{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K4WICMQWKMKOXK7IR4SL5RRRTC","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":"1cecb239f566f9f34a1aaa1e48006cecd30a375d72e02be29a29f5c2dfab6031","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-09T20:26:30Z","title_canon_sha256":"3f9a37124008e1905db319bd338cb34d04e2769d42d92f17f134869db35d3d6b"},"schema_version":"1.0","source":{"id":"2502.06020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06020","created_at":"2026-07-05T10:11:46Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06020v1","created_at":"2026-07-05T10:11:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06020","created_at":"2026-07-05T10:11:46Z"},{"alias_kind":"pith_short_12","alias_value":"K4WICMQWKMKO","created_at":"2026-07-05T10:11:46Z"},{"alias_kind":"pith_short_16","alias_value":"K4WICMQWKMKOXK7I","created_at":"2026-07-05T10:11:46Z"},{"alias_kind":"pith_short_8","alias_value":"K4WICMQW","created_at":"2026-07-05T10:11:46Z"}],"graph_snapshots":[{"event_id":"sha256:fef50bc90a5e81956bffedbc2cd8fa5e405c4c0309a7c900fa99e3978e560f89","target":"graph","created_at":"2026-07-05T10:11:46Z","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/2502.06020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal foundation models (MFMs) have demonstrated significant success in tasks such as visual captioning, question answering, and image-text retrieval. However, these models face inherent limitations due to their finite internal capacity, which restricts their ability to process extended temporal sequences, a crucial requirement for comprehensive video and audio analysis. To overcome these challenges, we introduce a specialized cognitive module, temporal working memory (TWM), which aims to enhance the temporal modeling capabilities of MFMs. It selectively retains task-relevant information ","authors_text":"Chunhui Zhang, Jiang Gui, Ming Cheng, Peijun Qing, Soroush Vosoughi, Weiyi Wu, Xingjian Diao, Zhongyu Ouyang","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-09T20:26:30Z","title":"Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06020","kind":"arxiv","version":1},"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":"sha256:31a37ccba225e53f00064c28bda6304359363ef4773e79bc033f0ad73cb04fe8","target":"record","created_at":"2026-07-05T10:11:46Z","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":"1cecb239f566f9f34a1aaa1e48006cecd30a375d72e02be29a29f5c2dfab6031","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-09T20:26:30Z","title_canon_sha256":"3f9a37124008e1905db319bd338cb34d04e2769d42d92f17f134869db35d3d6b"},"schema_version":"1.0","source":{"id":"2502.06020","kind":"arxiv","version":1}},"canonical_sha256":"572c8132165314ebabe88f24bec6319889e7ec9927c77b48423711b2cdda4738","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"572c8132165314ebabe88f24bec6319889e7ec9927c77b48423711b2cdda4738","first_computed_at":"2026-07-05T10:11:46.551198Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:46.551198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0ML5Qk2rf07T8CxyCvRREBEACbaLeNkNItEAp2NQBgkvdLpei0SJ3IokDtnGRi5RxIweWWGVlg9dY4MfjXEQCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:46.551778Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06020","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31a37ccba225e53f00064c28bda6304359363ef4773e79bc033f0ad73cb04fe8","sha256:fef50bc90a5e81956bffedbc2cd8fa5e405c4c0309a7c900fa99e3978e560f89"],"state_sha256":"ad1c03a352d957960133a4ef4fccc5625ce49b05debcb8d9ad9ef58793dd1458"}