{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IE6HRWERGERVRKCESIAMXD32K4","short_pith_number":"pith:IE6HRWER","canonical_record":{"source":{"id":"2307.01158","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-03T17:07:18Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"d3260d04673c3a6b6dfb8a884d1fe7a71590268fad26bb9021eb2ce974013d56","abstract_canon_sha256":"6ad2d67bf56634c07dd3f62982c9ce0a0275654df33647039d363731547ee684"},"schema_version":"1.0"},"canonical_sha256":"413c78d891312358a8449200cb8f7a572a3673fcce079334a6f651b520271bce","source":{"kind":"arxiv","id":"2307.01158","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.01158","created_at":"2026-07-05T06:32:40Z"},{"alias_kind":"arxiv_version","alias_value":"2307.01158v2","created_at":"2026-07-05T06:32:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01158","created_at":"2026-07-05T06:32:40Z"},{"alias_kind":"pith_short_12","alias_value":"IE6HRWERGERV","created_at":"2026-07-05T06:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"IE6HRWERGERVRKCE","created_at":"2026-07-05T06:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"IE6HRWER","created_at":"2026-07-05T06:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IE6HRWERGERVRKCESIAMXD32K4","target":"record","payload":{"canonical_record":{"source":{"id":"2307.01158","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-03T17:07:18Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"d3260d04673c3a6b6dfb8a884d1fe7a71590268fad26bb9021eb2ce974013d56","abstract_canon_sha256":"6ad2d67bf56634c07dd3f62982c9ce0a0275654df33647039d363731547ee684"},"schema_version":"1.0"},"canonical_sha256":"413c78d891312358a8449200cb8f7a572a3673fcce079334a6f651b520271bce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:32:40.011031Z","signature_b64":"GSUMAOgTaeZ09nxRvwbGNIUKQIfsCESq5WlFiigSt9hB0/8CFp/toEEeEeam8GoGJreAfeQr7cksQhUDO5sGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"413c78d891312358a8449200cb8f7a572a3673fcce079334a6f651b520271bce","last_reissued_at":"2026-07-05T06:32:40.010491Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:32:40.010491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.01158","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":"2026-07-05T06:32:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wrrE4Sk5ZTIYPRXevDDQkUbVkwglCLVIIRyuemMfWKluyI1EsVkPdxgclsE9Vc4klMT/Z4IMumNGkKuNoy/+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:23:31.013176Z"},"content_sha256":"fb451cf840c9c80bc18b1c5371dc80d9eecd62511543b95b50f15df0fe6c831a","schema_version":"1.0","event_id":"sha256:fb451cf840c9c80bc18b1c5371dc80d9eecd62511543b95b50f15df0fe6c831a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IE6HRWERGERVRKCESIAMXD32K4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Theory of Mind as Intrinsic Motivation for Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Ini Oguntola, Joseph Campbell, Katia Sycara, Simon Stepputtis","submitted_at":"2023-07-03T17:07:18Z","abstract_excerpt":"The ability to model the mental states of others is crucial to human social intelligence, and can offer similar benefits to artificial agents with respect to the social dynamics induced in multi-agent settings. We present a method of grounding semantically meaningful, human-interpretable beliefs within policies modeled by deep networks. We then consider the task of 2nd-order belief prediction. We propose that ability of each agent to predict the beliefs of the other agents can be used as an intrinsic reward signal for multi-agent reinforcement learning. Finally, we present preliminary empirica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01158","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/2307.01158/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":"2026-07-05T06:32:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dwj/BmTVBsV2LVtD02j9UNb5bvBD4NgT1ITiLCvDqJp9OLw6HN8V9EgxTzkGv6V9/iSi23hh/AUAL+fGrtzzCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:23:31.014083Z"},"content_sha256":"138d10b5668d4945c3d964247f33a4dd3183e39ef7179ec7f2e80a9f29164891","schema_version":"1.0","event_id":"sha256:138d10b5668d4945c3d964247f33a4dd3183e39ef7179ec7f2e80a9f29164891"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IE6HRWERGERVRKCESIAMXD32K4/bundle.json","state_url":"https://pith