{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QUVA7QRQJKEJG2G23LZVNWWCEB","short_pith_number":"pith:QUVA7QRQ","schema_version":"1.0","canonical_sha256":"852a0fc2304a889368dadaf356dac220580b258674e43b79c1ad16215aa80e58","source":{"kind":"arxiv","id":"2405.15223","version":3},"attestation_state":"computed","paper":{"title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Dong Li, Jialong Wu, Jianye Hao, Mingsheng Long, Ningya Feng, Shaofeng Yin, Xu He","submitted_at":"2024-05-24T05:29:12Z","abstract_excerpt":"World models empower model-based agents to interactively explore, reason, and plan within imagined environments for real-world decision-making. However, the high demand for interactivity poses challenges in harnessing recent advancements in video generative models for developing world models at scale. This work introduces Interactive VideoGPT (iVideoGPT), a scalable autoregressive transformer framework that integrates multimodal signals--visual observations, actions, and rewards--into a sequence of tokens, facilitating an interactive experience of agents via next-token prediction. iVideoGPT fe"},"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":"2405.15223","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T05:29:12Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"ecebdc94f2c203a924c217b37185e75e71f5ecf144812da88f48605ef81497db","abstract_canon_sha256":"afd68f12d340fcb274edeff1ec42ac2209c6fb8eb1e6a3f9269f0d188bd5e094"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:50.203984Z","signature_b64":"Kfd9Vd/dlTn5cEAcXvaxHT0o4AODPnUDAhIVNBHxdTU2QIo8SYgJND/24zmM23SacVq5H1g/zqvwcLp/j1CWDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"852a0fc2304a889368dadaf356dac220580b258674e43b79c1ad16215aa80e58","last_reissued_at":"2026-07-05T09:28:50.203490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:50.203490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Dong Li, Jialong Wu, Jianye Hao, Mingsheng Long, Ningya Feng, Shaofeng Yin, Xu He","submitted_at":"2024-05-24T05:29:12Z","abstract_excerpt":"World models empower model-based agents to interactively explore, reason, and plan within imagined environments for real-world decision-making. However, the high demand for interactivity poses challenges in harnessing recent advancements in video generative models for developing world models at scale. This work introduces Interactive VideoGPT (iVideoGPT), a scalable autoregressive transformer framework that integrates multimodal signals--visual observations, actions, and rewards--into a sequence of tokens, facilitating an interactive experience of agents via next-token prediction. iVideoGPT fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15223","kind":"arxiv","version":3},"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/2405.15223/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":"2405.15223","created_at":"2026-07-05T09:28:50.203558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15223v3","created_at":"2026-07-05T09:28:50.203558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15223","created_at":"2026-07-05T09:28:50.203558+00:00"},{"alias_kind":"pith_short_12","alias_value":"QUVA7QRQJKEJ","created_at":"2026-07-05T09:28:50.203558+00:00"},{"alias_kind":"pith_short_16","alias_value":"QUVA7QRQJKEJG2G2","created_at":"2026-07-05T09:28:50.203558+00:00"},{"alias_kind":"pith_short_8","alias_value":"QUVA7QRQ","created_at":"2026-07-05T09:28:50.203558+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20781","citing_title":"World Action Models: A Survey","ref_index":174,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04130","citing_title":"CLAW: Learning Continuous Latent Action World Models via Adversarial Latent Regularization","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QUVA7QRQJKEJG2G23LZVNWWCEB","json":"https://pith.science/pith/QUVA7QRQJKEJG2G23LZVNWWCEB.json","graph_json":"https://pith.science/api/pith-number/QUVA7QRQJKEJG2G23LZVNWWCEB/graph.json","events_json":"https://pith.science/api/pith-number/QUVA7QRQJKEJG2G23LZVNWWCEB/events.json","paper":"https://pith.science/paper/QUVA7QRQ"},"agent_actions":{"view_html":"https://pith.science/pith/QUVA7QRQJKEJG2G23LZVNWWCEB","download_json":"https://pith.science/pith/QUVA7QRQJKEJG2G23LZVNWWCEB.json","view_paper":"https://pith.science/paper/QUVA7QRQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15223&json=true","fetch_graph":"https://pith.science/api/pith-number/QUVA7QRQJKEJG2G23LZVNWWCEB/graph.json","fetch_events":"https://pith.science/api/pith-number/QUVA7QRQJKEJG2G23LZVNWWCEB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QUVA7QRQJKEJG2G23LZVNWWCEB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QUVA7QRQJKEJG2G23LZVNWWCEB/action/storage_attestation","attest_author":"https://pith.science/pith/QUVA7QRQJKEJG2G23LZVNWWCEB/action/author_attestation","sign_citation":"https://pith.science/pith/QUVA7QRQJKEJG2G23LZVNWWCEB/action/citation_signature","submit_replication":"https://pith.science/pith/QUVA7QRQJKEJG2G23LZVNWWCEB/action/replication_record"}},"created_at":"2026-07-05T09:28:50.203558+00:00","updated_at":"2026-07-05T09:28:50.203558+00:00"}