{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:2YYC5EGEUXBFF5OT35ASJLE25U","short_pith_number":"pith:2YYC5EGE","canonical_record":{"source":{"id":"2103.02727","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-03-03T22:32:43Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"7eec4740ccce550ae714cb062e6f4d452b8ebfe93e26194d02f4000b2dcd9cd0","abstract_canon_sha256":"51956b09ed60c595ccf45b5b777ee9dbe756ff98cd2d938454d6c9e9c798dbd5"},"schema_version":"1.0"},"canonical_sha256":"d6302e90c4a5c252f5d3df4124ac9aed11e90ae876c839e871f5feeee92ea365","source":{"kind":"arxiv","id":"2103.02727","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.02727","created_at":"2026-07-05T02:20:20Z"},{"alias_kind":"arxiv_version","alias_value":"2103.02727v1","created_at":"2026-07-05T02:20:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.02727","created_at":"2026-07-05T02:20:20Z"},{"alias_kind":"pith_short_12","alias_value":"2YYC5EGEUXBF","created_at":"2026-07-05T02:20:20Z"},{"alias_kind":"pith_short_16","alias_value":"2YYC5EGEUXBFF5OT","created_at":"2026-07-05T02:20:20Z"},{"alias_kind":"pith_short_8","alias_value":"2YYC5EGE","created_at":"2026-07-05T02:20:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:2YYC5EGEUXBFF5OT35ASJLE25U","target":"record","payload":{"canonical_record":{"source":{"id":"2103.02727","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-03-03T22:32:43Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"7eec4740ccce550ae714cb062e6f4d452b8ebfe93e26194d02f4000b2dcd9cd0","abstract_canon_sha256":"51956b09ed60c595ccf45b5b777ee9dbe756ff98cd2d938454d6c9e9c798dbd5"},"schema_version":"1.0"},"canonical_sha256":"d6302e90c4a5c252f5d3df4124ac9aed11e90ae876c839e871f5feeee92ea365","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:20:20.333348Z","signature_b64":"qqPom1DW3nRs/j8Jjl2ucJHKDhXAgd1TlyTCDLlm+sIlXGVyTHIsqUGPRxWLJ+9zTuL2ZUFCPtTXgBtwAj58Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6302e90c4a5c252f5d3df4124ac9aed11e90ae876c839e871f5feeee92ea365","last_reissued_at":"2026-07-05T02:20:20.332887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:20:20.332887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.02727","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":"2026-07-05T02:20:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IOaXvPFqpwakwzwL4Ug3mGYcQUxHxK44t3BnWnsSqDZXvLJ28JsxumaH5dnqeubowr5Uq3J/H3/af73xO9meBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:37:52.235762Z"},"content_sha256":"d4bac1b840334e984477cb65b377b0495292ffb2be51e1c34968b1d84e2f3123","schema_version":"1.0","event_id":"sha256:d4bac1b840334e984477cb65b377b0495292ffb2be51e1c34968b1d84e2f3123"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:2YYC5EGEUXBFF5OT35ASJLE25U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Preference-based Learning of Reward Function Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.RO","authors_text":"Amir Maleki, Erdem B{\\i}y{\\i}k, Mykel J. Kochenderfer, Sydney M. Katz","submitted_at":"2021-03-03T22:32:43Z","abstract_excerpt":"Preference-based learning of reward functions, where the reward function is learned using comparison data, has been well studied for complex robotic tasks such as autonomous driving. Existing algorithms have focused on learning reward functions that are linear in a set of trajectory features. The features are typically hand-coded, and preference-based learning is used to determine a particular user's relative weighting for each feature. Designing a representative set of features to encode reward is challenging and can result in inaccurate models that fail to model the users' preferences or per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.02727","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/2103.02727/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":"2026-07-05T02:20:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WTRZkYrYch1qeNlMZw9G4nfvIX/uTTEaKj9NgUMePsp+5/bWiahUdRU++9Czo7a6hbUPHRmW5u6l9uXjSm6TCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:37:52.237366Z"},"content_sha256":"e01465f13fd0affa1a86ab593497e25deb852086956a8604c600647e9811a7ab","schema_version":"1.0","event_id":"sha256:e01465f13fd0affa1a86ab593497e25deb852086956a8604c600647e9811a7ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2YYC5EGEUXBFF5OT35ASJLE25U/bundle.json","state_url":"https://pith.science/pith/