{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XFCETSF42W5T3N4RNUNIYKI7A4","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":"9a84a67df43eb8b243a10e419366bf9a576078eb8002b71078c070bfff4bfa87","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-25T17:01:38Z","title_canon_sha256":"0983ee3e1db9e425c3c3b9d6b601f1ed14f34e3fa6193ec6a57b00901766854e"},"schema_version":"1.0","source":{"id":"2311.15075","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.15075","created_at":"2026-07-05T07:16:58Z"},{"alias_kind":"arxiv_version","alias_value":"2311.15075v1","created_at":"2026-07-05T07:16:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15075","created_at":"2026-07-05T07:16:58Z"},{"alias_kind":"pith_short_12","alias_value":"XFCETSF42W5T","created_at":"2026-07-05T07:16:58Z"},{"alias_kind":"pith_short_16","alias_value":"XFCETSF42W5T3N4R","created_at":"2026-07-05T07:16:58Z"},{"alias_kind":"pith_short_8","alias_value":"XFCETSF4","created_at":"2026-07-05T07:16:58Z"}],"graph_snapshots":[{"event_id":"sha256:e06c21689145765d8b6d7058c75523eaffe5fa06c2babdf6d4b3b1d7ccf1d774","target":"graph","created_at":"2026-07-05T07:16:58Z","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/2311.15075/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale image-language pretrained models, e.g., CLIP, have demonstrated remarkable proficiency in acquiring general multi-modal knowledge through web-scale image-text data. Despite the impressive performance of image-language models on various image tasks, how to effectively expand them on general video understanding remains an area of ongoing exploration. In this paper, we investigate the image-to-video transferring from the perspective of the model and the data, unveiling two key obstacles impeding the adaptation of image-language models: non-generalizable temporal modeling and partially","authors_text":"Ge Li, Jingjia Huang, Ruyang Liu, Thomas H. Li, Wei Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-25T17:01:38Z","title":"Mug-STAN: Adapting Image-Language Pretrained Models for General Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15075","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":"sha256:20664113e8e75df5784c52905b518f150fd3dce83da0cbbbf20f01179825d1b5","target":"record","created_at":"2026-07-05T07:16:58Z","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":"9a84a67df43eb8b243a10e419366bf9a576078eb8002b71078c070bfff4bfa87","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-25T17:01:38Z","title_canon_sha256":"0983ee3e1db9e425c3c3b9d6b601f1ed14f34e3fa6193ec6a57b00901766854e"},"schema_version":"1.0","source":{"id":"2311.15075","kind":"arxiv","version":1}},"canonical_sha256":"b94449c8bcd5bb3db7916d1a8c291f07119b44a9dd48fcd99198f8cb098df5fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b94449c8bcd5bb3db7916d1a8c291f07119b44a9dd48fcd99198f8cb098df5fc","first_computed_at":"2026-07-05T07:16:58.562106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:16:58.562106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uXeX0bKLt2gh2MMQMRygddI3jNtD61N6i7r6vb3NrVLdXcAyVs2bFF1ZAspW0w5Y5ZuJAT5eIpX4hZENCiTfDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:16:58.562470Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.15075","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20664113e8e75df5784c52905b518f150fd3dce83da0cbbbf20f01179825d1b5","sha256:e06c21689145765d8b6d7058c75523eaffe5fa06c2babdf6d4b3b1d7ccf1d774"],"state_sha256":"f0ad42a02d0f3e2ad49b5d9f785f13a25258b1ebac3f1996488c1dc9bc399377"}