{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:YRTEFE4QUDW7VZBVGLEMT75UOV","short_pith_number":"pith:YRTEFE4Q","canonical_record":{"source":{"id":"1606.03137","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-06-09T22:39:54Z","cross_cats_sorted":[],"title_canon_sha256":"a693c21211efef1dcf3c342e5b329007148c44be2880eb4cba458ade74f4d569","abstract_canon_sha256":"7a2e5d362748ebc84cc347ee01d9d5e1e3fdc5757746269e493df63451315610"},"schema_version":"1.0"},"canonical_sha256":"c466429390a0edfae43532c8c9ffb475702ffe9858c6731e8d3660453ed40f96","source":{"kind":"arxiv","id":"1606.03137","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.03137","created_at":"2026-07-05T07:46:08Z"},{"alias_kind":"arxiv_version","alias_value":"1606.03137v4","created_at":"2026-07-05T07:46:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.03137","created_at":"2026-07-05T07:46:08Z"},{"alias_kind":"pith_short_12","alias_value":"YRTEFE4QUDW7","created_at":"2026-07-05T07:46:08Z"},{"alias_kind":"pith_short_16","alias_value":"YRTEFE4QUDW7VZBV","created_at":"2026-07-05T07:46:08Z"},{"alias_kind":"pith_short_8","alias_value":"YRTEFE4Q","created_at":"2026-07-05T07:46:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:YRTEFE4QUDW7VZBVGLEMT75UOV","target":"record","payload":{"canonical_record":{"source":{"id":"1606.03137","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-06-09T22:39:54Z","cross_cats_sorted":[],"title_canon_sha256":"a693c21211efef1dcf3c342e5b329007148c44be2880eb4cba458ade74f4d569","abstract_canon_sha256":"7a2e5d362748ebc84cc347ee01d9d5e1e3fdc5757746269e493df63451315610"},"schema_version":"1.0"},"canonical_sha256":"c466429390a0edfae43532c8c9ffb475702ffe9858c6731e8d3660453ed40f96","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:08.402962Z","signature_b64":"1CkacsUtJZIC/+wJhHVWpgWwZ1qG0Ci+9ObznAFjj/SFp3uCbWu0t2wn0JPcDQXSH3Ter0xEUETwgNRPMzKqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c466429390a0edfae43532c8c9ffb475702ffe9858c6731e8d3660453ed40f96","last_reissued_at":"2026-07-05T07:46:08.402590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:08.402590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.03137","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":"2026-07-05T07:46:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oXz7dfj9iPYpT45vEhNhwa9rQtvK4EptxOHEBWjktIX0J4iRWVDckh90etWySjP+OBQXKA3Yp1wvPLWnYOHQCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:40:51.813624Z"},"content_sha256":"abd2a994d2e724830494d09168c9a4fad6d9dbfd8e033ed4cda560d52b5c927f","schema_version":"1.0","event_id":"sha256:abd2a994d2e724830494d09168c9a4fad6d9dbfd8e033ed4cda560d52b5c927f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:YRTEFE4QUDW7VZBVGLEMT75UOV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cooperative Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anca Dragan, Dylan Hadfield-Menell, Pieter Abbeel, Stuart Russell","submitted_at":"2016-06-09T22:39:54Z","abstract_excerpt":"For an autonomous system to be helpful to humans and to pose no unwarranted risks, it needs to align its values with those of the humans in its environment in such a way that its actions contribute to the maximization of value for the humans. We propose a formal definition of the value alignment problem as cooperative inverse reinforcement learning (CIRL). A CIRL problem is a cooperative, partial-information game with two agents, human and robot; both are rewarded according to the human's reward function, but the robot does not initially know what this is. In contrast to classical IRL, where t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.03137","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/1606.03137/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":"2026-07-05T07:46:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Eg2AM6u3LJQUsLqmbLFWb7dNgV15gdI+54jGpVnnog11XzawGD/CBNNyBQaYtdpuwoqSnUIkjbKJW3ivvwtoAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:40:51.814212Z"},"content_sha256":"0198a39efcabefa77eb05237c4dbb583493ae4b4216204473a5a29ebedb1bee9","schema_version":"1.0","event_id":"sha256:0198a39efcabefa77eb05237c4dbb583493ae4b4216204473a5a29ebedb1bee9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YRTEFE4QUDW7VZBVGLEMT75UOV/bundle.json","state_url":"https://pith.science