{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RTW3RL4ODY7LO4KHPWVPZN3ZXN","short_pith_number":"pith:RTW3RL4O","canonical_record":{"source":{"id":"2204.01160","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-04-03T21:00:51Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"4f586dd2f327866e87a328d6908e6304ac31c67f6678013abe3cb63d8b5c9220","abstract_canon_sha256":"6bb3912263a29e56f27a7b3186af9c60f4f3ae7c78570078f5ef70dd63d3108b"},"schema_version":"1.0"},"canonical_sha256":"8cedb8af8e1e3eb771477daafcb779bb59ad9ee2385298ac64852ed80fd7e102","source":{"kind":"arxiv","id":"2204.01160","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.01160","created_at":"2026-07-05T04:11:15Z"},{"alias_kind":"arxiv_version","alias_value":"2204.01160v1","created_at":"2026-07-05T04:11:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.01160","created_at":"2026-07-05T04:11:15Z"},{"alias_kind":"pith_short_12","alias_value":"RTW3RL4ODY7L","created_at":"2026-07-05T04:11:15Z"},{"alias_kind":"pith_short_16","alias_value":"RTW3RL4ODY7LO4KH","created_at":"2026-07-05T04:11:15Z"},{"alias_kind":"pith_short_8","alias_value":"RTW3RL4O","created_at":"2026-07-05T04:11:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RTW3RL4ODY7LO4KHPWVPZN3ZXN","target":"record","payload":{"canonical_record":{"source":{"id":"2204.01160","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-04-03T21:00:51Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"4f586dd2f327866e87a328d6908e6304ac31c67f6678013abe3cb63d8b5c9220","abstract_canon_sha256":"6bb3912263a29e56f27a7b3186af9c60f4f3ae7c78570078f5ef70dd63d3108b"},"schema_version":"1.0"},"canonical_sha256":"8cedb8af8e1e3eb771477daafcb779bb59ad9ee2385298ac64852ed80fd7e102","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:15.988471Z","signature_b64":"G/wWa9WcxVDpRDannpskeMytuTY823iqT16AHUfLgMIIsj2xUb8Dq8V6304Bmch4m41xFVsV9PLKjrS4G8wuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cedb8af8e1e3eb771477daafcb779bb59ad9ee2385298ac64852ed80fd7e102","last_reissued_at":"2026-07-05T04:11:15.988056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:15.988056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.01160","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":"2026-07-05T04:11:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2WRe+0acran1dceeQ5jZkJVQ6WmSdiruXwMORAuVD1DNa5nFEAYXcWfPXcyLrmQR4bOcMgi/aN5gKvxjagWlAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T16:42:22.248350Z"},"content_sha256":"c86cd7c3d014287216154f19c24631d2d7ab1dc3d81c9b288efbb0bd43548616","schema_version":"1.0","event_id":"sha256:c86cd7c3d014287216154f19c24631d2d7ab1dc3d81c9b288efbb0bd43548616"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RTW3RL4ODY7LO4KHPWVPZN3ZXN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Best-Response Bayesian Reinforcement Learning with Bayes-adaptive POMDPs for Centaurs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Frans A. Oliehoek, Mustafa Mert \\c{C}elikok, Samuel Kaski","submitted_at":"2022-04-03T21:00:51Z","abstract_excerpt":"Centaurs are half-human, half-AI decision-makers where the AI's goal is to complement the human. To do so, the AI must be able to recognize the goals and constraints of the human and have the means to help them. We present a novel formulation of the interaction between the human and the AI as a sequential game where the agents are modelled using Bayesian best-response models. We show that in this case the AI's problem of helping bounded-rational humans make better decisions reduces to a Bayes-adaptive POMDP. In our simulated experiments, we consider an instantiation of our framework for humans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.01160","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/2204.01160/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":"2026-07-05T04:11:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ALDUSg5riWz1nsw0lmYzIX3JqivKttDND0+PMlJn3QqWnQvhqMuYYWF5UbYuomwTiFiErhFmoPcsftTDMiqfCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T16:42:22.248747Z"},"content_sha256":"2795cc49efd1e9baeb77704921c833ee6c1a46b03dc93ddf14ce7446e07526f4","schema_version":"1.0","event_id":"sha256:2795cc49efd1e9baeb77704921c833ee6c1a46b03dc93ddf14ce7446e07526f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RTW3RL4ODY7LO4KHPWVPZN3ZXN/bundle.json","state_url":"https://pith.