{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:S2SD3QU73K4YS2WF6ETLGOBP7O","short_pith_number":"pith:S2SD3QU7","schema_version":"1.0","canonical_sha256":"96a43dc29fdab9896ac5f126b3382ffb8335c256b7c9cd7939a25f9bf8fa9638","source":{"kind":"arxiv","id":"2605.28865","version":1},"attestation_state":"computed","paper":{"title":"Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiayi Fang","submitted_at":"2026-05-22T03:31:47Z","abstract_excerpt":"What does a world model learn from physical exploration, without any linguistic supervision? We argue the answer is organized by a single principle: the geometric structure of the physical world. Training a VAE-based world model on random embodied exploration, we find that its latent space develops spatial semantic structure that mirrors physical geometry -- direction accuracy 0.677+-0.029 versus 0.547 for a randomly initialized encoder, and position RSA 0.192+-0.047 versus 0.029 for random encoders (6.6x improvement), showing that training induces genuine structural organization beyond CNN in"},"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":"2605.28865","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T03:31:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7e87159343cdc38b27543f38f75c98f7822ef3c103d4b7f9de7322e84eb5fdb2","abstract_canon_sha256":"e51624a4df1fc7d9e4dc6a6627996b5b3b14d833279825bc4902c1ac4917af89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T00:04:14.663523Z","signature_b64":"HDxArvRKAZvDiqPh8piUPvYyocGQ1BbLDRlFu1dCqK7V/TRTHsfRFrJhw0BZ4bsD612jZ0wabzhP6Kr8Tm4UAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96a43dc29fdab9896ac5f126b3382ffb8335c256b7c9cd7939a25f9bf8fa9638","last_reissued_at":"2026-05-29T00:04:14.662999Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T00:04:14.662999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiayi Fang","submitted_at":"2026-05-22T03:31:47Z","abstract_excerpt":"What does a world model learn from physical exploration, without any linguistic supervision? We argue the answer is organized by a single principle: the geometric structure of the physical world. Training a VAE-based world model on random embodied exploration, we find that its latent space develops spatial semantic structure that mirrors physical geometry -- direction accuracy 0.677+-0.029 versus 0.547 for a randomly initialized encoder, and position RSA 0.192+-0.047 versus 0.029 for random encoders (6.6x improvement), showing that training induces genuine structural organization beyond CNN in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28865","kind":"arxiv","version":1},"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/2605.28865/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":"2605.28865","created_at":"2026-05-29T00:04:14.663086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28865v1","created_at":"2026-05-29T00:04:14.663086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28865","created_at":"2026-05-29T00:04:14.663086+00:00"},{"alias_kind":"pith_short_12","alias_value":"S2SD3QU73K4Y","created_at":"2026-05-29T00:04:14.663086+00:00"},{"alias_kind":"pith_short_16","alias_value":"S2SD3QU73K4YS2WF","created_at":"2026-05-29T00:04:14.663086+00:00"},{"alias_kind":"pith_short_8","alias_value":"S2SD3QU7","created_at":"2026-05-29T00:04:14.663086+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S2SD3QU73K4YS2WF6ETLGOBP7O","json":"https://pith.science/pith/S2SD3QU73K4YS2WF6ETLGOBP7O.json","graph_json":"https://pith.science/api/pith-number/S2SD3QU73K4YS2WF6ETLGOBP7O/graph.json","events_json":"https://pith.science/api/pith-number/S2SD3QU73K4YS2WF6ETLGOBP7O/events.json","paper":"https://pith.science/paper/S2SD3QU7"},"agent_actions":{"view_html":"https://pith.science/pith/S2SD3QU73K4YS2WF6ETLGOBP7O","download_json":"https://pith.science/pith/S2SD3QU73K4YS2WF6ETLGOBP7O.json","view_paper":"https://pith.science/paper/S2SD3QU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28865&json=true","fetch_graph":"https://pith.science/api/pith-number/S2SD3QU73K4YS2WF6ETLGOBP7O/graph.json","fetch_events":"https://pith.science/api/pith-number/S2SD3QU73K4YS2WF6ETLGOBP7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S2SD3QU73K4YS2WF6ETLGOBP7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S2SD3QU73K4YS2WF6ETLGOBP7O/action/storage_attestation","attest_author":"https://pith.science/pith/S2SD3QU73K4YS2WF6ETLGOBP7O/action/author_attestation","sign_citation":"https://pith.science/pith/S2SD3QU73K4YS2WF6ETLGOBP7O/action/citation_signature","submit_replication":"https://pith.science/pith/S2SD3QU73K4YS2WF6ETLGOBP7O/action/replication_record"}},"created_at":"2026-05-29T00:04:14.663086+00:00","updated_at":"2026-05-29T00:04:14.663086+00:00"}