{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TY2Y63SKEL6ZEIMI5MOHEX655M","short_pith_number":"pith:TY2Y63SK","schema_version":"1.0","canonical_sha256":"9e358f6e4a22fd922188eb1c725fddeb1b2fd435cb764d0413dc644c43a6a281","source":{"kind":"arxiv","id":"2608.04302","version":1},"attestation_state":"computed","paper":{"title":"CLIP-CC-Bench: Evaluating Paragraph-Level Video Descriptions in Video-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chulwoo Pack, Harsh Dubey, Mukhtiar Ali, Sugam Mishra","submitted_at":"2026-08-05T00:20:23Z","abstract_excerpt":"Benchmarking video-language models has largely focused on short clips and single-sentence metrics, leaving open whether current systems can generate accurate long-form, paragraph-level descriptions. We introduce CLIP-CC-Bench, an evaluation suite for long-form video description built from 5 hours of movie content segmented into 90-second clips, each paired with an expert-written paragraph-style reference. The evaluation suite employs an ensemble of five state-of-the-art LLM-based embedding models to increase reliability and mitigate single-model bias, and applies two complementary methodologie"},"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":"2608.04302","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T00:20:23Z","cross_cats_sorted":["cs.IR","cs.MM"],"title_canon_sha256":"0397021e1326d8625ed5fac2500bc1c2e511e1e53285ada5b995e0a28e9a55e2","abstract_canon_sha256":"60107740b01e1b324935709e874c5c21c1eb7f1101e1334c2bfb99aadfaa350c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:32:10.261110Z","signature_b64":"HaQic5NKR6HXeVYYETm85M8EvvPWVd178a+KbwqjBHO8069YDZzf0esQgAFfov35LSae0Yd0knDIxO6ADpAgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e358f6e4a22fd922188eb1c725fddeb1b2fd435cb764d0413dc644c43a6a281","last_reissued_at":"2026-08-06T01:32:10.259562Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:32:10.259562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP-CC-Bench: Evaluating Paragraph-Level Video Descriptions in Video-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chulwoo Pack, Harsh Dubey, Mukhtiar Ali, Sugam Mishra","submitted_at":"2026-08-05T00:20:23Z","abstract_excerpt":"Benchmarking video-language models has largely focused on short clips and single-sentence metrics, leaving open whether current systems can generate accurate long-form, paragraph-level descriptions. We introduce CLIP-CC-Bench, an evaluation suite for long-form video description built from 5 hours of movie content segmented into 90-second clips, each paired with an expert-written paragraph-style reference. The evaluation suite employs an ensemble of five state-of-the-art LLM-based embedding models to increase reliability and mitigate single-model bias, and applies two complementary methodologie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04302","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/2608.04302/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":"2608.04302","created_at":"2026-08-06T01:32:10.261434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04302v1","created_at":"2026-08-06T01:32:10.261434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04302","created_at":"2026-08-06T01:32:10.261434+00:00"},{"alias_kind":"pith_short_12","alias_value":"TY2Y63SKEL6Z","created_at":"2026-08-06T01:32:10.261434+00:00"},{"alias_kind":"pith_short_16","alias_value":"TY2Y63SKEL6ZEIMI","created_at":"2026-08-06T01:32:10.261434+00:00"},{"alias_kind":"pith_short_8","alias_value":"TY2Y63SK","created_at":"2026-08-06T01:32:10.261434+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TY2Y63SKEL6ZEIMI5MOHEX655M","json":"https://pith.science/pith/TY2Y63SKEL6ZEIMI5MOHEX655M.json","graph_json":"https://pith.science/api/pith-number/TY2Y63SKEL6ZEIMI5MOHEX655M/graph.json","events_json":"https://pith.science/api/pith-number/TY2Y63SKEL6ZEIMI5MOHEX655M/events.json","paper":"https://pith.science/paper/TY2Y63SK"},"agent_actions":{"view_html":"https://pith.science/pith/TY2Y63SKEL6ZEIMI5MOHEX655M","download_json":"https://pith.science/pith/TY2Y63SKEL6ZEIMI5MOHEX655M.json","view_paper":"https://pith.science/paper/TY2Y63SK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04302&json=true","fetch_graph":"https://pith.science/api/pith-number/TY2Y63SKEL6ZEIMI5MOHEX655M/graph.json","fetch_events":"https://pith.science/api/pith-number/TY2Y63SKEL6ZEIMI5MOHEX655M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TY2Y63SKEL6ZEIMI5MOHEX655M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TY2Y63SKEL6ZEIMI5MOHEX655M/action/storage_attestation","attest_author":"https://pith.science/pith/TY2Y63SKEL6ZEIMI5MOHEX655M/action/author_attestation","sign_citation":"https://pith.science/pith/TY2Y63SKEL6ZEIMI5MOHEX655M/action/citation_signature","submit_replication":"https://pith.science/pith/TY2Y63SKEL6ZEIMI5MOHEX655M/action/replication_record"}},"created_at":"2026-08-06T01:32:10.261434+00:00","updated_at":"2026-08-06T01:32:10.261434+00:00"}