science/pith/RTW3RL4ODY7LO4KHPWVPZN3ZXN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RTW3RL4ODY7LO4KHPWVPZN3ZXN/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":"2026-07-28T16:42:22Z","links":{"resolver":"https://pith.science/pith/RTW3RL4ODY7LO4KHPWVPZN3ZXN","bundle":"https://pith.science/pith/RTW3RL4ODY7LO4KHPWVPZN3ZXN/bundle.json","state":"https://pith.science/pith/RTW3RL4ODY7LO4KHPWVPZN3ZXN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RTW3RL4ODY7LO4KHPWVPZN3ZXN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RTW3RL4ODY7LO4KHPWVPZN3ZXN","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":"6bb3912263a29e56f27a7b3186af9c60f4f3ae7c78570078f5ef70dd63d3108b","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-04-03T21:00:51Z","title_canon_sha256":"4f586dd2f327866e87a328d6908e6304ac31c67f6678013abe3cb63d8b5c9220"},"schema_version":"1.0","source":{"id":"2204.01160","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.01160","created_at":"2026-07-05T04:11:15Z"},{"alias_kind":"arxiv_version","alias_value":"2204.01160v1","created_at":"2026-07-05T04:11:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.01160","created_at":"2026-07-05T04:11:15Z"},{"alias_kind":"pith_short_12","alias_value":"RTW3RL4ODY7L","created_at":"2026-07-05T04:11:15Z"},{"alias_kind":"pith_short_16","alias_value":"RTW3RL4ODY7LO4KH","created_at":"2026-07-05T04:11:15Z"},{"alias_kind":"pith_short_8","alias_value":"RTW3RL4O","created_at":"2026-07-05T04:11:15Z"}],"graph_snapshots":[{"event_id":"sha256:2795cc49efd1e9baeb77704921c833ee6c1a46b03dc93ddf14ce7446e07526f4","target":"graph","created_at":"2026-07-05T04:11:15Z","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/2204.01160/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Centaurs are half-human, half-AI decision-makers where the AI's goal is to complement the human. To do so, the AI must be able to recognize the goals and constraints of the human and have the means to help them. We present a novel formulation of the interaction between the human and the AI as a sequential game where the agents are modelled using Bayesian best-response models. We show that in this case the AI's problem of helping bounded-rational humans make better decisions reduces to a Bayes-adaptive POMDP. In our simulated experiments, we consider an instantiation of our framework for humans","authors_text":"Frans A. Oliehoek, Mustafa Mert \\c{C}elikok, Samuel Kaski","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-04-03T21:00:51Z","title":"Best-Response Bayesian Reinforcement Learning with Bayes-adaptive POMDPs for Centaurs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.01160","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:c86cd7c3d014287216154f19c24631d2d7ab1dc3d81c9b288efbb0bd43548616","target":"record","created_at":"2026-07-05T04:11:15Z","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":"6bb3912263a29e56f27a7b3186af9c60f4f3ae7c78570078f5ef70dd63d3108b","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-04-03T21:00:51Z","title_canon_sha256":"4f586dd2f327866e87a328d6908e6304ac31c67f6678013abe3cb63d8b5c9220"},"schema_version":"1.0","source":{"id":"2204.01160","kind":"arxiv","version":1}},"canonical_sha256":"8cedb8af8e1e3eb771477daafcb779bb59ad9ee2385298ac64852ed80fd7e102","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8cedb8af8e1e3eb771477daafcb779bb59ad9ee2385298ac64852ed80fd7e102","first_computed_at":"2026-07-05T04:11:15.988056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:11:15.988056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G/wWa9WcxVDpRDannpskeMytuTY823iqT16AHUfLgMIIsj2xUb8Dq8V6304Bmch4m41xFVsV9PLKjrS4G8wuAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:11:15.988471Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.01160","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c86cd7c3d014287216154f19c24631d2d7ab1dc3d81c9b288efbb0bd43548616","sha256:2795cc49efd1e9baeb77704921c833ee6c1a46b03dc93ddf14ce7446e07526f4"],"state_sha256":"9ac04512bfe6326ec293a805649e521ead47b0d1fe3d4ab944b66ee2a015c266"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NSyovibr3VuGAvfuXifBlvawj7r1LU7XlErp24bDPa36+DZNvGW/KsQjc7/GmM4aDO2aVxSv2Et1ylhoAoQ+DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-28T16:42:22.251348Z","bundle_sha256":"f78252b6ef2f39f662a812d9fd2b87efaf32fb6618bd62932fbaf46a7979e293"}}