{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:I4ESWN7YQF27VMPMDWQC245C5I","short_pith_number":"pith:I4ESWN7Y","schema_version":"1.0","canonical_sha256":"47092b37f88175fab1ec1da02d73a2ea17b4aa74a1e6149f6968f1ce1ff160b5","source":{"kind":"arxiv","id":"2605.31029","version":1},"attestation_state":"computed","paper":{"title":"PEEK: Picking Essential frames via Efficient Knowledge distillation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anas Filali Razzouki, Khalil Guetari, Killian Steunou, Moun\\^im A. El-Yacoubi, Yannis Tevissen","submitted_at":"2026-05-29T09:01:56Z","abstract_excerpt":"Video-language models can process only a limited number of frames, making frame selection a key bottleneck for efficient video captioning. Most captioning pipelines still rely on uniform sampling, which is computationally cheap but agnostic to visual content. Adaptive frame sampling has recently emerged as a promising approach for selecting the most informative frames from a video; however, existing methods remain computationally expensive. We introduce PEEK, an efficient dynamic frame sampling method that distills caption-conditioned frame relevance rankings from a stronger teacher model into"},"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":"2605.31029","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T09:01:56Z","cross_cats_sorted":[],"title_canon_sha256":"6a032707ef286ade2f7e48f9ce9a557108e02b117275d5ac9119dc603aadbbe8","abstract_canon_sha256":"1a9c729b0f1df2460c38ca9bc4911f65829b0b54376b4df55605f99449c29c52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:31.646529Z","signature_b64":"FdCwtlUjJjE41EAfRx0SuGWKY/WXzxvUBtTfleX8JWL2yHYrBlrnAGNwRYrfKmjsj9Dd9vqjUwO9igGfwQvsCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47092b37f88175fab1ec1da02d73a2ea17b4aa74a1e6149f6968f1ce1ff160b5","last_reissued_at":"2026-06-01T01:03:31.645586Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:31.645586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PEEK: Picking Essential frames via Efficient Knowledge distillation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anas Filali Razzouki, Khalil Guetari, Killian Steunou, Moun\\^im A. El-Yacoubi, Yannis Tevissen","submitted_at":"2026-05-29T09:01:56Z","abstract_excerpt":"Video-language models can process only a limited number of frames, making frame selection a key bottleneck for efficient video captioning. Most captioning pipelines still rely on uniform sampling, which is computationally cheap but agnostic to visual content. Adaptive frame sampling has recently emerged as a promising approach for selecting the most informative frames from a video; however, existing methods remain computationally expensive. We introduce PEEK, an efficient dynamic frame sampling method that distills caption-conditioned frame relevance rankings from a stronger teacher model into"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31029","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/2605.31029/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":"2605.31029","created_at":"2026-06-01T01:03:31.645738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31029v1","created_at":"2026-06-01T01:03:31.645738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31029","created_at":"2026-06-01T01:03:31.645738+00:00"},{"alias_kind":"pith_short_12","alias_value":"I4ESWN7YQF27","created_at":"2026-06-01T01:03:31.645738+00:00"},{"alias_kind":"pith_short_16","alias_value":"I4ESWN7YQF27VMPM","created_at":"2026-06-01T01:03:31.645738+00:00"},{"alias_kind":"pith_short_8","alias_value":"I4ESWN7Y","created_at":"2026-06-01T01:03:31.645738+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/I4ESWN7YQF27VMPMDWQC245C5I","json":"https://pith.science/pith/I4ESWN7YQF27VMPMDWQC245C5I.json","graph_json":"https://pith.science/api/pith-number/I4ESWN7YQF27VMPMDWQC245C5I/graph.json","events_json":"https://pith.science/api/pith-number/I4ESWN7YQF27VMPMDWQC245C5I/events.json","paper":"https://pith.science/paper/I4ESWN7Y"},"agent_actions":{"view_html":"https://pith.science/pith/I4ESWN7YQF27VMPMDWQC245C5I","download_json":"https://pith.science/pith/I4ESWN7YQF27VMPMDWQC245C5I.json","view_paper":"https://pith.science/paper/I4ESWN7Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31029&json=true","fetch_graph":"https://pith.science/api/pith-number/I4ESWN7YQF27VMPMDWQC245C5I/graph.json","fetch_events":"https://pith.science/api/pith-number/I4ESWN7YQF27VMPMDWQC245C5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I4ESWN7YQF27VMPMDWQC245C5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I4ESWN7YQF27VMPMDWQC245C5I/action/storage_attestation","attest_author":"https://pith.science/pith/I4ESWN7YQF27VMPMDWQC245C5I/action/author_attestation","sign_citation":"https://pith.science/pith/I4ESWN7YQF27VMPMDWQC245C5I/action/citation_signature","submit_replication":"https://pith.science/pith/I4ESWN7YQF27VMPMDWQC245C5I/action/replication_record"}},"created_at":"2026-06-01T01:03:31.645738+00:00","updated_at":"2026-06-01T01:03:31.645738+00:00"}