.science/pith/IE6HRWERGERVRKCESIAMXD32K4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IE6HRWERGERVRKCESIAMXD32K4/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":"2026-08-08T08:23:31Z","links":{"resolver":"https://pith.science/pith/IE6HRWERGERVRKCESIAMXD32K4","bundle":"https://pith.science/pith/IE6HRWERGERVRKCESIAMXD32K4/bundle.json","state":"https://pith.science/pith/IE6HRWERGERVRKCESIAMXD32K4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IE6HRWERGERVRKCESIAMXD32K4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IE6HRWERGERVRKCESIAMXD32K4","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":"6ad2d67bf56634c07dd3f62982c9ce0a0275654df33647039d363731547ee684","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-03T17:07:18Z","title_canon_sha256":"d3260d04673c3a6b6dfb8a884d1fe7a71590268fad26bb9021eb2ce974013d56"},"schema_version":"1.0","source":{"id":"2307.01158","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.01158","created_at":"2026-07-05T06:32:40Z"},{"alias_kind":"arxiv_version","alias_value":"2307.01158v2","created_at":"2026-07-05T06:32:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01158","created_at":"2026-07-05T06:32:40Z"},{"alias_kind":"pith_short_12","alias_value":"IE6HRWERGERV","created_at":"2026-07-05T06:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"IE6HRWERGERVRKCE","created_at":"2026-07-05T06:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"IE6HRWER","created_at":"2026-07-05T06:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:138d10b5668d4945c3d964247f33a4dd3183e39ef7179ec7f2e80a9f29164891","target":"graph","created_at":"2026-07-05T06:32:40Z","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/2307.01158/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability to model the mental states of others is crucial to human social intelligence, and can offer similar benefits to artificial agents with respect to the social dynamics induced in multi-agent settings. We present a method of grounding semantically meaningful, human-interpretable beliefs within policies modeled by deep networks. We then consider the task of 2nd-order belief prediction. We propose that ability of each agent to predict the beliefs of the other agents can be used as an intrinsic reward signal for multi-agent reinforcement learning. Finally, we present preliminary empirica","authors_text":"Ini Oguntola, Joseph Campbell, Katia Sycara, Simon Stepputtis","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-03T17:07:18Z","title":"Theory of Mind as Intrinsic Motivation for Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01158","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:fb451cf840c9c80bc18b1c5371dc80d9eecd62511543b95b50f15df0fe6c831a","target":"record","created_at":"2026-07-05T06:32:40Z","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":"6ad2d67bf56634c07dd3f62982c9ce0a0275654df33647039d363731547ee684","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-03T17:07:18Z","title_canon_sha256":"d3260d04673c3a6b6dfb8a884d1fe7a71590268fad26bb9021eb2ce974013d56"},"schema_version":"1.0","source":{"id":"2307.01158","kind":"arxiv","version":2}},"canonical_sha256":"413c78d891312358a8449200cb8f7a572a3673fcce079334a6f651b520271bce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"413c78d891312358a8449200cb8f7a572a3673fcce079334a6f651b520271bce","first_computed_at":"2026-07-05T06:32:40.010491Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:32:40.010491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GSUMAOgTaeZ09nxRvwbGNIUKQIfsCESq5WlFiigSt9hB0/8CFp/toEEeEeam8GoGJreAfeQr7cksQhUDO5sGDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:32:40.011031Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.01158","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb451cf840c9c80bc18b1c5371dc80d9eecd62511543b95b50f15df0fe6c831a","sha256:138d10b5668d4945c3d964247f33a4dd3183e39ef7179ec7f2e80a9f29164891"],"state_sha256":"a581ad712c2b16be27f43d75870ccf824120945424d036c8cd59112a0874a76a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W2wxLDCyX8/9VKGVuSCkur7r9vOuyThkoWbJjZ16I6GlPC7U3jEQrEEg/SJpgj0o+WP1LhxXpJarRdrKRSOBAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:23:31.021045Z","bundle_sha256":"7a3bbf47e178badffadf7b6fc295f2f2f2b172a82c1c7e7b9f134b889864cc94"}}