{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2C3HPGJEM6VGRTFQGLK5STWS6Y","short_pith_number":"pith:2C3HPGJE","schema_version":"1.0","canonical_sha256":"d0b677992467aa68ccb032d5d94ed2f6127b3dbecb926eae4c81cbee6c88a88c","source":{"kind":"arxiv","id":"1802.07740","version":2},"attestation_state":"computed","paper":{"title":"Machine Theory of Mind","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chiyuan Zhang, Frank Perbet, H. Francis Song, Matthew Botvinick, Neil C. Rabinowitz, S.M. Ali Eslami","submitted_at":"2018-02-21T19:00:10Z","abstract_excerpt":"Theory of mind (ToM; Premack & Woodruff, 1978) broadly refers to humans' ability to represent the mental states of others, including their desires, beliefs, and intentions. We propose to train a machine to build such models too. We design a Theory of Mind neural network -- a ToMnet -- which uses meta-learning to build models of the agents it encounters, from observations of their behaviour alone. Through this process, it acquires a strong prior model for agents' behaviour, as well as the ability to bootstrap to richer predictions about agents' characteristics and mental states using only a sma"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1802.07740","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-21T19:00:10Z","cross_cats_sorted":[],"title_canon_sha256":"8f6761df21d83101977116017d78c78c3ac2d995489dd17fdf30a116f77aaa53","abstract_canon_sha256":"8dadc686a4d83cf6a99376f1f25e99a86dd7b0a8573e435c7542d25fb22a14b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:19.526799Z","signature_b64":"jyMiXlURQuL7aJlEnHzEn+lG6uma4BueTNjB/XpDyhxcyntYSm8MZxbQSv8HZ8g6CJC873kKEL7QBGc3S3JHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0b677992467aa68ccb032d5d94ed2f6127b3dbecb926eae4c81cbee6c88a88c","last_reissued_at":"2026-05-18T00:21:19.523701Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:19.523701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine Theory of Mind","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chiyuan Zhang, Frank Perbet, H. Francis Song, Matthew Botvinick, Neil C. Rabinowitz, S.M. Ali Eslami","submitted_at":"2018-02-21T19:00:10Z","abstract_excerpt":"Theory of mind (ToM; Premack & Woodruff, 1978) broadly refers to humans' ability to represent the mental states of others, including their desires, beliefs, and intentions. We propose to train a machine to build such models too. We design a Theory of Mind neural network -- a ToMnet -- which uses meta-learning to build models of the agents it encounters, from observations of their behaviour alone. Through this process, it acquires a strong prior model for agents' behaviour, as well as the ability to bootstrap to richer predictions about agents' characteristics and mental states using only a sma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07740","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1802.07740","created_at":"2026-05-18T00:21:19.524372+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.07740v2","created_at":"2026-05-18T00:21:19.524372+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07740","created_at":"2026-05-18T00:21:19.524372+00:00"},{"alias_kind":"pith_short_12","alias_value":"2C3HPGJEM6VG","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"2C3HPGJEM6VGRTFQ","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"2C3HPGJE","created_at":"2026-05-18T12:31:59.375834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2001.09768","citing_title":"Artificial Intelligence, Values and Alignment","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2C3HPGJEM6VGRTFQGLK5STWS6Y","json":"https://pith.science/pith/2C3HPGJEM6VGRTFQGLK5STWS6Y.json","graph_json":"https://pith.science/api/pith-number/2C3HPGJEM6VGRTFQGLK5STWS6Y/graph.json","events_json":"https://pith.science/api/pith-number/2C3HPGJEM6VGRTFQGLK5STWS6Y/events.json","paper":"https://pith.science/paper/2C3HPGJE"},"agent_actions":{"view_html":"https://pith.science/pith/2C3HPGJEM6VGRTFQGLK5STWS6Y","download_json":"https://pith.science/pith/2C3HPGJEM6VGRTFQGLK5STWS6Y.json","view_paper":"https://pith.science/paper/2C3HPGJE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.07740&json=true","fetch_graph":"https://pith.science/api/pith-number/2C3HPGJEM6VGRTFQGLK5STWS6Y/graph.json","fetch_events":"https://pith.science/api/pith-number/2C3HPGJEM6VGRTFQGLK5STWS6Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2C3HPGJEM6VGRTFQGLK5STWS6Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2C3HPGJEM6VGRTFQGLK5STWS6Y/action/storage_attestation","attest_author":"https://pith.science/pith/2C3HPGJEM6VGRTFQGLK5STWS6Y/action/author_attestation","sign_citation":"https://pith.science/pith/2C3HPGJEM6VGRTFQGLK5STWS6Y/action/citation_signature","submit_replication":"https://pith.science/pith/2C3HPGJEM6VGRTFQGLK5STWS6Y/action/replication_record"}},"created_at":"2026-05-18T00:21:19.524372+00:00","updated_at":"2026-05-18T00:21:19.524372+00:00"}