{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7TBGVBXCZQO26HRQ65Q2A2PVCN","short_pith_number":"pith:7TBGVBXC","schema_version":"1.0","canonical_sha256":"fcc26a86e2cc1daf1e30f761a069f51341acea2584075dd5aa208ba65b07dd5d","source":{"kind":"arxiv","id":"2606.31734","version":1},"attestation_state":"computed","paper":{"title":"MemLearner: Learning to Query Context memory for Video World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianhong Bai, Jianxiong Gao, Jiwen Yu, Kaiyi Huang, Kun Gai, Pengfei Wan, Quande Liu, Xihui Liu, Xintao Wang, Yiran Qin","submitted_at":"2026-06-30T14:31:32Z","abstract_excerpt":"Video World Models are interactive video generation models that predict future world states based on user actions and history video frames. A critical challenge in video world models is the lack of memory, causing inconsistent generated scenes over extended durations. Previous methods explored rule-based context frame retrieval as memory, but they fail to generalize in scenarios with scene occlusions and dynamic objects. We propose MemLearner, a learning-based adaptive context query method using query tokens to bridge context and predicted tokens. By leveraging the video generation model itsel"},"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":"2606.31734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T14:31:32Z","cross_cats_sorted":[],"title_canon_sha256":"e7d7641843721b5fa07a4111c4394782cf31d51e52cfb9471516c525054c76d0","abstract_canon_sha256":"2b6d1af9058eeb613397ea0830910b41178dd16aeba0712bfae951229a08c4de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:13.195678Z","signature_b64":"8wcI8gCstU4NbPVV27VOVNNmnHJbMVts/D+L5bmLKh/0N91BHNHTjr9Lf3ncseNxqQUSVWDu4gEANyT9N8s7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcc26a86e2cc1daf1e30f761a069f51341acea2584075dd5aa208ba65b07dd5d","last_reissued_at":"2026-07-01T01:18:13.195207Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:13.195207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MemLearner: Learning to Query Context memory for Video World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianhong Bai, Jianxiong Gao, Jiwen Yu, Kaiyi Huang, Kun Gai, Pengfei Wan, Quande Liu, Xihui Liu, Xintao Wang, Yiran Qin","submitted_at":"2026-06-30T14:31:32Z","abstract_excerpt":"Video World Models are interactive video generation models that predict future world states based on user actions and history video frames. A critical challenge in video world models is the lack of memory, causing inconsistent generated scenes over extended durations. Previous methods explored rule-based context frame retrieval as memory, but they fail to generalize in scenarios with scene occlusions and dynamic objects. We propose MemLearner, a learning-based adaptive context query method using query tokens to bridge context and predicted tokens. By leveraging the video generation model itsel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31734","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/2606.31734/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":"2606.31734","created_at":"2026-07-01T01:18:13.195272+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31734v1","created_at":"2026-07-01T01:18:13.195272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31734","created_at":"2026-07-01T01:18:13.195272+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TBGVBXCZQO2","created_at":"2026-07-01T01:18:13.195272+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TBGVBXCZQO26HRQ","created_at":"2026-07-01T01:18:13.195272+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TBGVBXC","created_at":"2026-07-01T01:18:13.195272+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/7TBGVBXCZQO26HRQ65Q2A2PVCN","json":"https://pith.science/pith/7TBGVBXCZQO26HRQ65Q2A2PVCN.json","graph_json":"https://pith.science/api/pith-number/7TBGVBXCZQO26HRQ65Q2A2PVCN/graph.json","events_json":"https://pith.science/api/pith-number/7TBGVBXCZQO26HRQ65Q2A2PVCN/events.json","paper":"https://pith.science/paper/7TBGVBXC"},"agent_actions":{"view_html":"https://pith.science/pith/7TBGVBXCZQO26HRQ65Q2A2PVCN","download_json":"https://pith.science/pith/7TBGVBXCZQO26HRQ65Q2A2PVCN.json","view_paper":"https://pith.science/paper/7TBGVBXC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31734&json=true","fetch_graph":"https://pith.science/api/pith-number/7TBGVBXCZQO26HRQ65Q2A2PVCN/graph.json","fetch_events":"https://pith.science/api/pith-number/7TBGVBXCZQO26HRQ65Q2A2PVCN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TBGVBXCZQO26HRQ65Q2A2PVCN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TBGVBXCZQO26HRQ65Q2A2PVCN/action/storage_attestation","attest_author":"https://pith.science/pith/7TBGVBXCZQO26HRQ65Q2A2PVCN/action/author_attestation","sign_citation":"https://pith.science/pith/7TBGVBXCZQO26HRQ65Q2A2PVCN/action/citation_signature","submit_replication":"https://pith.science/pith/7TBGVBXCZQO26HRQ65Q2A2PVCN/action/replication_record"}},"created_at":"2026-07-01T01:18:13.195272+00:00","updated_at":"2026-07-01T01:18:13.195272+00:00"}