{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QG3BO2JJKFGNNP3HOEWMLEPYQQ","short_pith_number":"pith:QG3BO2JJ","canonical_record":{"source":{"id":"2311.15769","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T12:39:42Z","cross_cats_sorted":[],"title_canon_sha256":"5280f8b5c86db9a47423df759a73f15a76de2ca9cb498d39dde0a9ed330f5e89","abstract_canon_sha256":"28c39751c53ed49b0c79292a38d0220e0f5fa3de3e50d6ee54ec065ade2359f6"},"schema_version":"1.0"},"canonical_sha256":"81b6176929514cd6bf67712cc591f8843d5f2b006c12ca6f795f43f594ea88ec","source":{"kind":"arxiv","id":"2311.15769","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.15769","created_at":"2026-07-05T07:17:09Z"},{"alias_kind":"arxiv_version","alias_value":"2311.15769v1","created_at":"2026-07-05T07:17:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15769","created_at":"2026-07-05T07:17:09Z"},{"alias_kind":"pith_short_12","alias_value":"QG3BO2JJKFGN","created_at":"2026-07-05T07:17:09Z"},{"alias_kind":"pith_short_16","alias_value":"QG3BO2JJKFGNNP3H","created_at":"2026-07-05T07:17:09Z"},{"alias_kind":"pith_short_8","alias_value":"QG3BO2JJ","created_at":"2026-07-05T07:17:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QG3BO2JJKFGNNP3HOEWMLEPYQQ","target":"record","payload":{"canonical_record":{"source":{"id":"2311.15769","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T12:39:42Z","cross_cats_sorted":[],"title_canon_sha256":"5280f8b5c86db9a47423df759a73f15a76de2ca9cb498d39dde0a9ed330f5e89","abstract_canon_sha256":"28c39751c53ed49b0c79292a38d0220e0f5fa3de3e50d6ee54ec065ade2359f6"},"schema_version":"1.0"},"canonical_sha256":"81b6176929514cd6bf67712cc591f8843d5f2b006c12ca6f795f43f594ea88ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:09.147835Z","signature_b64":"QEM0K11wnTt7jemyStFUJJqLUCOoFFXgM/XSiDnvQXTkxGqj/gT1JFo7J6QxDV8i84pIdcGWm+ufFcdTIIasAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81b6176929514cd6bf67712cc591f8843d5f2b006c12ca6f795f43f594ea88ec","last_reissued_at":"2026-07-05T07:17:09.147433Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:09.147433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.15769","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":"2026-07-05T07:17:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UQ3Yz3Ay91eu1zzdR1uFboLvej69cVABgWsT3GNSLWvCNtXRRRQa4XPD8FJbG3zbbtmz+9NNCeHA5AgNmno8Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:38:39.411110Z"},"content_sha256":"43d56af471a5603c3be0c56289015ee6b7f865c5f293783ebcc9763039f34a56","schema_version":"1.0","event_id":"sha256:43d56af471a5603c3be0c56289015ee6b7f865c5f293783ebcc9763039f34a56"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QG3BO2JJKFGNNP3HOEWMLEPYQQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huanjin Yao, Wenhao Wu, Zhiheng Li","submitted_at":"2023-11-27T12:39:42Z","abstract_excerpt":"Large pre-trained vision models achieve impressive success in computer vision. However, fully fine-tuning large models for downstream tasks, particularly in video understanding, can be prohibitively computationally expensive. Recent studies turn their focus towards efficient image-to-video transfer learning. Nevertheless, existing efficient fine-tuning methods lack attention to training memory usage and exploration of transferring a larger model to the video domain. In this paper, we present a novel Spatial-Temporal Side Network for memory-efficient fine-tuning large image models to video unde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15769","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/2311.15769/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":"2026-07-05T07:17:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rsjMTq+j4J4bJRBjDvVHXoXtfscirxEg7v1ikWKbUl01Iz2HN5R7vsGlBk1th0HNW4dt1AwbkMkEHkQcRvGKAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:38:39.411519Z"},"content_sha256":"f3de8bf0d3cbc52ff26036f1f70df600048d74f4876548f3f41b5594442bd092","schema_version":"1.0","event_id":"sha256:f3de8bf0d3cbc52ff26036f1f70df600048d74f4876548f3f41b5594442bd092"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QG3BO2JJKFGNNP3HOEWMLEPYQQ/bundle.json","state_url":"https://pith.science/pith/QG3BO2JJKFGNNP3HOEWMLEPYQQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QG3BO2JJKFGNNP3HOEWMLEPYQQ/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":"2026-08-18T16:38:39Z","links":{"resolver":"https://pith.science/pith/QG3BO2JJKFGNNP3HOEWMLEPYQQ","bundle":"https://pith.science/pith/QG3BO2JJKFGNNP3HOEWMLEPYQQ/bundle.json","state":"https://pith.science/pith/QG3BO2JJKFGNNP3HOEWMLEPYQQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QG3BO2JJKFGNNP3HOEWMLEPYQQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QG3BO2JJKFGNNP3HOEWMLEPYQQ","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":"28c39751c53ed49b0c79292a38d0220e0f5fa3de3e50d6ee54ec065ade2359f6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T12:39:42Z","title_canon_sha256":"5280f8b5c86db9a47423df759a73f15a76de2ca9cb498d39dde0a9ed330f5e89"},"schema_version":"1.0","source":{"id":"2311.15769","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.15769","created_at":"2026-07-05T07:17:09Z"},{"alias_kind":"arxiv_version","alias_value":"2311.15769v1","created_at":"2026-07-05T07:17:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15769","created_at":"2026-07-05T07:17:09Z"},{"alias_kind":"pith_short_12","alias_value":"QG3BO2JJKFGN","created_at":"2026-07-05T07:17:09Z"},{"alias_kind":"pith_short_16","alias_value":"QG3BO2JJKFGNNP3H","created_at":"2026-07-05T07:17:09Z"},{"alias_kind":"pith_short_8","alias_value":"QG3BO2JJ","created_at":"2026-07-05T07:17:09Z"}],"graph_snapshots":[{"event_id":"sha256:f3de8bf0d3cbc52ff26036f1f70df600048d74f4876548f3f41b5594442bd092","target":"graph","created_at":"2026-07-05T07:17:09Z","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/2311.15769/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large pre-trained vision models achieve impressive success in computer vision. However, fully fine-tuning large models for downstream tasks, particularly in video understanding, can be prohibitively computationally expensive. Recent studies turn their focus towards efficient image-to-video transfer learning. Nevertheless, existing efficient fine-tuning methods lack attention to training memory usage and exploration of transferring a larger model to the video domain. In this paper, we present a novel Spatial-Temporal Side Network for memory-efficient fine-tuning large image models to video unde","authors_text":"Huanjin Yao, Wenhao Wu, Zhiheng Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T12:39:42Z","title":"Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15769","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":"sha256:43d56af471a5603c3be0c56289015ee6b7f865c5f293783ebcc9763039f34a56","target":"record","created_at":"2026-07-05T07:17:09Z","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":"28c39751c53ed49b0c79292a38d0220e0f5fa3de3e50d6ee54ec065ade2359f6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T12:39:42Z","title_canon_sha256":"5280f8b5c86db9a47423df759a73f15a76de2ca9cb498d39dde0a9ed330f5e89"},"schema_version":"1.0","source":{"id":"2311.15769","kind":"arxiv","version":1}},"canonical_sha256":"81b6176929514cd6bf67712cc591f8843d5f2b006c12ca6f795f43f594ea88ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81b6176929514cd6bf67712cc591f8843d5f2b006c12ca6f795f43f594ea88ec","first_computed_at":"2026-07-05T07:17:09.147433Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:17:09.147433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QEM0K11wnTt7jemyStFUJJqLUCOoFFXgM/XSiDnvQXTkxGqj/gT1JFo7J6QxDV8i84pIdcGWm+ufFcdTIIasAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:17:09.147835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.15769","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43d56af471a5603c3be0c56289015ee6b7f865c5f293783ebcc9763039f34a56","sha256:f3de8bf0d3cbc52ff26036f1f70df600048d74f4876548f3f41b5594442bd092"],"state_sha256":"bebdc35e666862f8cd8049347812e36731fafd11f7a03c7ab8cde844017d14fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AEEcEQrbOel5b/9o4kDRqIlHLzDFrWL+2+ylbTqIyPnV6dyF1f6lw9cAU6Zt7NmJQkt9q1mTCwU6et7KhCaUCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T16:38:39.415812Z","bundle_sha256":"9f33b11d0d39d6790342f014b6dc1f2b1720ce3ea4f406dd9e1aefc529062b5a"}}