{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z7C3CXXBSSKN5KMHDVSG2CPN4Y","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":"e4532e9acc45c5b38bdc1110fd230d4786b98dc6f5413c1a7887bb2fddba461a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T12:01:22Z","title_canon_sha256":"d92c52ca535dcdd7274cd1821ccb91061e1403c7c66f1ebb37e4721851274be5"},"schema_version":"1.0","source":{"id":"2408.06840","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06840","created_at":"2026-07-05T08:55:10Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06840v2","created_at":"2026-07-05T08:55:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06840","created_at":"2026-07-05T08:55:10Z"},{"alias_kind":"pith_short_12","alias_value":"Z7C3CXXBSSKN","created_at":"2026-07-05T08:55:10Z"},{"alias_kind":"pith_short_16","alias_value":"Z7C3CXXBSSKN5KMH","created_at":"2026-07-05T08:55:10Z"},{"alias_kind":"pith_short_8","alias_value":"Z7C3CXXB","created_at":"2026-07-05T08:55:10Z"}],"graph_snapshots":[{"event_id":"sha256:ab0bb8f4de4151e78fb950fd4d5ca2eb32812959f8be994b5ce54f4f7e5d3518","target":"graph","created_at":"2026-07-05T08:55:10Z","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/2408.06840/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, the remarkable success of pre-trained Vision Transformers (ViTs) from image-text matching has sparked an interest in image-to-video adaptation. However, most current approaches retain the full forward pass for each frame, leading to a high computation overhead for processing entire videos. In this paper, we present InTI, a novel approach for compressive image-to-video adaptation using dynamic Inter-frame Token Interpolation. InTI aims to softly preserve the informative tokens without disrupting their coherent spatiotemporal structure. Specifically, each token pair at identical positi","authors_text":"Guozhen Zhang, Jingyu Liu, Kai Ma, Kevin Zhao, Limin Wang, Shengming Cao, Xiaotong Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T12:01:22Z","title":"Dynamic and Compressive Adaptation of Transformers From Images to Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06840","kind":"arxiv","version":2},"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:e408cfa34fd2967d942c8157fc446a4dd7a17c85f3d8eb805686cef78a62e9c7","target":"record","created_at":"2026-07-05T08:55:10Z","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":"e4532e9acc45c5b38bdc1110fd230d4786b98dc6f5413c1a7887bb2fddba461a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T12:01:22Z","title_canon_sha256":"d92c52ca535dcdd7274cd1821ccb91061e1403c7c66f1ebb37e4721851274be5"},"schema_version":"1.0","source":{"id":"2408.06840","kind":"arxiv","version":2}},"canonical_sha256":"cfc5b15ee19494dea9871d646d09ede6233ac76d631b3661e5ab7000e54d7564","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfc5b15ee19494dea9871d646d09ede6233ac76d631b3661e5ab7000e54d7564","first_computed_at":"2026-07-05T08:55:10.342296Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:10.342296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u8m/WxuMCkxNW0kcqXsnwFBTIA5hq3UdmiGiH0CgsR9S4aacX8OPOtmZv6KTepLEJm4Jfr2cYLMMcGvvNNi4Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:10.342751Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.06840","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e408cfa34fd2967d942c8157fc446a4dd7a17c85f3d8eb805686cef78a62e9c7","sha256:ab0bb8f4de4151e78fb950fd4d5ca2eb32812959f8be994b5ce54f4f7e5d3518"],"state_sha256":"2a91051e1d614b8f95b9076d72cedf8b06d7f6d625832313400abcbc3b7192df"}