162992bd01cfd27075417191bc"}}