{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GAHHQY7LQVBNZMQLOYVFSJ2EBO","short_pith_number":"pith:GAHHQY7L","canonical_record":{"source":{"id":"2101.07691","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-01-19T15:35:30Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"1ada033e0435055f548a74064cead67beaf8f00a54744a42613af71320d0de2a","abstract_canon_sha256":"135b41ee861dde7c68b561e71fd0b225871891e7d917bc0e1428b121ed17dfae"},"schema_version":"1.0"},"canonical_sha256":"300e7863eb8542dcb20b762a5927440bacbc6df51e610124fa321343bec4639b","source":{"kind":"arxiv","id":"2101.07691","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.07691","created_at":"2026-07-05T02:08:00Z"},{"alias_kind":"arxiv_version","alias_value":"2101.07691v1","created_at":"2026-07-05T02:08:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.07691","created_at":"2026-07-05T02:08:00Z"},{"alias_kind":"pith_short_12","alias_value":"GAHHQY7LQVBN","created_at":"2026-07-05T02:08:00Z"},{"alias_kind":"pith_short_16","alias_value":"GAHHQY7LQVBNZMQL","created_at":"2026-07-05T02:08:00Z"},{"alias_kind":"pith_short_8","alias_value":"GAHHQY7L","created_at":"2026-07-05T02:08:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GAHHQY7LQVBNZMQLOYVFSJ2EBO","target":"record","payload":{"canonical_record":{"source":{"id":"2101.07691","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-01-19T15:35:30Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"1ada033e0435055f548a74064cead67beaf8f00a54744a42613af71320d0de2a","abstract_canon_sha256":"135b41ee861dde7c68b561e71fd0b225871891e7d917bc0e1428b121ed17dfae"},"schema_version":"1.0"},"canonical_sha256":"300e7863eb8542dcb20b762a5927440bacbc6df51e610124fa321343bec4639b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:08:00.329114Z","signature_b64":"MRQgvNcVm6VP/EGkNYIX68Cy9mn/PN8feRtl35Tgfyxokg+sdArnqf/Hi8jg+/55Q9exums+P6SekcOm+8hhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"300e7863eb8542dcb20b762a5927440bacbc6df51e610124fa321343bec4639b","last_reissued_at":"2026-07-05T02:08:00.328648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:08:00.328648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.07691","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":"2026-07-05T02:08:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w3uYiL0mX/66HaHJWGIjhR7H+mumnXJAwhDmaIY50sDRebQLk+oFOjim53zOzJVN64dY4QomAXCVjIjuQ4HWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:29:04.276378Z"},"content_sha256":"227ac61f18a994fef631b67f814434ffa7948f17342b00c911e7311166fba53a","schema_version":"1.0","event_id":"sha256:227ac61f18a994fef631b67f814434ffa7948f17342b00c911e7311166fba53a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GAHHQY7LQVBNZMQLOYVFSJ2EBO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Choice Set Misspecification in Reward Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Anca Dragan, Rachel Freedman, Rohin Shah","submitted_at":"2021-01-19T15:35:30Z","abstract_excerpt":"Specifying reward functions for robots that operate in environments without a natural reward signal can be challenging, and incorrectly specified rewards can incentivise degenerate or dangerous behavior. A promising alternative to manually specifying reward functions is to enable robots to infer them from human feedback, like demonstrations or corrections. To interpret this feedback, robots treat as approximately optimal a choice the person makes from a choice set, like the set of possible trajectories they could have demonstrated or possible corrections they could have made. In this work, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.07691","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/2101.07691/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":"2026-07-05T02:08:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dfFKbXGq0kcewjDrlI226epIpPr0lhTiUeJcKUdzypk8e0+8dC3VsFvLyrkne3JuFub7gRUXlSIMz3uVbVc6Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:29:04.277211Z"},"content_sha256":"3c00e098e945d69e924a1c31975f16c314e3687c871cfd40b4d04c90e82fe221","schema_version":"1.0","event_id":"sha256:3c00e098e945d69e924a1c31975f16c314e3687c871cfd40b4d04c90e82fe221"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GAHHQY7LQVBNZMQLOYVFSJ2EBO/bundle.json","state_url":"https://pith.science/pith/GAHHQY7LQVBNZMQLOYVFSJ2EBO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GAHHQY7LQVBNZMQLOYVFSJ2EBO/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":"2026-08-17T21:29:04Z","links":{"resolver":"https://pith.science/pith/GAHHQY7LQVBNZMQLOYVFSJ2EBO","bundle":"https://pith.science/pith/GAHHQY7LQVBNZMQLOYVFSJ2EBO/bundle.json","state":"https://pith.science/pith/GAHHQY7LQVBNZMQLOYVFSJ2EBO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GAHHQY7LQVBNZMQLOYVFSJ2EBO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GAHHQY7LQVBNZMQLOYVFSJ2EBO","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":"135b41ee861dde7c68b561e71fd0b225871891e7d917bc0e1428b121ed17dfae","cross_cats_sorted":["cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-01-19T15:35:30Z","title_canon_sha256":"1ada033e0435055f548a74064cead67beaf8f00a54744a42613af71320d0de2a"},"schema_version":"1.0","source":{"id":"2101.07691","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.07691","created_at":"2026-07-05T02:08:00Z"},{"alias_kind":"arxiv_version","alias_value":"2101.07691v1","created_at":"2026-07-05T02:08:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.07691","created_at":"2026-07-05T02:08:00Z"},{"alias_kind":"pith_short_12","alias_value":"GAHHQY7LQVBN","created_at":"2026-07-05T02:08:00Z"},{"alias_kind":"pith_short_16","alias_value":"GAHHQY7LQVBNZMQL","created_at":"2026-07-05T02:08:00Z"},{"alias_kind":"pith_short_8","alias_value":"GAHHQY7L","created_at":"2026-07-05T02:08:00Z"}],"graph_snapshots":[{"event_id":"sha256:3c00e098e945d69e924a1c31975f16c314e3687c871cfd40b4d04c90e82fe221","target":"graph","created_at":"2026-07-05T02:08:00Z","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/2101.07691/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Specifying reward functions for robots that operate in environments without a natural reward signal can be challenging, and incorrectly specified rewards can incentivise degenerate or dangerous behavior. A promising alternative to manually specifying reward functions is to enable robots to infer them from human feedback, like demonstrations or corrections. To interpret this feedback, robots treat as approximately optimal a choice the person makes from a choice set, like the set of possible trajectories they could have demonstrated or possible corrections they could have made. In this work, we ","authors_text":"Anca Dragan, Rachel Freedman, Rohin Shah","cross_cats":["cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-01-19T15:35:30Z","title":"Choice Set Misspecification in Reward Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.07691","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":"sha256:227ac61f18a994fef631b67f814434ffa7948f17342b00c911e7311166fba53a","target":"record","created_at":"2026-07-05T02:08:00Z","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":"135b41ee861dde7c68b561e71fd0b225871891e7d917bc0e1428b121ed17dfae","cross_cats_sorted":["cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-01-19T15:35:30Z","title_canon_sha256":"1ada033e0435055f548a74064cead67beaf8f00a54744a42613af71320d0de2a"},"schema_version":"1.0","source":{"id":"2101.07691","kind":"arxiv","version":1}},"canonical_sha256":"300e7863eb8542dcb20b762a5927440bacbc6df51e610124fa321343bec4639b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"300e7863eb8542dcb20b762a5927440bacbc6df51e610124fa321343bec4639b","first_computed_at":"2026-07-05T02:08:00.328648Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:08:00.328648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MRQgvNcVm6VP/EGkNYIX68Cy9mn/PN8feRtl35Tgfyxokg+sdArnqf/Hi8jg+/55Q9exums+P6SekcOm+8hhBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:08:00.329114Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.07691","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:227ac61f18a994fef631b67f814434ffa7948f17342b00c911e7311166fba53a","sha256:3c00e098e945d69e924a1c31975f16c314e3687c871cfd40b4d04c90e82fe221"],"state_sha256":"e141c475ec45eff69ff1aa17c48de4ec4a4b808d7062a700d393fb216b698a1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aKDYcalC1cnrXSzA3+h9ZhFGvDI+1YgqYWywoOLIxYU2vBbj5ryinmhKZ6wyDDBWT2Uhc8uOufmUKtdsYTfQCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T21:29:04.284422Z","bundle_sha256":"2405e1ba2d2960036fd5c961f6d5df29ecce752550c2aef391a1e4f27d07ce7e"}}