2YYC5EGEUXBFF5OT35ASJLE25U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2YYC5EGEUXBFF5OT35ASJLE25U/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":"2026-08-01T07:37:52Z","links":{"resolver":"https://pith.science/pith/2YYC5EGEUXBFF5OT35ASJLE25U","bundle":"https://pith.science/pith/2YYC5EGEUXBFF5OT35ASJLE25U/bundle.json","state":"https://pith.science/pith/2YYC5EGEUXBFF5OT35ASJLE25U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2YYC5EGEUXBFF5OT35ASJLE25U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2YYC5EGEUXBFF5OT35ASJLE25U","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":"51956b09ed60c595ccf45b5b777ee9dbe756ff98cd2d938454d6c9e9c798dbd5","cross_cats_sorted":["cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-03-03T22:32:43Z","title_canon_sha256":"7eec4740ccce550ae714cb062e6f4d452b8ebfe93e26194d02f4000b2dcd9cd0"},"schema_version":"1.0","source":{"id":"2103.02727","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.02727","created_at":"2026-07-05T02:20:20Z"},{"alias_kind":"arxiv_version","alias_value":"2103.02727v1","created_at":"2026-07-05T02:20:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.02727","created_at":"2026-07-05T02:20:20Z"},{"alias_kind":"pith_short_12","alias_value":"2YYC5EGEUXBF","created_at":"2026-07-05T02:20:20Z"},{"alias_kind":"pith_short_16","alias_value":"2YYC5EGEUXBFF5OT","created_at":"2026-07-05T02:20:20Z"},{"alias_kind":"pith_short_8","alias_value":"2YYC5EGE","created_at":"2026-07-05T02:20:20Z"}],"graph_snapshots":[{"event_id":"sha256:e01465f13fd0affa1a86ab593497e25deb852086956a8604c600647e9811a7ab","target":"graph","created_at":"2026-07-05T02:20:20Z","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/2103.02727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference-based learning of reward functions, where the reward function is learned using comparison data, has been well studied for complex robotic tasks such as autonomous driving. Existing algorithms have focused on learning reward functions that are linear in a set of trajectory features. The features are typically hand-coded, and preference-based learning is used to determine a particular user's relative weighting for each feature. Designing a representative set of features to encode reward is challenging and can result in inaccurate models that fail to model the users' preferences or per","authors_text":"Amir Maleki, Erdem B{\\i}y{\\i}k, Mykel J. Kochenderfer, Sydney M. Katz","cross_cats":["cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-03-03T22:32:43Z","title":"Preference-based Learning of Reward Function Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.02727","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:d4bac1b840334e984477cb65b377b0495292ffb2be51e1c34968b1d84e2f3123","target":"record","created_at":"2026-07-05T02:20:20Z","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":"51956b09ed60c595ccf45b5b777ee9dbe756ff98cd2d938454d6c9e9c798dbd5","cross_cats_sorted":["cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-03-03T22:32:43Z","title_canon_sha256":"7eec4740ccce550ae714cb062e6f4d452b8ebfe93e26194d02f4000b2dcd9cd0"},"schema_version":"1.0","source":{"id":"2103.02727","kind":"arxiv","version":1}},"canonical_sha256":"d6302e90c4a5c252f5d3df4124ac9aed11e90ae876c839e871f5feeee92ea365","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6302e90c4a5c252f5d3df4124ac9aed11e90ae876c839e871f5feeee92ea365","first_computed_at":"2026-07-05T02:20:20.332887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:20:20.332887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qqPom1DW3nRs/j8Jjl2ucJHKDhXAgd1TlyTCDLlm+sIlXGVyTHIsqUGPRxWLJ+9zTuL2ZUFCPtTXgBtwAj58Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:20:20.333348Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.02727","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4bac1b840334e984477cb65b377b0495292ffb2be51e1c34968b1d84e2f3123","sha256:e01465f13fd0affa1a86ab593497e25deb852086956a8604c600647e9811a7ab"],"state_sha256":"52247bbbb03b1f6a00d652dd0c57ce2f5f3f52deaff70a2276e6abd2457b5de0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kL3I1N0Sqs8UZY82XU8omiGZdHVchCocTz4EBP0xmfWR80Rs2tdz3ZWAyar20UF9aBzp74R7a81aIWEeQoAgAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T07:37:52.243655Z","bundle_sha256":"c7080a09670e827f765fc1f938ab5bc51fce420b46e46b332ac2b6abcf175386"}}