{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M2PM7S4SZ75Z3XDBH4JQTVQTT6","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":"fcf55014ddd655a0fdba291419de19c02fc86c757bbc8ee9eb96c0c5f3f697a1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-15T13:27:34Z","title_canon_sha256":"cc1a6fb1c5ac00d0faf988973ce6182c2bea4053866cde41ec058787425ec585"},"schema_version":"1.0","source":{"id":"2401.07669","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.07669","created_at":"2026-05-27T01:04:46Z"},{"alias_kind":"arxiv_version","alias_value":"2401.07669v3","created_at":"2026-05-27T01:04:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07669","created_at":"2026-05-27T01:04:46Z"},{"alias_kind":"pith_short_12","alias_value":"M2PM7S4SZ75Z","created_at":"2026-05-27T01:04:46Z"},{"alias_kind":"pith_short_16","alias_value":"M2PM7S4SZ75Z3XDB","created_at":"2026-05-27T01:04:46Z"},{"alias_kind":"pith_short_8","alias_value":"M2PM7S4S","created_at":"2026-05-27T01:04:46Z"}],"graph_snapshots":[{"event_id":"sha256:e33c4bb1cf3c557c99a61b5337368c813fbcfa3b98b4f36bd6c2aeb9011bf40f","target":"graph","created_at":"2026-05-27T01:04:46Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"simple contrastive finetuning on a mere 23k video-caption pairs is adequate to learn powerful, transferable representations applicable across a diverse range of video understanding tasks that require varying levels of perceptual granularity"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that rule-based captions generated from SRL annotations supply a sufficiently rich and holistic learning signal compared with the sparse narrations found in large-scale video datasets."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SRL-CLIP uses rule-based captions derived from semantic role labels to adapt CLIP via contrastive fine-tuning on 23k pairs, matching or exceeding larger models trained on far more data across video tasks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Structured semantic role label captions let CLIP adapt to video tasks with only 23k pairs."}],"snapshot_sha256":"ba2ebc07fb3a874cbe15b8e8c4fd5e320f52630e60c333fc2363c5cc1484a372"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.07669/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adapting CLIP for videos has gained popularity due to its semantic and rich representation. While CLIP is a good starting point, it typically undergoes post-pretraining (contrastive finetuning) on large video narration or caption datasets (e.g. HowTo100M, WebVid2.5M). However, such narrations or captions often lack comprehensive information needed to represent a video holistically. As the learning signal from text is sparse, the visual learning is inefficient and adaptation requires millions of samples to post-pretrain. In this work, we ask: is it possible to efficiently adapt CLIP for general","authors_text":"Darshan Singh, Makarand Tapaswi, Zeeshan Khan","cross_cats":[],"headline":"Structured semantic role label captions let CLIP adapt to video tasks with only 23k pairs.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-15T13:27:34Z","title":"SRL-CLIP: Efficient CLIP Video Adaptation via Structured Semantic Role Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07669","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-24T04:44:46.609542Z","id":"0874eff8-3e60-4cab-a376-c3686baea2de","model_set":{"reader":"grok-4.3"},"one_line_summary":"SRL-CLIP uses rule-based captions derived from semantic role labels to adapt CLIP via contrastive fine-tuning on 23k pairs, matching or exceeding larger models trained on far more data across video tasks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Structured semantic role label captions let CLIP adapt to video tasks with only 23k pairs.","strongest_claim":"simple contrastive finetuning on a mere 23k video-caption pairs is adequate to learn powerful, transferable representations applicable across a diverse range of video understanding tasks that require varying levels of perceptual granularity","weakest_assumption":"The assumption that rule-based captions generated from SRL annotations supply a sufficiently rich and holistic learning signal compared with the sparse narrations found in large-scale video datasets."}},"verdict_id":"0874eff8-3e60-4cab-a376-c3686baea2de"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c8a04754e040046c2859e47beb233540e817fb0e79364b24319660d4a92d8c0d","target":"record","created_at":"2026-05-27T01:04:46Z","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":"fcf55014ddd655a0fdba291419de19c02fc86c757bbc8ee9eb96c0c5f3f697a1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-15T13:27:34Z","title_canon_sha256":"cc1a6fb1c5ac00d0faf988973ce6182c2bea4053866cde41ec058787425ec585"},"schema_version":"1.0","source":{"id":"2401.07669","kind":"arxiv","version":3}},"canonical_sha256":"669ecfcb92cffb9ddc613f1309d6139fafb6b2dda89137fe5bc30b948fe25d20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"669ecfcb92cffb9ddc613f1309d6139fafb6b2dda89137fe5bc30b948fe25d20","first_computed_at":"2026-05-27T01:04:46.725046Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:04:46.725046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3cvgGHN1Hlvge7IcBSeREP+CfZEG3Ya9meXYdyQf/VxyCLT9nc6oPCZ4vBnXZfW9u/CUe2SE8QGM46nwWk8MBA==","signature_status":"signed_v1","signed_at":"2026-05-27T01:04:46.725740Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.07669","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8a04754e040046c2859e47beb233540e817fb0e79364b24319660d4a92d8c0d","sha256:e33c4bb1cf3c557c99a61b5337368c813fbcfa3b98b4f36bd6c2aeb9011bf40f"],"state_sha256":"a39b21b077113543188e3cc3d5854f7d99d9dc6188591aed31e950b7ae63207b"}