{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XFCETSF42W5T3N4RNUNIYKI7A4","short_pith_number":"pith:XFCETSF4","schema_version":"1.0","canonical_sha256":"b94449c8bcd5bb3db7916d1a8c291f07119b44a9dd48fcd99198f8cb098df5fc","source":{"kind":"arxiv","id":"2311.15075","version":1},"attestation_state":"computed","paper":{"title":"Mug-STAN: Adapting Image-Language Pretrained Models for General Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ge Li, Jingjia Huang, Ruyang Liu, Thomas H. Li, Wei Gao","submitted_at":"2023-11-25T17:01:38Z","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"},"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":"2311.15075","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-25T17:01:38Z","cross_cats_sorted":[],"title_canon_sha256":"0983ee3e1db9e425c3c3b9d6b601f1ed14f34e3fa6193ec6a57b00901766854e","abstract_canon_sha256":"9a84a67df43eb8b243a10e419366bf9a576078eb8002b71078c070bfff4bfa87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:58.562470Z","signature_b64":"uXeX0bKLt2gh2MMQMRygddI3jNtD61N6i7r6vb3NrVLdXcAyVs2bFF1ZAspW0w5Y5ZuJAT5eIpX4hZENCiTfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b94449c8bcd5bb3db7916d1a8c291f07119b44a9dd48fcd99198f8cb098df5fc","last_reissued_at":"2026-07-05T07:16:58.562106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:58.562106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mug-STAN: Adapting Image-Language Pretrained Models for General Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ge Li, Jingjia Huang, Ruyang Liu, Thomas H. Li, Wei Gao","submitted_at":"2023-11-25T17:01:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15075","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/2311.15075/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":"2311.15075","created_at":"2026-07-05T07:16:58.562159+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.15075v1","created_at":"2026-07-05T07:16:58.562159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15075","created_at":"2026-07-05T07:16:58.562159+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFCETSF42W5T","created_at":"2026-07-05T07:16:58.562159+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFCETSF42W5T3N4R","created_at":"2026-07-05T07:16:58.562159+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFCETSF4","created_at":"2026-07-05T07:16:58.562159+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20518","citing_title":"T2VParser: Adaptive Decomposition Tokens for Partial Alignment in Text to Video Retrieval","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XFCETSF42W5T3N4RNUNIYKI7A4","json":"https://pith.science/pith/XFCETSF42W5T3N4RNUNIYKI7A4.json","graph_json":"https://pith.science/api/pith-number/XFCETSF42W5T3N4RNUNIYKI7A4/graph.json","events_json":"https://pith.science/api/pith-number/XFCETSF42W5T3N4RNUNIYKI7A4/events.json","paper":"https://pith.science/paper/XFCETSF4"},"agent_actions":{"view_html":"https://pith.science/pith/XFCETSF42W5T3N4RNUNIYKI7A4","download_json":"https://pith.science/pith/XFCETSF42W5T3N4RNUNIYKI7A4.json","view_paper":"https://pith.science/paper/XFCETSF4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.15075&json=true","fetch_graph":"https://pith.science/api/pith-number/XFCETSF42W5T3N4RNUNIYKI7A4/graph.json","fetch_events":"https://pith.science/api/pith-number/XFCETSF42W5T3N4RNUNIYKI7A4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFCETSF42W5T3N4RNUNIYKI7A4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFCETSF42W5T3N4RNUNIYKI7A4/action/storage_attestation","attest_author":"https://pith.science/pith/XFCETSF42W5T3N4RNUNIYKI7A4/action/author_attestation","sign_citation":"https://pith.science/pith/XFCETSF42W5T3N4RNUNIYKI7A4/action/citation_signature","submit_replication":"https://pith.science/pith/XFCETSF42W5T3N4RNUNIYKI7A4/action/replication_record"}},"created_at":"2026-07-05T07:16:58.562159+00:00","updated_at":"2026-07-05T07:16:58.562159+00:00"}