{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Z47JLLHC3ZD6WCCVJLLQKBNKF3","short_pith_number":"pith:Z47JLLHC","canonical_record":{"source":{"id":"2403.06003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-09T20:32:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4f65393a7e8ed880ac7cb478177281729c119968d06cb81ee4de60638024d1e0","abstract_canon_sha256":"47b997533990ad9498aa2ee0b96a08801ad2f5aeda3542ceec72942d1c9c358a"},"schema_version":"1.0"},"canonical_sha256":"cf3e95ace2de47eb08554ad70505aa2efb3d4a1449de083e483601282387f0cc","source":{"kind":"arxiv","id":"2403.06003","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06003","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06003v1","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06003","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"pith_short_12","alias_value":"Z47JLLHC3ZD6","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"pith_short_16","alias_value":"Z47JLLHC3ZD6WCCV","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"pith_short_8","alias_value":"Z47JLLHC","created_at":"2026-07-05T07:54:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Z47JLLHC3ZD6WCCVJLLQKBNKF3","target":"record","payload":{"canonical_record":{"source":{"id":"2403.06003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-09T20:32:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4f65393a7e8ed880ac7cb478177281729c119968d06cb81ee4de60638024d1e0","abstract_canon_sha256":"47b997533990ad9498aa2ee0b96a08801ad2f5aeda3542ceec72942d1c9c358a"},"schema_version":"1.0"},"canonical_sha256":"cf3e95ace2de47eb08554ad70505aa2efb3d4a1449de083e483601282387f0cc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:16.703781Z","signature_b64":"D+4VCF+isp+iak+YyhZRVFdYtAnsmomCFBO/gZQ/i84b9sNpqm7I+ihA5CXNloenI3atuAP5orvj2pkHCF+FCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf3e95ace2de47eb08554ad70505aa2efb3d4a1449de083e483601282387f0cc","last_reissued_at":"2026-07-05T07:54:16.703411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:16.703411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.06003","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":"2026-07-05T07:54:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qFBxvWU8wiaY4jIFMuFVc7Q6HnU/g/TPzL6wYVL3TUxTRND0/dG/2cakp7cslcxJP/pWS8XsWkeebk4N+JTqCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:38:43.720605Z"},"content_sha256":"253d0da94b953241fe50697e85495a6e4c5ced0ec8e733cc1551675760d84814","schema_version":"1.0","event_id":"sha256:253d0da94b953241fe50697e85495a6e4c5ced0ec8e733cc1551675760d84814"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Z47JLLHC3ZD6WCCVJLLQKBNKF3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Generalized Acquisition Function for Preference-based Reward Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Anca Dragan, Erdem B{\\i}y{\\i}k, Evan Ellis, Gaurav R. Ghosal, Stuart J. Russell","submitted_at":"2024-03-09T20:32:17Z","abstract_excerpt":"Preference-based reward learning is a popular technique for teaching robots and autonomous systems how a human user wants them to perform a task. Previous works have shown that actively synthesizing preference queries to maximize information gain about the reward function parameters improves data efficiency. The information gain criterion focuses on precisely identifying all parameters of the reward function. This can potentially be wasteful as many parameters may result in the same reward, and many rewards may result in the same behavior in the downstream tasks. Instead, we show that it is po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06003","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/2403.06003/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":"2026-07-05T07:54:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gwC0xGfR44Ks+QndShesyrU0XIwUFUKercZSNga8MwnYaI2ws/KMZ85Toqa/kx+jtpSl2LOu5a4xkEDgIvLvCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:38:43.720988Z"},"content_sha256":"5f473ff1567b5a413a22379881f2c12d585aa5fc5fdb8e1ec879148ba338788b","schema_version":"1.0","event_id":"sha256:5f473ff1567b5a413a22379881f2c12d585aa5fc5fdb8e1ec879148ba338788b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z47JLLHC3ZD6WCCVJLLQKBNKF3/bundle.json","state_url":"https://pith.science