{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:D55KQMVHSQWWAYOSDOVMC74ZQO","short_pith_number":"pith:D55KQMVH","schema_version":"1.0","canonical_sha256":"1f7aa832a7942d6061d21baac17f99839cd5814b2871e942a5b4e7c0ac257977","source":{"kind":"arxiv","id":"2606.00793","version":1},"attestation_state":"computed","paper":{"title":"MBench: A Comprehensive Benchmark on Memory Capability for Video World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Li, Chensheng Dai, Hanyang Wang, Hao Liu, Min Chen, Shengjun Zhang, Simin Huang, Yifan Li, Yingjie Chen, Yueqi Duan, Yuxin Li, Zhang Zhang, Zhenyu Tang","submitted_at":"2026-05-30T16:17:33Z","abstract_excerpt":"Recent advancements in video-based world models have demonstrated an unprecedented ability to synthesize high-fidelity visual sequences. However, a fundamental gap persists between visually plausible video generation and the functional requirements of a world model, particularly in maintaining a stable and reasonable internal state over extended temporal horizons. While existing benchmarks primarily emphasize visual quality, motion coherence, and text-video alignment, they largely overlook memory, the core capability of a world model to preserve consistency across long-term horizons and comple"},"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":"2606.00793","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-30T16:17:33Z","cross_cats_sorted":[],"title_canon_sha256":"895854e6d5629ec62030efefe7a2baa6802aa97584ba52b83001fd1e00a5882b","abstract_canon_sha256":"e25a679ec0f7e94656f2316a56a7b68c21afe4c6cec390a30a9dd3ff2c95fda3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:06.002382Z","signature_b64":"givtcWA3rGib+PJ5UP96iTTE6z5H8iMqRUwskbru0wd+bZalqoD+g0T1jmrcbf8PLxeVK+hdMxhrkSt6F3y0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f7aa832a7942d6061d21baac17f99839cd5814b2871e942a5b4e7c0ac257977","last_reissued_at":"2026-06-02T01:04:06.001941Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:06.001941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MBench: A Comprehensive Benchmark on Memory Capability for Video World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Li, Chensheng Dai, Hanyang Wang, Hao Liu, Min Chen, Shengjun Zhang, Simin Huang, Yifan Li, Yingjie Chen, Yueqi Duan, Yuxin Li, Zhang Zhang, Zhenyu Tang","submitted_at":"2026-05-30T16:17:33Z","abstract_excerpt":"Recent advancements in video-based world models have demonstrated an unprecedented ability to synthesize high-fidelity visual sequences. However, a fundamental gap persists between visually plausible video generation and the functional requirements of a world model, particularly in maintaining a stable and reasonable internal state over extended temporal horizons. While existing benchmarks primarily emphasize visual quality, motion coherence, and text-video alignment, they largely overlook memory, the core capability of a world model to preserve consistency across long-term horizons and comple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00793","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/2606.00793/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":"2606.00793","created_at":"2026-06-02T01:04:06.001997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00793v1","created_at":"2026-06-02T01:04:06.001997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00793","created_at":"2026-06-02T01:04:06.001997+00:00"},{"alias_kind":"pith_short_12","alias_value":"D55KQMVHSQWW","created_at":"2026-06-02T01:04:06.001997+00:00"},{"alias_kind":"pith_short_16","alias_value":"D55KQMVHSQWWAYOS","created_at":"2026-06-02T01:04:06.001997+00:00"},{"alias_kind":"pith_short_8","alias_value":"D55KQMVH","created_at":"2026-06-02T01:04:06.001997+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/D55KQMVHSQWWAYOSDOVMC74ZQO","json":"https://pith.science/pith/D55KQMVHSQWWAYOSDOVMC74ZQO.json","graph_json":"https://pith.science/api/pith-number/D55KQMVHSQWWAYOSDOVMC74ZQO/graph.json","events_json":"https://pith.science/api/pith-number/D55KQMVHSQWWAYOSDOVMC74ZQO/events.json","paper":"https://pith.science/paper/D55KQMVH"},"agent_actions":{"view_html":"https://pith.science/pith/D55KQMVHSQWWAYOSDOVMC74ZQO","download_json":"https://pith.science/pith/D55KQMVHSQWWAYOSDOVMC74ZQO.json","view_paper":"https://pith.science/paper/D55KQMVH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00793&json=true","fetch_graph":"https://pith.science/api/pith-number/D55KQMVHSQWWAYOSDOVMC74ZQO/graph.json","fetch_events":"https://pith.science/api/pith-number/D55KQMVHSQWWAYOSDOVMC74ZQO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D55KQMVHSQWWAYOSDOVMC74ZQO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D55KQMVHSQWWAYOSDOVMC74ZQO/action/storage_attestation","attest_author":"https://pith.science/pith/D55KQMVHSQWWAYOSDOVMC74ZQO/action/author_attestation","sign_citation":"https://pith.science/pith/D55KQMVHSQWWAYOSDOVMC74ZQO/action/citation_signature","submit_replication":"https://pith.science/pith/D55KQMVHSQWWAYOSDOVMC74ZQO/action/replication_record"}},"created_at":"2026-06-02T01:04:06.001997+00:00","updated_at":"2026-06-02T01:04:06.001997+00:00"}