{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6TR7CJMUYHMRIDTENM7S3BUZDH","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":"c7dcf778d9b7c6616366801d5b44be011c10b43d9547f9b4b00864bfcfa6e39c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-08T07:03:31Z","title_canon_sha256":"63f93a7cca5cc4cf04cef9a9ec87457b8d73c7045e0788b26d28df87a362f29f"},"schema_version":"1.0","source":{"id":"2210.03941","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03941","created_at":"2026-07-05T05:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03941v1","created_at":"2026-07-05T05:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03941","created_at":"2026-07-05T05:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"6TR7CJMUYHMR","created_at":"2026-07-05T05:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"6TR7CJMUYHMRIDTE","created_at":"2026-07-05T05:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"6TR7CJMU","created_at":"2026-07-05T05:04:34Z"}],"graph_snapshots":[{"event_id":"sha256:25ccad84b4a81bde50dec3719c3ff326dc95a76ec922f2295705ca745db9a58b","target":"graph","created_at":"2026-07-05T05:04:34Z","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/2210.03941/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While recent large-scale video-language pre-training made great progress in video question answering, the design of spatial modeling of video-language models is less fine-grained than that of image-language models; existing practices of temporal modeling also suffer from weak and noisy alignment between modalities. To learn fine-grained visual understanding, we decouple spatial-temporal modeling and propose a hybrid pipeline, Decoupled Spatial-Temporal Encoders, integrating an image- and a video-language encoder. The former encodes spatial semantics from larger but sparsely sampled frames inde","authors_text":"Bing-Chen Tsai, Hsin-Ying Lee, Hung-Ting Su, Jia-Fong Yeh, Tsung-Han Wu, Winston H. Hsu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-08T07:03:31Z","title":"Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03941","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":"sha256:904171ff4928278be87f11f4c7983d9e38e2b672daf6d4b8d4fcab9adcf17902","target":"record","created_at":"2026-07-05T05:04:34Z","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":"c7dcf778d9b7c6616366801d5b44be011c10b43d9547f9b4b00864bfcfa6e39c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-08T07:03:31Z","title_canon_sha256":"63f93a7cca5cc4cf04cef9a9ec87457b8d73c7045e0788b26d28df87a362f29f"},"schema_version":"1.0","source":{"id":"2210.03941","kind":"arxiv","version":1}},"canonical_sha256":"f4e3f12594c1d9140e646b3f2d869919cf02115f8a5ed264c7b277919c376f73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4e3f12594c1d9140e646b3f2d869919cf02115f8a5ed264c7b277919c376f73","first_computed_at":"2026-07-05T05:04:34.118198Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:34.118198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M48uT3snIDRp82thrACQfrG1HTOudO0aVjZIfhBIRryFCgGsNqu5s2G05n4E7m5MagyItIvdIsrWoHFNUrJgAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:34.118627Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.03941","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:904171ff4928278be87f11f4c7983d9e38e2b672daf6d4b8d4fcab9adcf17902","sha256:25ccad84b4a81bde50dec3719c3ff326dc95a76ec922f2295705ca745db9a58b"],"state_sha256":"b80d108c1bb4df28c57923cb8a121e6e62f226f1bca6cb84cd316234ee3adc79"}