{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VSXCWOS75YEGWR6UDB2ZDXWWIT","short_pith_number":"pith:VSXCWOS7","schema_version":"1.0","canonical_sha256":"acae2b3a5fee086b47d4187591ded644c301b192648a688539453b557371e04d","source":{"kind":"arxiv","id":"2605.24578","version":1},"attestation_state":"computed","paper":{"title":"World Models as Group Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanqi Zhang, Guanbin Li, Weiming Zhang, Wei Zhang, Xiao Tan, Yipeng Qin, Zijie Wang","submitted_at":"2026-05-23T13:42:35Z","abstract_excerpt":"Video world models have achieved strong visual realism, but this does not ensure that their dynamics are truly governed by actions. In this work, we argue that action faithfulness should be understood through the compositional structure of actions, which in many embodied settings follows a group structure (e.g., SE(2) for navigation). Based on this insight, we formalize action-conditioned world modeling as realizing a group action on the state space, providing a principled criterion for evaluating dynamics beyond visual quality. To operationalize this framework, we propose a unified approach t"},"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":"2605.24578","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-23T13:42:35Z","cross_cats_sorted":[],"title_canon_sha256":"d9d697bad24c67d96cb29e32fe643904727fd1acd95408bc50e95075b18da76f","abstract_canon_sha256":"18efe8e9922fd87024745f7621ef33cc556a33d2e55b21476fe95fb027d06e60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:47.206733Z","signature_b64":"bUGpunBenqKfb6/a4iiFCHb+pK1YLUYsNw7VyRH6riPkTtRB4I4dw5GaOLOsv4gQBLR2vQBIh8jzasm7WjBkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acae2b3a5fee086b47d4187591ded644c301b192648a688539453b557371e04d","last_reissued_at":"2026-05-26T01:03:47.205855Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:47.205855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"World Models as Group Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanqi Zhang, Guanbin Li, Weiming Zhang, Wei Zhang, Xiao Tan, Yipeng Qin, Zijie Wang","submitted_at":"2026-05-23T13:42:35Z","abstract_excerpt":"Video world models have achieved strong visual realism, but this does not ensure that their dynamics are truly governed by actions. In this work, we argue that action faithfulness should be understood through the compositional structure of actions, which in many embodied settings follows a group structure (e.g., SE(2) for navigation). Based on this insight, we formalize action-conditioned world modeling as realizing a group action on the state space, providing a principled criterion for evaluating dynamics beyond visual quality. To operationalize this framework, we propose a unified approach t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24578","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/2605.24578/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":"2605.24578","created_at":"2026-05-26T01:03:47.206034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24578v1","created_at":"2026-05-26T01:03:47.206034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24578","created_at":"2026-05-26T01:03:47.206034+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSXCWOS75YEG","created_at":"2026-05-26T01:03:47.206034+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSXCWOS75YEGWR6U","created_at":"2026-05-26T01:03:47.206034+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSXCWOS7","created_at":"2026-05-26T01:03:47.206034+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/VSXCWOS75YEGWR6UDB2ZDXWWIT","json":"https://pith.science/pith/VSXCWOS75YEGWR6UDB2ZDXWWIT.json","graph_json":"https://pith.science/api/pith-number/VSXCWOS75YEGWR6UDB2ZDXWWIT/graph.json","events_json":"https://pith.science/api/pith-number/VSXCWOS75YEGWR6UDB2ZDXWWIT/events.json","paper":"https://pith.science/paper/VSXCWOS7"},"agent_actions":{"view_html":"https://pith.science/pith/VSXCWOS75YEGWR6UDB2ZDXWWIT","download_json":"https://pith.science/pith/VSXCWOS75YEGWR6UDB2ZDXWWIT.json","view_paper":"https://pith.science/paper/VSXCWOS7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24578&json=true","fetch_graph":"https://pith.science/api/pith-number/VSXCWOS75YEGWR6UDB2ZDXWWIT/graph.json","fetch_events":"https://pith.science/api/pith-number/VSXCWOS75YEGWR6UDB2ZDXWWIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSXCWOS75YEGWR6UDB2ZDXWWIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSXCWOS75YEGWR6UDB2ZDXWWIT/action/storage_attestation","attest_author":"https://pith.science/pith/VSXCWOS75YEGWR6UDB2ZDXWWIT/action/author_attestation","sign_citation":"https://pith.science/pith/VSXCWOS75YEGWR6UDB2ZDXWWIT/action/citation_signature","submit_replication":"https://pith.science/pith/VSXCWOS75YEGWR6UDB2ZDXWWIT/action/replication_record"}},"created_at":"2026-05-26T01:03:47.206034+00:00","updated_at":"2026-05-26T01:03:47.206034+00:00"}