{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M2PM7S4SZ75Z3XDBH4JQTVQTT6","short_pith_number":"pith:M2PM7S4S","schema_version":"1.0","canonical_sha256":"669ecfcb92cffb9ddc613f1309d6139fafb6b2dda89137fe5bc30b948fe25d20","source":{"kind":"arxiv","id":"2401.07669","version":3},"attestation_state":"computed","paper":{"title":"SRL-CLIP: Efficient CLIP Video Adaptation via Structured Semantic Role Labels","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Structured semantic role label captions let CLIP adapt to video tasks with only 23k pairs.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Darshan Singh, Makarand Tapaswi, Zeeshan Khan","submitted_at":"2024-01-15T13:27:34Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.07669","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-15T13:27:34Z","cross_cats_sorted":[],"title_canon_sha256":"cc1a6fb1c5ac00d0faf988973ce6182c2bea4053866cde41ec058787425ec585","abstract_canon_sha256":"fcf55014ddd655a0fdba291419de19c02fc86c757bbc8ee9eb96c0c5f3f697a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:04:46.725740Z","signature_b64":"3cvgGHN1Hlvge7IcBSeREP+CfZEG3Ya9meXYdyQf/VxyCLT9nc6oPCZ4vBnXZfW9u/CUe2SE8QGM46nwWk8MBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"669ecfcb92cffb9ddc613f1309d6139fafb6b2dda89137fe5bc30b948fe25d20","last_reissued_at":"2026-05-27T01:04:46.725046Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:04:46.725046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SRL-CLIP: Efficient CLIP Video Adaptation via Structured Semantic Role Labels","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Structured semantic role label captions let CLIP adapt to video tasks with only 23k pairs.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Darshan Singh, Makarand Tapaswi, Zeeshan Khan","submitted_at":"2024-01-15T13:27:34Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Structured semantic role label captions let CLIP adapt to video tasks with only 23k pairs.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ba2ebc07fb3a874cbe15b8e8c4fd5e320f52630e60c333fc2363c5cc1484a372"},"source":{"id":"2401.07669","kind":"arxiv","version":3},"verdict":{"id":"0874eff8-3e60-4cab-a376-c3686baea2de","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-24T04:44:46.609542Z","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","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","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.","pith_extraction_headline":"Structured semantic role label captions let CLIP adapt to video tasks with only 23k pairs."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.07669/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.07669","created_at":"2026-05-27T01:04:46.725143+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.07669v3","created_at":"2026-05-27T01:04:46.725143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07669","created_at":"2026-05-27T01:04:46.725143+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2PM7S4SZ75Z","created_at":"2026-05-27T01:04:46.725143+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2PM7S4SZ75Z3XDB","created_at":"2026-05-27T01:04:46.725143+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2PM7S4S","created_at":"2026-05-27T01:04:46.725143+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.12335","citing_title":"All in One: A Unified Synthetic Data Pipeline for Multimodal Video Understanding","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M2PM7S4SZ75Z3XDBH4JQTVQTT6","json":"https://pith.science/pith/M2PM7S4SZ75Z3XDBH4JQTVQTT6.json","graph_json":"https://pith.science/api/pith-number/M2PM7S4SZ75Z3XDBH4JQTVQTT6/graph.json","events_json":"https://pith.science/api/pith-number/M2PM7S4SZ75Z3XDBH4JQTVQTT6/events.json","paper":"https://pith.science/paper/M2PM7S4S"},"agent_actions":{"view_html":"https://pith.science/pith/M2PM7S4SZ75Z3XDBH4JQTVQTT6","download_json":"https://pith.science/pith/M2PM7S4SZ75Z3XDBH4JQTVQTT6.json","view_paper":"https://pith.science/paper/M2PM7S4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.07669&json=true","fetch_graph":"https://pith.science/api/pith-number/M2PM7S4SZ75Z3XDBH4JQTVQTT6/graph.json","fetch_events":"https://pith.science/api/pith-number/M2PM7S4SZ75Z3XDBH4JQTVQTT6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2PM7S4SZ75Z3XDBH4JQTVQTT6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2PM7S4SZ75Z3XDBH4JQTVQTT6/action/storage_attestation","attest_author":"https://pith.science/pith/M2PM7S4SZ75Z3XDBH4JQTVQTT6/action/author_attestation","sign_citation":"https://pith.science/pith/M2PM7S4SZ75Z3XDBH4JQTVQTT6/action/citation_signature","submit_replication":"https://pith.science/pith/M2PM7S4SZ75Z3XDBH4JQTVQTT6/action/replication_record"}},"created_at":"2026-05-27T01:04:46.725143+00:00","updated_at":"2026-05-27T01:04:46.725143+00:00"}