{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:EQXH5PSBEGWALIS22MOUJYNV3D","short_pith_number":"pith:EQXH5PSB","canonical_record":{"source":{"id":"2010.09054","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.MA","submitted_at":"2020-10-18T18:18:37Z","cross_cats_sorted":[],"title_canon_sha256":"af80cfee9c4078bd19d13414785d816c041a5309fa8c22b7d6278701b9dc3286","abstract_canon_sha256":"90d03fcd5023d10db163d151869e0173a47edc07914503a92d1c51f122ec9883"},"schema_version":"1.0"},"canonical_sha256":"242e7ebe4121ac05a25ad31d44e1b5d8fd1c9fcc32ef0a3dd1bb85e9496d5e33","source":{"kind":"arxiv","id":"2010.09054","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.09054","created_at":"2026-07-05T01:59:14Z"},{"alias_kind":"arxiv_version","alias_value":"2010.09054v2","created_at":"2026-07-05T01:59:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.09054","created_at":"2026-07-05T01:59:14Z"},{"alias_kind":"pith_short_12","alias_value":"EQXH5PSBEGWA","created_at":"2026-07-05T01:59:14Z"},{"alias_kind":"pith_short_16","alias_value":"EQXH5PSBEGWALIS2","created_at":"2026-07-05T01:59:14Z"},{"alias_kind":"pith_short_8","alias_value":"EQXH5PSB","created_at":"2026-07-05T01:59:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:EQXH5PSBEGWALIS22MOUJYNV3D","target":"record","payload":{"canonical_record":{"source":{"id":"2010.09054","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.MA","submitted_at":"2020-10-18T18:18:37Z","cross_cats_sorted":[],"title_canon_sha256":"af80cfee9c4078bd19d13414785d816c041a5309fa8c22b7d6278701b9dc3286","abstract_canon_sha256":"90d03fcd5023d10db163d151869e0173a47edc07914503a92d1c51f122ec9883"},"schema_version":"1.0"},"canonical_sha256":"242e7ebe4121ac05a25ad31d44e1b5d8fd1c9fcc32ef0a3dd1bb85e9496d5e33","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:59:14.991172Z","signature_b64":"zl2gA5va0bbyKIB6ZBpZShf4PrpgwzZ/qrhTmF+bMggS1OrhgRhcaszo0l3WjffkbozgLsCDtulIgwRPVAk5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"242e7ebe4121ac05a25ad31d44e1b5d8fd1c9fcc32ef0a3dd1bb85e9496d5e33","last_reissued_at":"2026-07-05T01:59:14.990751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:59:14.990751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.09054","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:59:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pNZRpKPGFJ/jFlyDhf17kIfHsKimXywP1B2G4zorCmenYm6Sk9aJyDUY256pDY6468ZKwgRo6d+VHbewi8CkDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:09:31.953525Z"},"content_sha256":"93e47ef99f88220fb2029d99aa4a795eb62210af23c3d3a592026efcd8851c80","schema_version":"1.0","event_id":"sha256:93e47ef99f88220fb2029d99aa4a795eb62210af23c3d3a592026efcd8851c80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:EQXH5PSBEGWALIS22MOUJYNV3D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-free conventions in multi-agent reinforcement learning with heterogeneous preferences","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Edgar A. Du\\'e\\~nez-Guzm\\'an, Edward Hughes, Joel Z. Leibo, Kevin R. McKee, Laura Weidinger, Matthew Botvinick, Raphael K\\\"oster, Richard Everett, Thore Graepel, William S. Isaac","submitted_at":"2020-10-18T18:18:37Z","abstract_excerpt":"Game theoretic views of convention generally rest on notions of common knowledge and hyper-rational models of individual behavior. However, decades of work in behavioral economics have questioned the validity of both foundations. Meanwhile, computational neuroscience has contributed a modernized 'dual process' account of decision-making where model-free (MF) reinforcement learning trades off with model-based (MB) reinforcement learning. The former captures habitual and procedural learning while the latter captures choices taken via explicit planning and deduction. Some conventions (e.g. intern"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.09054","kind":"arxiv","version":2},"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/2010.09054/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":"2026-07-05T01:59:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"45xgzXToUEYJp3r/uoOIt2dls/cRfJAUKo9dWHqLJXtjHdOFKuy5pwfF04Pu/O0wT8uE54S6hGg3WZgDtTxHCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:09:31.954208Z"},"content_sha256":"f4e114d9d736846be0631f83cd6e29b8b574caaaa2f87b8e9e23bd09341c2b68","schema_version":"1.0","event_id":"sha256:f4e114d9d736846be0631f83cd6e29b8b574caaaa2f87b8e9e23bd09341c2b68"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EQXH5PSBEGWALIS22MOUJYNV3D/bundle.json","state_url":"https://pith.science/pith/EQXH5PSBEGWALIS22MOUJYNV3D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EQXH5PSBEGWALIS22MOUJYNV3D/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":"2026-08-03T17:09:31Z","links":{"resolver":"https://pith.science/pith/EQXH5PSBEGWALIS22MOUJYNV3D","bundle":"https://pith.science/pith/EQXH5PSBEGWALIS22MOUJYNV3D/bundle.json","state":"https://pith.science/pith/EQXH5PSBEGWALIS22MOUJYNV3D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EQXH5PSBEGWALIS22MOUJYNV3D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:EQXH5PSBEGWALIS22MOUJYNV3D","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":"90d03fcd5023d10db163d151869e0173a47edc07914503a92d1c51f122ec9883","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.MA","submitted_at":"2020-10-18T18:18:37Z","title_canon_sha256":"af80cfee9c4078bd19d13414785d816c041a5309fa8c22b7d6278701b9dc3286"},"schema_version":"1.0","source":{"id":"2010.09054","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.09054","created_at":"2026-07-05T01:59:14Z"},{"alias_kind":"arxiv_version","alias_value":"2010.09054v2","created_at":"2026-07-05T01:59:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.09054","created_at":"2026-07-05T01:59:14Z"},{"alias_kind":"pith_short_12","alias_value":"EQXH5PSBEGWA","created_at":"2026-07-05T01:59:14Z"},{"alias_kind":"pith_short_16","alias_value":"EQXH5PSBEGWALIS2","created_at":"2026-07-05T01:59:14Z"},{"alias_kind":"pith_short_8","alias_value":"EQXH5PSB","created_at":"2026-07-05T01:59:14Z"}],"graph_snapshots":[{"event_id":"sha256:f4e114d9d736846be0631f83cd6e29b8b574caaaa2f87b8e9e23bd09341c2b68","target":"graph","created_at":"2026-07-05T01:59:14Z","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/2010.09054/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Game theoretic views of convention generally rest on notions of common knowledge and hyper-rational models of individual behavior. However, decades of work in behavioral economics have questioned the validity of both foundations. Meanwhile, computational neuroscience has contributed a modernized 'dual process' account of decision-making where model-free (MF) reinforcement learning trades off with model-based (MB) reinforcement learning. The former captures habitual and procedural learning while the latter captures choices taken via explicit planning and deduction. Some conventions (e.g. intern","authors_text":"Edgar A. Du\\'e\\~nez-Guzm\\'an, Edward Hughes, Joel Z. Leibo, Kevin R. McKee, Laura Weidinger, Matthew Botvinick, Raphael K\\\"oster, Richard Everett, Thore Graepel, William S. Isaac","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.MA","submitted_at":"2020-10-18T18:18:37Z","title":"Model-free conventions in multi-agent reinforcement learning with heterogeneous preferences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.09054","kind":"arxiv","version":2},"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":"sha256:93e47ef99f88220fb2029d99aa4a795eb62210af23c3d3a592026efcd8851c80","target":"record","created_at":"2026-07-05T01:59:14Z","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":"90d03fcd5023d10db163d151869e0173a47edc07914503a92d1c51f122ec9883","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.MA","submitted_at":"2020-10-18T18:18:37Z","title_canon_sha256":"af80cfee9c4078bd19d13414785d816c041a5309fa8c22b7d6278701b9dc3286"},"schema_version":"1.0","source":{"id":"2010.09054","kind":"arxiv","version":2}},"canonical_sha256":"242e7ebe4121ac05a25ad31d44e1b5d8fd1c9fcc32ef0a3dd1bb85e9496d5e33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"242e7ebe4121ac05a25ad31d44e1b5d8fd1c9fcc32ef0a3dd1bb85e9496d5e33","first_computed_at":"2026-07-05T01:59:14.990751Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:59:14.990751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zl2gA5va0bbyKIB6ZBpZShf4PrpgwzZ/qrhTmF+bMggS1OrhgRhcaszo0l3WjffkbozgLsCDtulIgwRPVAk5AA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:59:14.991172Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.09054","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93e47ef99f88220fb2029d99aa4a795eb62210af23c3d3a592026efcd8851c80","sha256:f4e114d9d736846be0631f83cd6e29b8b574caaaa2f87b8e9e23bd09341c2b68"],"state_sha256":"0ee7732e55d14f13ed7fa530d1deb777e66c6c06b34ca9aceee2ba4671430a2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sqNHZadytqZ+MV6qgaCJ/pLLm4QvmURb6nwxQGKGH/hDjhghGAYb5K4DzCDson/i39EbZ3LAETLJsxCnbLyJCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:09:31.959625Z","bundle_sha256":"c23c061aed659c9b068d8021790e913953d7ec316cbcd2f74e9bf7d4a02929b4"}}