/pith/Z47JLLHC3ZD6WCCVJLLQKBNKF3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z47JLLHC3ZD6WCCVJLLQKBNKF3/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":"2026-07-06T18:38:43Z","links":{"resolver":"https://pith.science/pith/Z47JLLHC3ZD6WCCVJLLQKBNKF3","bundle":"https://pith.science/pith/Z47JLLHC3ZD6WCCVJLLQKBNKF3/bundle.json","state":"https://pith.science/pith/Z47JLLHC3ZD6WCCVJLLQKBNKF3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z47JLLHC3ZD6WCCVJLLQKBNKF3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z47JLLHC3ZD6WCCVJLLQKBNKF3","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":"47b997533990ad9498aa2ee0b96a08801ad2f5aeda3542ceec72942d1c9c358a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-09T20:32:17Z","title_canon_sha256":"4f65393a7e8ed880ac7cb478177281729c119968d06cb81ee4de60638024d1e0"},"schema_version":"1.0","source":{"id":"2403.06003","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06003","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06003v1","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06003","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"pith_short_12","alias_value":"Z47JLLHC3ZD6","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"pith_short_16","alias_value":"Z47JLLHC3ZD6WCCV","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"pith_short_8","alias_value":"Z47JLLHC","created_at":"2026-07-05T07:54:16Z"}],"graph_snapshots":[{"event_id":"sha256:5f473ff1567b5a413a22379881f2c12d585aa5fc5fdb8e1ec879148ba338788b","target":"graph","created_at":"2026-07-05T07:54:16Z","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/2403.06003/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference-based reward learning is a popular technique for teaching robots and autonomous systems how a human user wants them to perform a task. Previous works have shown that actively synthesizing preference queries to maximize information gain about the reward function parameters improves data efficiency. The information gain criterion focuses on precisely identifying all parameters of the reward function. This can potentially be wasteful as many parameters may result in the same reward, and many rewards may result in the same behavior in the downstream tasks. Instead, we show that it is po","authors_text":"Anca Dragan, Erdem B{\\i}y{\\i}k, Evan Ellis, Gaurav R. Ghosal, Stuart J. Russell","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-09T20:32:17Z","title":"A Generalized Acquisition Function for Preference-based Reward Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06003","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":"sha256:253d0da94b953241fe50697e85495a6e4c5ced0ec8e733cc1551675760d84814","target":"record","created_at":"2026-07-05T07:54:16Z","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":"47b997533990ad9498aa2ee0b96a08801ad2f5aeda3542ceec72942d1c9c358a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-09T20:32:17Z","title_canon_sha256":"4f65393a7e8ed880ac7cb478177281729c119968d06cb81ee4de60638024d1e0"},"schema_version":"1.0","source":{"id":"2403.06003","kind":"arxiv","version":1}},"canonical_sha256":"cf3e95ace2de47eb08554ad70505aa2efb3d4a1449de083e483601282387f0cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf3e95ace2de47eb08554ad70505aa2efb3d4a1449de083e483601282387f0cc","first_computed_at":"2026-07-05T07:54:16.703411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:54:16.703411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D+4VCF+isp+iak+YyhZRVFdYtAnsmomCFBO/gZQ/i84b9sNpqm7I+ihA5CXNloenI3atuAP5orvj2pkHCF+FCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:54:16.703781Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06003","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:253d0da94b953241fe50697e85495a6e4c5ced0ec8e733cc1551675760d84814","sha256:5f473ff1567b5a413a22379881f2c12d585aa5fc5fdb8e1ec879148ba338788b"],"state_sha256":"de63c138fc69b5a07390782a4ff1e8aeca75908fc0267e161585db9fd74eb24b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5T8O8SfRzBCRlIfBq3VMvN75dK6z6r0994aTi6A4+al9Ikw7/sO4p05ujBQDypPnlsA+XXWdknHJe4f27r18Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:38:43.722930Z","bundle_sha256":"8788074d39cd2c37b142eda27db40b4e2fd40a97e0999faa59f8c0f4f47c6a37"}}