{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XFCETSF42W5T3N4RNUNIYKI7A4","short_pith_number":"pith:XFCETSF4","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"},"canonical_sha256":"b94449c8bcd5bb3db7916d1a8c291f07119b44a9dd48fcd99198f8cb098df5fc","source":{"kind":"arxiv","id":"2311.15075","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XFCETSF42W5T3N4RNUNIYKI7A4","target":"record","payload":{"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"},"canonical_sha256":"b94449c8bcd5bb3db7916d1a8c291f07119b44a9dd48fcd99198f8cb098df5fc","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"},"source_kind":"arxiv","source_id":"2311.15075","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:16:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0lLLxWQqm88kkX6ePSZvn5RsTzYcgXau2P/D5TWykorc7YhnAK2xt5cWx/nYfu7YPXYde6YsHWhm1SaC9s0jCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:45:07.133277Z"},"content_sha256":"20664113e8e75df5784c52905b518f150fd3dce83da0cbbbf20f01179825d1b5","schema_version":"1.0","event_id":"sha256:20664113e8e75df5784c52905b518f150fd3dce83da0cbbbf20f01179825d1b5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XFCETSF42W5T3N4RNUNIYKI7A4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:16:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DwXfC7RkkRS5vYU4z1bf5xpoPtNnRx3m77xgwFzjX0HDqWgte1cPyXgt38C4zo4QibVqqM+RIhknsIJESQUsBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:45:07.134172Z"},"content_sha256":"e06c21689145765d8b6d7058c75523eaffe5fa06c2babdf6d4b3b1d7ccf1d774","schema_version":"1.0","event_id":"sha256:e06c21689145765d8b6d7058c75523eaffe5fa06c2babdf6d4b3b1d7ccf1d774"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XFCETSF42W5T3N4RNUNIYKI7A4/bundle.json","state_url":"https://pith.science/pith/XFCETSF42W5T3N4RNUNIYKI7A4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XFCETSF42W5T3N4RNUNIYKI7A4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T05:45:07Z","links":{"resolver":"https://pith.science/pith/XFCETSF42W5T3N4RNUNIYKI7A4","bundle":"https://pith.science/pith/XFCETSF42W5T3N4RNUNIYKI7A4/bundle.json","state":"https://pith.science/pith/XFCETSF42W5T3N4RNUNIYKI7A4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XFCETSF42W5T3N4RNUNIYKI7A4/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VvVFdnB891mLdnlLN8kM3zjS++I4isTVQExrMZkFAXLk8poTHnIl2nKUKRlolVJRQaBEEhazhWxe4CjcsXgvBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T05:45:07.205969Z","bundle_sha256":"a70c78ffeb18c8d1a3f9eead469aad910a0bc660e43fe9881ab92fc7bc6b28ba"}}