{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QUVA7QRQJKEJG2G23LZVNWWCEB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"afd68f12d340fcb274edeff1ec42ac2209c6fb8eb1e6a3f9269f0d188bd5e094","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T05:29:12Z","title_canon_sha256":"ecebdc94f2c203a924c217b37185e75e71f5ecf144812da88f48605ef81497db"},"schema_version":"1.0","source":{"id":"2405.15223","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15223","created_at":"2026-07-05T09:28:50Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15223v3","created_at":"2026-07-05T09:28:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15223","created_at":"2026-07-05T09:28:50Z"},{"alias_kind":"pith_short_12","alias_value":"QUVA7QRQJKEJ","created_at":"2026-07-05T09:28:50Z"},{"alias_kind":"pith_short_16","alias_value":"QUVA7QRQJKEJG2G2","created_at":"2026-07-05T09:28:50Z"},{"alias_kind":"pith_short_8","alias_value":"QUVA7QRQ","created_at":"2026-07-05T09:28:50Z"}],"graph_snapshots":[{"event_id":"sha256:bcabaf1f371abab0f3396928cce73cade6346b6d4656dca9249e90ed14267143","target":"graph","created_at":"2026-07-05T09:28:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.15223/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dong Li, Jialong Wu, Jianye Hao, Mingsheng Long, Ningya Feng, Shaofeng Yin, Xu He","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T05:29:12Z","title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15223","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f927928a1847a38f3db5c00effe456e0be6a2e9e26ad173294781fc3ee9e5498","target":"record","created_at":"2026-07-05T09:28:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"afd68f12d340fcb274edeff1ec42ac2209c6fb8eb1e6a3f9269f0d188bd5e094","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T05:29:12Z","title_canon_sha256":"ecebdc94f2c203a924c217b37185e75e71f5ecf144812da88f48605ef81497db"},"schema_version":"1.0","source":{"id":"2405.15223","kind":"arxiv","version":3}},"canonical_sha256":"852a0fc2304a889368dadaf356dac220580b258674e43b79c1ad16215aa80e58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"852a0fc2304a889368dadaf356dac220580b258674e43b79c1ad16215aa80e58","first_computed_at":"2026-07-05T09:28:50.203490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:50.203490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kfd9Vd/dlTn5cEAcXvaxHT0o4AODPnUDAhIVNBHxdTU2QIo8SYgJND/24zmM23SacVq5H1g/zqvwcLp/j1CWDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:50.203984Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.15223","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f927928a1847a38f3db5c00effe456e0be6a2e9e26ad173294781fc3ee9e5498","sha256:bcabaf1f371abab0f3396928cce73cade6346b6d4656dca9249e90ed14267143"],"state_sha256":"c671bd1221338dca51db5ac8781e046ffba578bdbb3f2fd160caf3dbbec12fc6"}