{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CXKXZ23R5DLTNI2N3ZHNYPQ6IB","short_pith_number":"pith:CXKXZ23R","schema_version":"1.0","canonical_sha256":"15d57ceb71e8d736a34dde4edc3e1e4063ae5f103883f3c932d6f815c2237389","source":{"kind":"arxiv","id":"2605.30263","version":1},"attestation_state":"computed","paper":{"title":"minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bokai Yan, Chongxuan Li, Fan Bao, Guande He, Hongzhou Zhu, Jun Zhu, Kaiwen Zheng, Min Zhao, Wenqiang Sun, Xiao Yang, Yimin Chen, Zihan Zhou","submitted_at":"2026-05-28T17:27:03Z","abstract_excerpt":"Recent video diffusion foundation models have achieved remarkable progress in high-quality video generation, yet turning them into real-time interactive video world models remains challenging. Interactive world models require controllable, causal, and low-latency rollout, which in practice demands a full pipeline spanning data construction, controllable fine-tuning, autoregressive training, few-step distillation, and streaming inference. In this work, we present minWM, a full-stack open-source framework for building real-time interactive video world models. minWM provides an end-to-end pipelin"},"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":"2605.30263","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:27:03Z","cross_cats_sorted":[],"title_canon_sha256":"4a92afb593df2775b15b16cd2ed817c1bcdaf54e9f4f63a081b76a44b62982b9","abstract_canon_sha256":"1e2d73d5dc594f228dfa7bfcc3c978b0f041d742c55428463eb98faa0a268b35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:14.454193Z","signature_b64":"gUlLC1opVC39fKsZHMJ6BjhboITwlJJ1Bj5D70oCgeDrmyP89WSSeGWC6p10T6OtpnOLQ/FqViDwgRYjqWRmDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15d57ceb71e8d736a34dde4edc3e1e4063ae5f103883f3c932d6f815c2237389","last_reissued_at":"2026-05-29T02:06:14.453751Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:14.453751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bokai Yan, Chongxuan Li, Fan Bao, Guande He, Hongzhou Zhu, Jun Zhu, Kaiwen Zheng, Min Zhao, Wenqiang Sun, Xiao Yang, Yimin Chen, Zihan Zhou","submitted_at":"2026-05-28T17:27:03Z","abstract_excerpt":"Recent video diffusion foundation models have achieved remarkable progress in high-quality video generation, yet turning them into real-time interactive video world models remains challenging. Interactive world models require controllable, causal, and low-latency rollout, which in practice demands a full pipeline spanning data construction, controllable fine-tuning, autoregressive training, few-step distillation, and streaming inference. In this work, we present minWM, a full-stack open-source framework for building real-time interactive video world models. minWM provides an end-to-end pipelin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30263","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/2605.30263/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":"2605.30263","created_at":"2026-05-29T02:06:14.453815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30263v1","created_at":"2026-05-29T02:06:14.453815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30263","created_at":"2026-05-29T02:06:14.453815+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXKXZ23R5DLT","created_at":"2026-05-29T02:06:14.453815+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXKXZ23R5DLTNI2N","created_at":"2026-05-29T02:06:14.453815+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXKXZ23R","created_at":"2026-05-29T02:06:14.453815+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/CXKXZ23R5DLTNI2N3ZHNYPQ6IB","json":"https://pith.science/pith/CXKXZ23R5DLTNI2N3ZHNYPQ6IB.json","graph_json":"https://pith.science/api/pith-number/CXKXZ23R5DLTNI2N3ZHNYPQ6IB/graph.json","events_json":"https://pith.science/api/pith-number/CXKXZ23R5DLTNI2N3ZHNYPQ6IB/events.json","paper":"https://pith.science/paper/CXKXZ23R"},"agent_actions":{"view_html":"https://pith.science/pith/CXKXZ23R5DLTNI2N3ZHNYPQ6IB","download_json":"https://pith.science/pith/CXKXZ23R5DLTNI2N3ZHNYPQ6IB.json","view_paper":"https://pith.science/paper/CXKXZ23R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30263&json=true","fetch_graph":"https://pith.science/api/pith-number/CXKXZ23R5DLTNI2N3ZHNYPQ6IB/graph.json","fetch_events":"https://pith.science/api/pith-number/CXKXZ23R5DLTNI2N3ZHNYPQ6IB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXKXZ23R5DLTNI2N3ZHNYPQ6IB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXKXZ23R5DLTNI2N3ZHNYPQ6IB/action/storage_attestation","attest_author":"https://pith.science/pith/CXKXZ23R5DLTNI2N3ZHNYPQ6IB/action/author_attestation","sign_citation":"https://pith.science/pith/CXKXZ23R5DLTNI2N3ZHNYPQ6IB/action/citation_signature","submit_replication":"https://pith.science/pith/CXKXZ23R5DLTNI2N3ZHNYPQ6IB/action/replication_record"}},"created_at":"2026-05-29T02:06:14.453815+00:00","updated_at":"2026-05-29T02:06:14.453815+00:00"}