{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AV3NOVACW4D3544W4XS3RNI27F","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":"6934e50ed98be866f56a9450e2fc8ed9cc91a6f511d0e8796e6fe0651a2cb2d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-05T19:03:58Z","title_canon_sha256":"893b695f68d473fae93fb6a3375a3faabd56dc9dae65b7275cba52d2a3050eed"},"schema_version":"1.0","source":{"id":"2502.03549","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03549","created_at":"2026-07-05T10:11:33Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03549v3","created_at":"2026-07-05T10:11:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03549","created_at":"2026-07-05T10:11:33Z"},{"alias_kind":"pith_short_12","alias_value":"AV3NOVACW4D3","created_at":"2026-07-05T10:11:33Z"},{"alias_kind":"pith_short_16","alias_value":"AV3NOVACW4D3544W","created_at":"2026-07-05T10:11:33Z"},{"alias_kind":"pith_short_8","alias_value":"AV3NOVAC","created_at":"2026-07-05T10:11:33Z"}],"graph_snapshots":[{"event_id":"sha256:75809ab4414772c7ce906aff77ca0cc5a87c37ff7f0ed49f814d7b413ec9d029","target":"graph","created_at":"2026-07-05T10:11:33Z","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/2502.03549/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive language-image pretraining (CLIP) has significantly advanced image-based vision learning. A pressing topic subsequently arises: how can we effectively adapt CLIP to the video domain? Recent studies have focused on adjusting either the textual or visual branch of CLIP for action recognition. However, we argue that adaptations of both branches are crucial. In this paper, we propose \\textbf{CLAVER}: a \\textbf{C}ontrastive \\textbf{L}anguage-\\textbf{A}ction \\textbf{V}ideo Learn\\textbf{er}, designed to shift CLIP's focus from the alignment of static visual objects and concrete nouns to t","authors_text":"Hui Li, Jia He, Jingyi Yang, Xiuming Ni, Zitong Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-05T19:03:58Z","title":"Kronecker Mask and Interpretive Prompts are Language-Action Video Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03549","kind":"arxiv","version":3},"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:eb086ce35f64b8425c4d2d0734fcfbfa064e5718ca174f87ba0a60f1ff6b5fd9","target":"record","created_at":"2026-07-05T10:11:33Z","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":"6934e50ed98be866f56a9450e2fc8ed9cc91a6f511d0e8796e6fe0651a2cb2d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-05T19:03:58Z","title_canon_sha256":"893b695f68d473fae93fb6a3375a3faabd56dc9dae65b7275cba52d2a3050eed"},"schema_version":"1.0","source":{"id":"2502.03549","kind":"arxiv","version":3}},"canonical_sha256":"0576d75402b707bef396e5e5b8b51af959bd2f1e41c35c90217d2a39eac4fdc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0576d75402b707bef396e5e5b8b51af959bd2f1e41c35c90217d2a39eac4fdc7","first_computed_at":"2026-07-05T10:11:33.365415Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:33.365415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z1/sGT/OknvcFivY5vYvRzERPGClhC+hxsnjLC5qsM+QKhho4hP2IgLmvVoM/wYfhdR4H1mJe1F5EBjHTYopAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:33.365929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.03549","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb086ce35f64b8425c4d2d0734fcfbfa064e5718ca174f87ba0a60f1ff6b5fd9","sha256:75809ab4414772c7ce906aff77ca0cc5a87c37ff7f0ed49f814d7b413ec9d029"],"state_sha256":"a992f702fcaa18888de6b2f5137c9d1833e0953def1e647e8f6848b80a175b94"}