{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IXJWLJA7R3MOWI6GPFXX2M3N5L","short_pith_number":"pith:IXJWLJA7","schema_version":"1.0","canonical_sha256":"45d365a41f8ed8eb23c6796f7d336dead9f4f39baf1627dcc73499d0fb766ba2","source":{"kind":"arxiv","id":"2501.00226","version":2},"attestation_state":"computed","paper":{"title":"Generative Emergent Communication: Large Language Model is a Collective World Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Akira Taniguchi, Masahiro Suzuki, Ryo Ueda, Tadahiro Taniguchi, Tomoaki Nakamura","submitted_at":"2024-12-31T02:23:10Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated a remarkable ability to capture extensive world knowledge, yet how this is achieved without direct sensorimotor experience remains a fundamental puzzle. This study proposes a novel theoretical solution by introducing the Collective World Model hypothesis. We argue that an LLM does not learn a world model from scratch; instead, it learns a statistical approximation of a collective world model that is already implicitly encoded in human language through a society-wide process of embodied, interactive sense-making. To formalize this process, we intro"},"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":"2501.00226","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-31T02:23:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1180c6427012dacfbafd84af4abae7dbdc77e2cadcebf20ed9232f2740484654","abstract_canon_sha256":"45c5ecb65c6d30845eb6533efdfe5cf36b8a88c455fef242a4f13d3018c15d4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:03.403868Z","signature_b64":"eo8eF+LZOr4LvOBSRDIN+Rz+7vsm+88PP+DvV3DsHdqBmXTMA89SWUgF9oB0Tj7qbW7zMSdV9oT9LgMEq89wCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45d365a41f8ed8eb23c6796f7d336dead9f4f39baf1627dcc73499d0fb766ba2","last_reissued_at":"2026-07-05T11:38:03.403332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:03.403332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Emergent Communication: Large Language Model is a Collective World Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Akira Taniguchi, Masahiro Suzuki, Ryo Ueda, Tadahiro Taniguchi, Tomoaki Nakamura","submitted_at":"2024-12-31T02:23:10Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated a remarkable ability to capture extensive world knowledge, yet how this is achieved without direct sensorimotor experience remains a fundamental puzzle. This study proposes a novel theoretical solution by introducing the Collective World Model hypothesis. We argue that an LLM does not learn a world model from scratch; instead, it learns a statistical approximation of a collective world model that is already implicitly encoded in human language through a society-wide process of embodied, interactive sense-making. To formalize this process, we intro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00226","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/2501.00226/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":"2501.00226","created_at":"2026-07-05T11:38:03.403394+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00226v2","created_at":"2026-07-05T11:38:03.403394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00226","created_at":"2026-07-05T11:38:03.403394+00:00"},{"alias_kind":"pith_short_12","alias_value":"IXJWLJA7R3MO","created_at":"2026-07-05T11:38:03.403394+00:00"},{"alias_kind":"pith_short_16","alias_value":"IXJWLJA7R3MOWI6G","created_at":"2026-07-05T11:38:03.403394+00:00"},{"alias_kind":"pith_short_8","alias_value":"IXJWLJA7","created_at":"2026-07-05T11:38:03.403394+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.03353","citing_title":"Decentralized Collective World Model for Emergent Communication and Coordination","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18759","citing_title":"Interoceptive Divergence in Aesthetic Evaluation and Implications for Human-AI Alignment","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11695","citing_title":"Emergent Communication between Heterogeneous Visual Agents through Decentralized Learning","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11695","citing_title":"Emergent Communication between Heterogeneous Visual Agents through Decentralized Learning","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08368","citing_title":"On Distinguishing Capability Elicitation from Capability Creation in Post-Training: A Free-Energy Perspective","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05861","citing_title":"SANEmerg: An Emergent Communication Framework for Semantic-aware Agentic AI Networking","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IXJWLJA7R3MOWI6GPFXX2M3N5L","json":"https://pith.science/pith/IXJWLJA7R3MOWI6GPFXX2M3N5L.json","graph_json":"https://pith.science/api/pith-number/IXJWLJA7R3MOWI6GPFXX2M3N5L/graph.json","events_json":"https://pith.science/api/pith-number/IXJWLJA7R3MOWI6GPFXX2M3N5L/events.json","paper":"https://pith.science/paper/IXJWLJA7"},"agent_actions":{"view_html":"https://pith.science/pith/IXJWLJA7R3MOWI6GPFXX2M3N5L","download_json":"https://pith.science/pith/IXJWLJA7R3MOWI6GPFXX2M3N5L.json","view_paper":"https://pith.science/paper/IXJWLJA7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00226&json=true","fetch_graph":"https://pith.science/api/pith-number/IXJWLJA7R3MOWI6GPFXX2M3N5L/graph.json","fetch_events":"https://pith.science/api/pith-number/IXJWLJA7R3MOWI6GPFXX2M3N5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IXJWLJA7R3MOWI6GPFXX2M3N5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IXJWLJA7R3MOWI6GPFXX2M3N5L/action/storage_attestation","attest_author":"https://pith.science/pith/IXJWLJA7R3MOWI6GPFXX2M3N5L/action/author_attestation","sign_citation":"https://pith.science/pith/IXJWLJA7R3MOWI6GPFXX2M3N5L/action/citation_signature","submit_replication":"https://pith.science/pith/IXJWLJA7R3MOWI6GPFXX2M3N5L/action/replication_record"}},"created_at":"2026-07-05T11:38:03.403394+00:00","updated_at":"2026-07-05T11:38:03.403394+00:00"}