{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JAFMZ3H4ZMAR3XAIMPWDLP5VTH","short_pith_number":"pith:JAFMZ3H4","schema_version":"1.0","canonical_sha256":"480accecfccb011ddc0863ec35bfb599ffd0b788fee171fce18f27aef5752021","source":{"kind":"arxiv","id":"2604.02330","version":2},"attestation_state":"computed","paper":{"title":"ActionParty: Multi-Subject Action Binding in Generative Video Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Pondaven, Aliaksandr Siarohin, Fabio Pizzati, Igor Gilitschenski, Philip Torr, Sergey Tulyakov, Ziyi Wu","submitted_at":"2026-04-02T17:59:58Z","abstract_excerpt":"Recent advances in video diffusion have enabled the development of \"world models\" capable of simulating interactive environments. However, these models are largely restricted to single-agent settings, failing to control multiple agents simultaneously in a scene. In this work, we tackle a fundamental issue of action binding in existing video diffusion models, which struggle to associate specific actions with their corresponding subjects. For this purpose, we propose ActionParty, an action controllable multi-subject world model for generative video games. It introduces subject state tokens, i.e."},"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":"2604.02330","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-02T17:59:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0082ebbee7f34518492a759556ec133ce09174bb07bb3fecdc475a23018f2ad9","abstract_canon_sha256":"846634d83637ab21245d97d34f4335a890ed98f100f59bf4aed26cbc4bf9fa1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T00:10:44.619244Z","signature_b64":"miXRQjVugfX/4ZLK/UELF5OkWL3pl2FVCRY8/v0urlk21l4hjICgqZFVLaYXgNSvnp9dd5OtwLe4tG2yjgPeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"480accecfccb011ddc0863ec35bfb599ffd0b788fee171fce18f27aef5752021","last_reissued_at":"2026-08-03T00:10:44.616800Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T00:10:44.616800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ActionParty: Multi-Subject Action Binding in Generative Video Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Pondaven, Aliaksandr Siarohin, Fabio Pizzati, Igor Gilitschenski, Philip Torr, Sergey Tulyakov, Ziyi Wu","submitted_at":"2026-04-02T17:59:58Z","abstract_excerpt":"Recent advances in video diffusion have enabled the development of \"world models\" capable of simulating interactive environments. However, these models are largely restricted to single-agent settings, failing to control multiple agents simultaneously in a scene. In this work, we tackle a fundamental issue of action binding in existing video diffusion models, which struggle to associate specific actions with their corresponding subjects. For this purpose, we propose ActionParty, an action controllable multi-subject world model for generative video games. It introduces subject state tokens, i.e."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.02330","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/2604.02330/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":"2604.02330","created_at":"2026-08-03T00:10:44.618351+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.02330v2","created_at":"2026-08-03T00:10:44.618351+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.02330","created_at":"2026-08-03T00:10:44.618351+00:00"},{"alias_kind":"pith_short_12","alias_value":"JAFMZ3H4ZMAR","created_at":"2026-08-03T00:10:44.618351+00:00"},{"alias_kind":"pith_short_16","alias_value":"JAFMZ3H4ZMAR3XAI","created_at":"2026-08-03T00:10:44.618351+00:00"},{"alias_kind":"pith_short_8","alias_value":"JAFMZ3H4","created_at":"2026-08-03T00:10:44.618351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.05352","citing_title":"Multiplayer Interactive World Models with Representation Autoencoders","ref_index":266,"is_internal_anchor":true},{"citing_arxiv_id":"2606.01164","citing_title":"Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends","ref_index":99,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JAFMZ3H4ZMAR3XAIMPWDLP5VTH","json":"https://pith.science/pith/JAFMZ3H4ZMAR3XAIMPWDLP5VTH.json","graph_json":"https://pith.science/api/pith-number/JAFMZ3H4ZMAR3XAIMPWDLP5VTH/graph.json","events_json":"https://pith.science/api/pith-number/JAFMZ3H4ZMAR3XAIMPWDLP5VTH/events.json","paper":"https://pith.science/paper/JAFMZ3H4"},"agent_actions":{"view_html":"https://pith.science/pith/JAFMZ3H4ZMAR3XAIMPWDLP5VTH","download_json":"https://pith.science/pith/JAFMZ3H4ZMAR3XAIMPWDLP5VTH.json","view_paper":"https://pith.science/paper/JAFMZ3H4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.02330&json=true","fetch_graph":"https://pith.science/api/pith-number/JAFMZ3H4ZMAR3XAIMPWDLP5VTH/graph.json","fetch_events":"https://pith.science/api/pith-number/JAFMZ3H4ZMAR3XAIMPWDLP5VTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JAFMZ3H4ZMAR3XAIMPWDLP5VTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JAFMZ3H4ZMAR3XAIMPWDLP5VTH/action/storage_attestation","attest_author":"https://pith.science/pith/JAFMZ3H4ZMAR3XAIMPWDLP5VTH/action/author_attestation","sign_citation":"https://pith.science/pith/JAFMZ3H4ZMAR3XAIMPWDLP5VTH/action/citation_signature","submit_replication":"https://pith.science/pith/JAFMZ3H4ZMAR3XAIMPWDLP5VTH/action/replication_record"}},"created_at":"2026-08-03T00:10:44.618351+00:00","updated_at":"2026-08-03T00:10:44.618351+00:00"}