/pith/YRTEFE4QUDW7VZBVGLEMT75UOV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YRTEFE4QUDW7VZBVGLEMT75UOV/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":"2026-08-06T04:40:51Z","links":{"resolver":"https://pith.science/pith/YRTEFE4QUDW7VZBVGLEMT75UOV","bundle":"https://pith.science/pith/YRTEFE4QUDW7VZBVGLEMT75UOV/bundle.json","state":"https://pith.science/pith/YRTEFE4QUDW7VZBVGLEMT75UOV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YRTEFE4QUDW7VZBVGLEMT75UOV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:YRTEFE4QUDW7VZBVGLEMT75UOV","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":"7a2e5d362748ebc84cc347ee01d9d5e1e3fdc5757746269e493df63451315610","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-06-09T22:39:54Z","title_canon_sha256":"a693c21211efef1dcf3c342e5b329007148c44be2880eb4cba458ade74f4d569"},"schema_version":"1.0","source":{"id":"1606.03137","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.03137","created_at":"2026-07-05T07:46:08Z"},{"alias_kind":"arxiv_version","alias_value":"1606.03137v4","created_at":"2026-07-05T07:46:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.03137","created_at":"2026-07-05T07:46:08Z"},{"alias_kind":"pith_short_12","alias_value":"YRTEFE4QUDW7","created_at":"2026-07-05T07:46:08Z"},{"alias_kind":"pith_short_16","alias_value":"YRTEFE4QUDW7VZBV","created_at":"2026-07-05T07:46:08Z"},{"alias_kind":"pith_short_8","alias_value":"YRTEFE4Q","created_at":"2026-07-05T07:46:08Z"}],"graph_snapshots":[{"event_id":"sha256:0198a39efcabefa77eb05237c4dbb583493ae4b4216204473a5a29ebedb1bee9","target":"graph","created_at":"2026-07-05T07:46:08Z","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/1606.03137/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For an autonomous system to be helpful to humans and to pose no unwarranted risks, it needs to align its values with those of the humans in its environment in such a way that its actions contribute to the maximization of value for the humans. We propose a formal definition of the value alignment problem as cooperative inverse reinforcement learning (CIRL). A CIRL problem is a cooperative, partial-information game with two agents, human and robot; both are rewarded according to the human's reward function, but the robot does not initially know what this is. In contrast to classical IRL, where t","authors_text":"Anca Dragan, Dylan Hadfield-Menell, Pieter Abbeel, Stuart Russell","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-06-09T22:39:54Z","title":"Cooperative Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.03137","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:abd2a994d2e724830494d09168c9a4fad6d9dbfd8e033ed4cda560d52b5c927f","target":"record","created_at":"2026-07-05T07:46:08Z","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":"7a2e5d362748ebc84cc347ee01d9d5e1e3fdc5757746269e493df63451315610","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-06-09T22:39:54Z","title_canon_sha256":"a693c21211efef1dcf3c342e5b329007148c44be2880eb4cba458ade74f4d569"},"schema_version":"1.0","source":{"id":"1606.03137","kind":"arxiv","version":4}},"canonical_sha256":"c466429390a0edfae43532c8c9ffb475702ffe9858c6731e8d3660453ed40f96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c466429390a0edfae43532c8c9ffb475702ffe9858c6731e8d3660453ed40f96","first_computed_at":"2026-07-05T07:46:08.402590Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:08.402590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1CkacsUtJZIC/+wJhHVWpgWwZ1qG0Ci+9ObznAFjj/SFp3uCbWu0t2wn0JPcDQXSH3Ter0xEUETwgNRPMzKqAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:08.402962Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.03137","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:abd2a994d2e724830494d09168c9a4fad6d9dbfd8e033ed4cda560d52b5c927f","sha256:0198a39efcabefa77eb05237c4dbb583493ae4b4216204473a5a29ebedb1bee9"],"state_sha256":"bbe2e29b2ca74a03501bf19e8a758a26ee08e1c53e92e4a3a30e8d22a40fd12a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rSbXqh5P0ldhF3qtTNyYhBYr03riEeN/qMAIZb+BSE1eThgcZgKe+EpOGWEQsPOx7D6LEvt+mAKwJ5ZiQzFPBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:40:51.818768Z","bundle_sha256":"154e0873ec0dc47bc355ce0d0ac1070413721ae95a09f4e311286d9de0873301"}}