{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OCIPKZMRC4EDRYGCBLWO3747LY","short_pith_number":"pith:OCIPKZMR","schema_version":"1.0","canonical_sha256":"7090f56591170838e0c20aecedff9f5e0951498d0e5b337c6cd8050e8c339d00","source":{"kind":"arxiv","id":"2605.15725","version":1},"attestation_state":"computed","paper":{"title":"DiLA: Disentangled Latent Action World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Fang Fang, Muyang Lyu, Si Wu, Tianqiu Zhang, Yufan Zhang","submitted_at":"2026-05-15T08:22:37Z","abstract_excerpt":"Latent Action Models (LAMs) enable the learning of world models from unlabeled video by inferring abstract actions between consecutive frames. However, LAMs face a fundamental trade-off between action abstraction and generation fidelity. Existing methods typically circumvent this issue by using two-stage training with pre-trained world models or by limiting predictions to optical flow. In this paper, we introduce DiLA, a novel Disentangled Latent Action world model that aims to resolve this trade-off via content-structure disentanglement. Our key insight is that disentanglement and latent acti"},"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":"2605.15725","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T08:22:37Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"3e95c992e2c4f10db8812c78c9d6598086f8729b700cb79db6878cbc62500956","abstract_canon_sha256":"70e6fd43927d00bb42947a0edd2701edea7b7df44b9f9a45b6f5bc1a4891054a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:15.044839Z","signature_b64":"b8Un1qgXanGX2DDqsxiXFcH0z/ZihCyB+MOc9kejnNsEh3UVwG+a9OpAAhC3Oha1loTTjq6uOSE20LshSut8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7090f56591170838e0c20aecedff9f5e0951498d0e5b337c6cd8050e8c339d00","last_reissued_at":"2026-05-20T00:01:15.043904Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:15.043904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiLA: Disentangled Latent Action World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Fang Fang, Muyang Lyu, Si Wu, Tianqiu Zhang, Yufan Zhang","submitted_at":"2026-05-15T08:22:37Z","abstract_excerpt":"Latent Action Models (LAMs) enable the learning of world models from unlabeled video by inferring abstract actions between consecutive frames. However, LAMs face a fundamental trade-off between action abstraction and generation fidelity. Existing methods typically circumvent this issue by using two-stage training with pre-trained world models or by limiting predictions to optical flow. In this paper, we introduce DiLA, a novel Disentangled Latent Action world model that aims to resolve this trade-off via content-structure disentanglement. Our key insight is that disentanglement and latent acti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15725","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/2605.15725/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:25.152290Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:21:56.000750Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"85fb5b26467d580b9a5ac964c05d8d97e524f6b9d3707ecf83358d9118c5cc6e"},"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":"2605.15725","created_at":"2026-05-20T00:01:15.044025+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15725v1","created_at":"2026-05-20T00:01:15.044025+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15725","created_at":"2026-05-20T00:01:15.044025+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCIPKZMRC4ED","created_at":"2026-05-20T00:01:15.044025+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCIPKZMRC4EDRYGC","created_at":"2026-05-20T00:01:15.044025+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCIPKZMR","created_at":"2026-05-20T00:01:15.044025+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/OCIPKZMRC4EDRYGCBLWO3747LY","json":"https://pith.science/pith/OCIPKZMRC4EDRYGCBLWO3747LY.json","graph_json":"https://pith.science/api/pith-number/OCIPKZMRC4EDRYGCBLWO3747LY/graph.json","events_json":"https://pith.science/api/pith-number/OCIPKZMRC4EDRYGCBLWO3747LY/events.json","paper":"https://pith.science/paper/OCIPKZMR"},"agent_actions":{"view_html":"https://pith.science/pith/OCIPKZMRC4EDRYGCBLWO3747LY","download_json":"https://pith.science/pith/OCIPKZMRC4EDRYGCBLWO3747LY.json","view_paper":"https://pith.science/paper/OCIPKZMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15725&json=true","fetch_graph":"https://pith.science/api/pith-number/OCIPKZMRC4EDRYGCBLWO3747LY/graph.json","fetch_events":"https://pith.science/api/pith-number/OCIPKZMRC4EDRYGCBLWO3747LY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCIPKZMRC4EDRYGCBLWO3747LY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCIPKZMRC4EDRYGCBLWO3747LY/action/storage_attestation","attest_author":"https://pith.science/pith/OCIPKZMRC4EDRYGCBLWO3747LY/action/author_attestation","sign_citation":"https://pith.science/pith/OCIPKZMRC4EDRYGCBLWO3747LY/action/citation_signature","submit_replication":"https://pith.science/pith/OCIPKZMRC4EDRYGCBLWO3747LY/action/replication_record"}},"created_at":"2026-05-20T00:01:15.044025+00:00","updated_at":"2026-05-20T00:01:15.044025+00:00"}