{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5GLSSDV3ZRZCOLRIVH3EMXRIJN","short_pith_number":"pith:5GLSSDV3","schema_version":"1.0","canonical_sha256":"e997290ebbcc72272e28a9f6465e284b4a64c1a0438e0a3ffb827624403305f4","source":{"kind":"arxiv","id":"2602.16229","version":2},"attestation_state":"computed","paper":{"title":"Factored Latent Action World Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amy Zhang, Chang Shi, Jiaheng Hu, Kevin Rohling, Peter Stone, Roberto Mart\\'in-Mart\\'in, Zizhao Wang","submitted_at":"2026-02-18T07:08:14Z","abstract_excerpt":"Learning latent actions from action-free video has emerged as a powerful paradigm for scaling up controllable world model learning. Latent actions provide a natural interface for users to iteratively generate and manipulate videos. However, most existing approaches rely on monolithic inverse and forward dynamics models that learn a single latent action to control the entire scene, and therefore struggle in complex environments where multiple entities act simultaneously. This paper introduces Factored Latent Action Model (FLAM), a factored dynamics framework that decomposes the scene into indep"},"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":"2602.16229","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-18T07:08:14Z","cross_cats_sorted":[],"title_canon_sha256":"9a7e1685ff85d820d440d98671ea464933cdd0f67daf361c91361e9f15788e93","abstract_canon_sha256":"84f4f7e263dbe851c1aea706f831760d4647656763475d0c76442288304d48ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:06.644667Z","signature_b64":"tufoPIacO6ZzAH4/2WW5WOiMaEXqT09uX0m6lBuWz+d4rp3SRNfJALD57xwp0oaPrFkS07AcML8iymvYYkFWCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e997290ebbcc72272e28a9f6465e284b4a64c1a0438e0a3ffb827624403305f4","last_reissued_at":"2026-05-26T02:04:06.643743Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:06.643743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Factored Latent Action World Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amy Zhang, Chang Shi, Jiaheng Hu, Kevin Rohling, Peter Stone, Roberto Mart\\'in-Mart\\'in, Zizhao Wang","submitted_at":"2026-02-18T07:08:14Z","abstract_excerpt":"Learning latent actions from action-free video has emerged as a powerful paradigm for scaling up controllable world model learning. Latent actions provide a natural interface for users to iteratively generate and manipulate videos. However, most existing approaches rely on monolithic inverse and forward dynamics models that learn a single latent action to control the entire scene, and therefore struggle in complex environments where multiple entities act simultaneously. This paper introduces Factored Latent Action Model (FLAM), a factored dynamics framework that decomposes the scene into indep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.16229","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/2602.16229/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":"2602.16229","created_at":"2026-05-26T02:04:06.643856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.16229v2","created_at":"2026-05-26T02:04:06.643856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.16229","created_at":"2026-05-26T02:04:06.643856+00:00"},{"alias_kind":"pith_short_12","alias_value":"5GLSSDV3ZRZC","created_at":"2026-05-26T02:04:06.643856+00:00"},{"alias_kind":"pith_short_16","alias_value":"5GLSSDV3ZRZCOLRI","created_at":"2026-05-26T02:04:06.643856+00:00"},{"alias_kind":"pith_short_8","alias_value":"5GLSSDV3","created_at":"2026-05-26T02:04:06.643856+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.01694","citing_title":"Latent State Design for World Models under Sufficiency Constraints","ref_index":62,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5GLSSDV3ZRZCOLRIVH3EMXRIJN","json":"https://pith.science/pith/5GLSSDV3ZRZCOLRIVH3EMXRIJN.json","graph_json":"https://pith.science/api/pith-number/5GLSSDV3ZRZCOLRIVH3EMXRIJN/graph.json","events_json":"https://pith.science/api/pith-number/5GLSSDV3ZRZCOLRIVH3EMXRIJN/events.json","paper":"https://pith.science/paper/5GLSSDV3"},"agent_actions":{"view_html":"https://pith.science/pith/5GLSSDV3ZRZCOLRIVH3EMXRIJN","download_json":"https://pith.science/pith/5GLSSDV3ZRZCOLRIVH3EMXRIJN.json","view_paper":"https://pith.science/paper/5GLSSDV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.16229&json=true","fetch_graph":"https://pith.science/api/pith-number/5GLSSDV3ZRZCOLRIVH3EMXRIJN/graph.json","fetch_events":"https://pith.science/api/pith-number/5GLSSDV3ZRZCOLRIVH3EMXRIJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5GLSSDV3ZRZCOLRIVH3EMXRIJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5GLSSDV3ZRZCOLRIVH3EMXRIJN/action/storage_attestation","attest_author":"https://pith.science/pith/5GLSSDV3ZRZCOLRIVH3EMXRIJN/action/author_attestation","sign_citation":"https://pith.science/pith/5GLSSDV3ZRZCOLRIVH3EMXRIJN/action/citation_signature","submit_replication":"https://pith.science/pith/5GLSSDV3ZRZCOLRIVH3EMXRIJN/action/replication_record"}},"created_at":"2026-05-26T02:04:06.643856+00:00","updated_at":"2026-05-26T02:04:06.643856+00:00"}