{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PP7CSRQTIBLQSS3NPL74Y76RQZ","short_pith_number":"pith:PP7CSRQT","canonical_record":{"source":{"id":"2302.03024","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-06T18:59:17Z","cross_cats_sorted":[],"title_canon_sha256":"1cf05c3cc75eb398c1192014898e2495cfacef87785890d6aed43c73881140a9","abstract_canon_sha256":"ec5cd3febe31f5521df63147f64a617e357acf4f7737dc7fa6fa0a7d59014c15"},"schema_version":"1.0"},"canonical_sha256":"7bfe2946134057094b6d7affcc7fd1865a0ae7dd9a1db390dae0245286585c11","source":{"kind":"arxiv","id":"2302.03024","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.03024","created_at":"2026-07-05T05:39:09Z"},{"alias_kind":"arxiv_version","alias_value":"2302.03024v1","created_at":"2026-07-05T05:39:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03024","created_at":"2026-07-05T05:39:09Z"},{"alias_kind":"pith_short_12","alias_value":"PP7CSRQTIBLQ","created_at":"2026-07-05T05:39:09Z"},{"alias_kind":"pith_short_16","alias_value":"PP7CSRQTIBLQSS3N","created_at":"2026-07-05T05:39:09Z"},{"alias_kind":"pith_short_8","alias_value":"PP7CSRQT","created_at":"2026-07-05T05:39:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PP7CSRQTIBLQSS3NPL74Y76RQZ","target":"record","payload":{"canonical_record":{"source":{"id":"2302.03024","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-06T18:59:17Z","cross_cats_sorted":[],"title_canon_sha256":"1cf05c3cc75eb398c1192014898e2495cfacef87785890d6aed43c73881140a9","abstract_canon_sha256":"ec5cd3febe31f5521df63147f64a617e357acf4f7737dc7fa6fa0a7d59014c15"},"schema_version":"1.0"},"canonical_sha256":"7bfe2946134057094b6d7affcc7fd1865a0ae7dd9a1db390dae0245286585c11","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:39:09.183552Z","signature_b64":"U/H+SNK8e5szrSsBMV1fzgZWOS5l1nXWx+Hw7MMOXlTFcWuXFO2S7WNbUV4/W0k8br8U/4SzxjWLKnPtdDMmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bfe2946134057094b6d7affcc7fd1865a0ae7dd9a1db390dae0245286585c11","last_reissued_at":"2026-07-05T05:39:09.183070Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:39:09.183070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.03024","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":"2026-07-05T05:39:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9L1a4XPi9LkVjAypgJZHRlsYmaadvDVdgXbVJyeFnPCOzDpnwF9KWlaGhSu0lgpf1fE8mwK+ToVzf4vH7GRUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T07:25:20.125741Z"},"content_sha256":"fc67ae8b684c69ac0c73c635ff2003aee62468411caf2a6c72a8d6679c0b2d3f","schema_version":"1.0","event_id":"sha256:fc67ae8b684c69ac0c73c635ff2003aee62468411caf2a6c72a8d6679c0b2d3f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PP7CSRQTIBLQSS3NPL74Y76RQZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AIM: Adapting Image Models for Efficient Video Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aston Zhang, Chen Chen, Mu Li, Taojiannan Yang, Yi Zhu, Yusheng Xie","submitted_at":"2023-02-06T18:59:17Z","abstract_excerpt":"Recent vision transformer based video models mostly follow the ``image pre-training then finetuning\" paradigm and have achieved great success on multiple video benchmarks. However, full finetuning such a video model could be computationally expensive and unnecessary, given the pre-trained image transformer models have demonstrated exceptional transferability. In this work, we propose a novel method to Adapt pre-trained Image Models (AIM) for efficient video understanding. By freezing the pre-trained image model and adding a few lightweight Adapters, we introduce spatial adaptation, temporal ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03024","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/2302.03024/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":"2026-07-05T05:39:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"85I9FhnwGVbA46rHiQdbWP6h/7VcTn8AtG6l27we3qwfcsjVVNjnvFTmugmqd+sbXy3BVyEpFdfX6vV+3GMhBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T07:25:20.126144Z"},"content_sha256":"0cbe87e121bcdb31aef3c75732212a93eefc0d8271a4fd6082f82969074e9e6b","schema_version":"1.0","event_id":"sha256:0cbe87e121bcdb31aef3c75732212a93eefc0d8271a4fd6082f82969074e9e6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PP7CSRQTIBLQSS3NPL74Y76RQZ/bundle.json","state_url":"https://pith.science/pith/PP7CSRQTIBLQSS3NPL74Y76RQZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PP7CSRQTIBLQSS3NPL74Y76RQZ/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":"2026-07-10T07:25:20Z","links":{"resolver":"https://pith.science/pith/PP7CSRQTIBLQSS3NPL74Y76RQZ","bundle":"https://pith.science/pith/PP7CSRQTIBLQSS3NPL74Y76RQZ/bundle.json","state":"https://pith.science/pith/PP7CSRQTIBLQSS3NPL74Y76RQZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PP7CSRQTIBLQSS3NPL74Y76RQZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PP7CSRQTIBLQSS3NPL74Y76RQZ","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":"ec5cd3febe31f5521df63147f64a617e357acf4f7737dc7fa6fa0a7d59014c15","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-06T18:59:17Z","title_canon_sha256":"1cf05c3cc75eb398c1192014898e2495cfacef87785890d6aed43c73881140a9"},"schema_version":"1.0","source":{"id":"2302.03024","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.03024","created_at":"2026-07-05T05:39:09Z"},{"alias_kind":"arxiv_version","alias_value":"2302.03024v1","created_at":"2026-07-05T05:39:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03024","created_at":"2026-07-05T05:39:09Z"},{"alias_kind":"pith_short_12","alias_value":"PP7CSRQTIBLQ","created_at":"2026-07-05T05:39:09Z"},{"alias_kind":"pith_short_16","alias_value":"PP7CSRQTIBLQSS3N","created_at":"2026-07-05T05:39:09Z"},{"alias_kind":"pith_short_8","alias_value":"PP7CSRQT","created_at":"2026-07-05T05:39:09Z"}],"graph_snapshots":[{"event_id":"sha256:0cbe87e121bcdb31aef3c75732212a93eefc0d8271a4fd6082f82969074e9e6b","target":"graph","created_at":"2026-07-05T05:39:09Z","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/2302.03024/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent vision transformer based video models mostly follow the ``image pre-training then finetuning\" paradigm and have achieved great success on multiple video benchmarks. However, full finetuning such a video model could be computationally expensive and unnecessary, given the pre-trained image transformer models have demonstrated exceptional transferability. In this work, we propose a novel method to Adapt pre-trained Image Models (AIM) for efficient video understanding. By freezing the pre-trained image model and adding a few lightweight Adapters, we introduce spatial adaptation, temporal ad","authors_text":"Aston Zhang, Chen Chen, Mu Li, Taojiannan Yang, Yi Zhu, Yusheng Xie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-06T18:59:17Z","title":"AIM: Adapting Image Models for Efficient Video Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03024","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:fc67ae8b684c69ac0c73c635ff2003aee62468411caf2a6c72a8d6679c0b2d3f","target":"record","created_at":"2026-07-05T05:39:09Z","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":"ec5cd3febe31f5521df63147f64a617e357acf4f7737dc7fa6fa0a7d59014c15","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-06T18:59:17Z","title_canon_sha256":"1cf05c3cc75eb398c1192014898e2495cfacef87785890d6aed43c73881140a9"},"schema_version":"1.0","source":{"id":"2302.03024","kind":"arxiv","version":1}},"canonical_sha256":"7bfe2946134057094b6d7affcc7fd1865a0ae7dd9a1db390dae0245286585c11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bfe2946134057094b6d7affcc7fd1865a0ae7dd9a1db390dae0245286585c11","first_computed_at":"2026-07-05T05:39:09.183070Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:39:09.183070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U/H+SNK8e5szrSsBMV1fzgZWOS5l1nXWx+Hw7MMOXlTFcWuXFO2S7WNbUV4/W0k8br8U/4SzxjWLKnPtdDMmBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:39:09.183552Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.03024","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc67ae8b684c69ac0c73c635ff2003aee62468411caf2a6c72a8d6679c0b2d3f","sha256:0cbe87e121bcdb31aef3c75732212a93eefc0d8271a4fd6082f82969074e9e6b"],"state_sha256":"33797c0a2bf42bc968238a9f7fdbbe79f6d47ec429d2f5e3d63c142eb3a86172"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1SYU35iM7bMNNosaB4ySWU7/TxdcZEb0PooS4///PHwYcsv/4M+b701FdyHqfv+3KmwnJxK322LW9JnPpskXDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T07:25:20.128213Z","bundle_sha256":"f55f7482bfd35dae40e2fc1bdab75406a69dffd567153c18d05a6b989d3ecc4a"}}