{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:GJ6XXDFNCC3VRBSZNMJLB6URLQ","short_pith_number":"pith:GJ6XXDFN","canonical_record":{"source":{"id":"2002.04833","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T08:07:49Z","cross_cats_sorted":["cs.AI","cs.HC","cs.RO"],"title_canon_sha256":"4e38a94fa76fa90d8fbb4c8263b2f39e9f1f14ce20665b6ef6093ca56b99cb18","abstract_canon_sha256":"28a51145f64be2433e9d3c1a6d94f58bfe240745794e8dd491aedbbda691a110"},"schema_version":"1.0"},"canonical_sha256":"327d7b8cad10b75886596b12b0fa915c1ab1b9c0980499df97dceea2a1f5413c","source":{"kind":"arxiv","id":"2002.04833","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.04833","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"arxiv_version","alias_value":"2002.04833v4","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.04833","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"pith_short_12","alias_value":"GJ6XXDFNCC3V","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"pith_short_16","alias_value":"GJ6XXDFNCC3VRBSZ","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"pith_short_8","alias_value":"GJ6XXDFN","created_at":"2026-07-05T01:58:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:GJ6XXDFNCC3VRBSZNMJLB6URLQ","target":"record","payload":{"canonical_record":{"source":{"id":"2002.04833","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T08:07:49Z","cross_cats_sorted":["cs.AI","cs.HC","cs.RO"],"title_canon_sha256":"4e38a94fa76fa90d8fbb4c8263b2f39e9f1f14ce20665b6ef6093ca56b99cb18","abstract_canon_sha256":"28a51145f64be2433e9d3c1a6d94f58bfe240745794e8dd491aedbbda691a110"},"schema_version":"1.0"},"canonical_sha256":"327d7b8cad10b75886596b12b0fa915c1ab1b9c0980499df97dceea2a1f5413c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:40.191070Z","signature_b64":"GrvLlUerZu52QbT2CANzFv9ujE8n61e5BmiDypGJ2nGf2IHNMk3pFnBNhNLWtYKMClNw2YahfjQqv6hQ+kAfAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"327d7b8cad10b75886596b12b0fa915c1ab1b9c0980499df97dceea2a1f5413c","last_reissued_at":"2026-07-05T01:58:40.190576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:40.190576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.04833","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:58:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o6hVAUsICdarnEzOIyvSCyJ5gIzfjgkfur0zW6P1gf2il2/nu532lUr4qwWD3PR2HrWoAI4vl1GzG/qS1tl5Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T02:20:44.362337Z"},"content_sha256":"98fd64edbda68b736d92a5eda321c9f87bf4c670a1544f3a32304a80c3f76555","schema_version":"1.0","event_id":"sha256:98fd64edbda68b736d92a5eda321c9f87bf4c670a1544f3a32304a80c3f76555"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:GJ6XXDFNCC3VRBSZNMJLB6URLQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reward-rational (implicit) choice: A unifying formalism for reward learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.RO"],"primary_cat":"cs.LG","authors_text":"Anca D. Dragan, Hong Jun Jeon, Smitha Milli","submitted_at":"2020-02-12T08:07:49Z","abstract_excerpt":"It is often difficult to hand-specify what the correct reward function is for a task, so researchers have instead aimed to learn reward functions from human behavior or feedback. The types of behavior interpreted as evidence of the reward function have expanded greatly in recent years. We've gone from demonstrations, to comparisons, to reading into the information leaked when the human is pushing the robot away or turning it off. And surely, there is more to come. How will a robot make sense of all these diverse types of behavior? Our key insight is that different types of behavior can be inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.04833","kind":"arxiv","version":4},"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/2002.04833/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":"2026-07-05T01:58:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8NyMnN/rGx2FsLq+y+KDxLiZlHflkTMwwofz8dGybVRRGVJns3JT6uYNA1Zw9VojXf6AzD/j1cyDxIo/mYnwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T02:20:44.363173Z"},"content_sha256":"ff33c498f2e42d2b83923f1c555b6f3fb595cd398ab2b36137dc61dcfc68c9b3","schema_version":"1.0","event_id":"sha256:ff33c498f2e42d2b83923f1c555b6f3fb595cd398ab2b36137dc61dcfc68c9b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GJ6XXDFNCC3VRBSZNMJLB6URLQ/bundle.json","state_url":"https://pith.science/pith/GJ6XXDFNCC3VRBSZNMJLB6URLQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GJ6XXDFNCC3VRBSZNMJLB6URLQ/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":"2026-08-18T02:20:44Z","links":{"resolver":"https://pith.science/pith/GJ6XXDFNCC3VRBSZNMJLB6URLQ","bundle":"https://pith.science/pith/GJ6XXDFNCC3VRBSZNMJLB6URLQ/bundle.json","state":"https://pith.science/pith/GJ6XXDFNCC3VRBSZNMJLB6URLQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GJ6XXDFNCC3VRBSZNMJLB6URLQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GJ6XXDFNCC3VRBSZNMJLB6URLQ","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":"28a51145f64be2433e9d3c1a6d94f58bfe240745794e8dd491aedbbda691a110","cross_cats_sorted":["cs.AI","cs.HC","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T08:07:49Z","title_canon_sha256":"4e38a94fa76fa90d8fbb4c8263b2f39e9f1f14ce20665b6ef6093ca56b99cb18"},"schema_version":"1.0","source":{"id":"2002.04833","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.04833","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"arxiv_version","alias_value":"2002.04833v4","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.04833","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"pith_short_12","alias_value":"GJ6XXDFNCC3V","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"pith_short_16","alias_value":"GJ6XXDFNCC3VRBSZ","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"pith_short_8","alias_value":"GJ6XXDFN","created_at":"2026-07-05T01:58:40Z"}],"graph_snapshots":[{"event_id":"sha256:ff33c498f2e42d2b83923f1c555b6f3fb595cd398ab2b36137dc61dcfc68c9b3","target":"graph","created_at":"2026-07-05T01:58:40Z","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/2002.04833/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is often difficult to hand-specify what the correct reward function is for a task, so researchers have instead aimed to learn reward functions from human behavior or feedback. The types of behavior interpreted as evidence of the reward function have expanded greatly in recent years. We've gone from demonstrations, to comparisons, to reading into the information leaked when the human is pushing the robot away or turning it off. And surely, there is more to come. How will a robot make sense of all these diverse types of behavior? Our key insight is that different types of behavior can be inte","authors_text":"Anca D. Dragan, Hong Jun Jeon, Smitha Milli","cross_cats":["cs.AI","cs.HC","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T08:07:49Z","title":"Reward-rational (implicit) choice: A unifying formalism for reward learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.04833","kind":"arxiv","version":4},"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":"sha256:98fd64edbda68b736d92a5eda321c9f87bf4c670a1544f3a32304a80c3f76555","target":"record","created_at":"2026-07-05T01:58:40Z","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":"28a51145f64be2433e9d3c1a6d94f58bfe240745794e8dd491aedbbda691a110","cross_cats_sorted":["cs.AI","cs.HC","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T08:07:49Z","title_canon_sha256":"4e38a94fa76fa90d8fbb4c8263b2f39e9f1f14ce20665b6ef6093ca56b99cb18"},"schema_version":"1.0","source":{"id":"2002.04833","kind":"arxiv","version":4}},"canonical_sha256":"327d7b8cad10b75886596b12b0fa915c1ab1b9c0980499df97dceea2a1f5413c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"327d7b8cad10b75886596b12b0fa915c1ab1b9c0980499df97dceea2a1f5413c","first_computed_at":"2026-07-05T01:58:40.190576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:58:40.190576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GrvLlUerZu52QbT2CANzFv9ujE8n61e5BmiDypGJ2nGf2IHNMk3pFnBNhNLWtYKMClNw2YahfjQqv6hQ+kAfAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:58:40.191070Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.04833","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98fd64edbda68b736d92a5eda321c9f87bf4c670a1544f3a32304a80c3f76555","sha256:ff33c498f2e42d2b83923f1c555b6f3fb595cd398ab2b36137dc61dcfc68c9b3"],"state_sha256":"337c71a845dd4c586eafcd1398b4eff2358f6b9984007840016da3045bd85f55"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OiKdePvYSIYjBHFaEXJwjfLb/t/Jw1pJSZ+WduXEGcuHrpp3EQcd++jmdXWVAAIxBjmrQMhBHqWbZGrzQQpyCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T02:20:44.369649Z","bundle_sha256":"ab59919874fb27fb259f3885f8acadff5d84755174aba39f7cfad7e0b55226a7"}}