{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5DQSFZI46EO5GOKDG32OB2TDBQ","short_pith_number":"pith:5DQSFZI4","schema_version":"1.0","canonical_sha256":"e8e122e51cf11dd3394336f4e0ea630c1773f46a8dcae3374d1be3a7170de77d","source":{"kind":"arxiv","id":"2402.01203","version":2},"attestation_state":"computed","paper":{"title":"Neural Language of Thought Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Minseung Lee, Sungjin Ahn, Yi-Fu Wu","submitted_at":"2024-02-02T08:13:18Z","abstract_excerpt":"The Language of Thought Hypothesis suggests that human cognition operates on a structured, language-like system of mental representations. While neural language models can naturally benefit from the compositional structure inherently and explicitly expressed in language data, learning such representations from non-linguistic general observations, like images, remains a challenge. In this work, we introduce the Neural Language of Thought Model (NLoTM), a novel approach for unsupervised learning of LoTH-inspired representation and generation. NLoTM comprises two key components: (1) the Semantic "},"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":"2402.01203","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T08:13:18Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3f234c0c4da1a918db72919e002a32eb19bdf6c098e2e8015fc3a834d81b4974","abstract_canon_sha256":"0a666d844a796519d529d389aee568c2ea5b214a1104bddff9e9858663a12ec9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:54.537011Z","signature_b64":"ucyiZb83/tGBoR5dXOaHDye26v5pfKdmlkvNShbg26f3m+agwOTcMBe/c2OeQf4S+DovVhC897qXbDMEXcJpBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8e122e51cf11dd3394336f4e0ea630c1773f46a8dcae3374d1be3a7170de77d","last_reissued_at":"2026-07-05T08:08:54.536511Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:54.536511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Language of Thought Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Minseung Lee, Sungjin Ahn, Yi-Fu Wu","submitted_at":"2024-02-02T08:13:18Z","abstract_excerpt":"The Language of Thought Hypothesis suggests that human cognition operates on a structured, language-like system of mental representations. While neural language models can naturally benefit from the compositional structure inherently and explicitly expressed in language data, learning such representations from non-linguistic general observations, like images, remains a challenge. In this work, we introduce the Neural Language of Thought Model (NLoTM), a novel approach for unsupervised learning of LoTH-inspired representation and generation. NLoTM comprises two key components: (1) the Semantic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01203","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/2402.01203/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.01203","created_at":"2026-07-05T08:08:54.536566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01203v2","created_at":"2026-07-05T08:08:54.536566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01203","created_at":"2026-07-05T08:08:54.536566+00:00"},{"alias_kind":"pith_short_12","alias_value":"5DQSFZI46EO5","created_at":"2026-07-05T08:08:54.536566+00:00"},{"alias_kind":"pith_short_16","alias_value":"5DQSFZI46EO5GOKD","created_at":"2026-07-05T08:08:54.536566+00:00"},{"alias_kind":"pith_short_8","alias_value":"5DQSFZI4","created_at":"2026-07-05T08:08:54.536566+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30942","citing_title":"PRISM: Progressive Reasoning through Iterative Slot Memory for Vision","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5DQSFZI46EO5GOKDG32OB2TDBQ","json":"https://pith.science/pith/5DQSFZI46EO5GOKDG32OB2TDBQ.json","graph_json":"https://pith.science/api/pith-number/5DQSFZI46EO5GOKDG32OB2TDBQ/graph.json","events_json":"https://pith.science/api/pith-number/5DQSFZI46EO5GOKDG32OB2TDBQ/events.json","paper":"https://pith.science/paper/5DQSFZI4"},"agent_actions":{"view_html":"https://pith.science/pith/5DQSFZI46EO5GOKDG32OB2TDBQ","download_json":"https://pith.science/pith/5DQSFZI46EO5GOKDG32OB2TDBQ.json","view_paper":"https://pith.science/paper/5DQSFZI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01203&json=true","fetch_graph":"https://pith.science/api/pith-number/5DQSFZI46EO5GOKDG32OB2TDBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/5DQSFZI46EO5GOKDG32OB2TDBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5DQSFZI46EO5GOKDG32OB2TDBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5DQSFZI46EO5GOKDG32OB2TDBQ/action/storage_attestation","attest_author":"https://pith.science/pith/5DQSFZI46EO5GOKDG32OB2TDBQ/action/author_attestation","sign_citation":"https://pith.science/pith/5DQSFZI46EO5GOKDG32OB2TDBQ/action/citation_signature","submit_replication":"https://pith.science/pith/5DQSFZI46EO5GOKDG32OB2TDBQ/action/replication_record"}},"created_at":"2026-07-05T08:08:54.536566+00:00","updated_at":"2026-07-05T08:08:54.536566+00:00"}