{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6DGZ2E2ZS7FMH7XXBC4C37BB4D","short_pith_number":"pith:6DGZ2E2Z","canonical_record":{"source":{"id":"2404.01745","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T09:01:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"929f0750db7cbd7f77dd37a53d9b1bc2a2e3bc7bbc4a0bcc0322e8e33a3141b8","abstract_canon_sha256":"2091b910a838e14f2f3bab05195c384801afa694fcfcee9e24995eb94dc3190f"},"schema_version":"1.0"},"canonical_sha256":"f0cd9d135997cac3fef708b82dfc21e0e8adb203ba3ecf36ce8bdffa977722aa","source":{"kind":"arxiv","id":"2404.01745","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01745","created_at":"2026-07-05T08:03:19Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01745v1","created_at":"2026-07-05T08:03:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01745","created_at":"2026-07-05T08:03:19Z"},{"alias_kind":"pith_short_12","alias_value":"6DGZ2E2ZS7FM","created_at":"2026-07-05T08:03:19Z"},{"alias_kind":"pith_short_16","alias_value":"6DGZ2E2ZS7FMH7XX","created_at":"2026-07-05T08:03:19Z"},{"alias_kind":"pith_short_8","alias_value":"6DGZ2E2Z","created_at":"2026-07-05T08:03:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6DGZ2E2ZS7FMH7XXBC4C37BB4D","target":"record","payload":{"canonical_record":{"source":{"id":"2404.01745","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T09:01:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"929f0750db7cbd7f77dd37a53d9b1bc2a2e3bc7bbc4a0bcc0322e8e33a3141b8","abstract_canon_sha256":"2091b910a838e14f2f3bab05195c384801afa694fcfcee9e24995eb94dc3190f"},"schema_version":"1.0"},"canonical_sha256":"f0cd9d135997cac3fef708b82dfc21e0e8adb203ba3ecf36ce8bdffa977722aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:19.022492Z","signature_b64":"uXPRiZoAFB8jSdZZ67nAdB7u9K6xKOmdU0FDxfnRFvC8STC3EvRf6JRvX7rChoklV3IWa8zlkWzM5RQqtmuGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0cd9d135997cac3fef708b82dfc21e0e8adb203ba3ecf36ce8bdffa977722aa","last_reissued_at":"2026-07-05T08:03:19.022128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:19.022128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.01745","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:03:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UPf701ifHQBCAK2TW8iRbeJKUkaMLqmc+JiL+NJxwyLuxNMTPuweZcXCyfIEZkDO1kfaENEnRD/fWPiVy8VhBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:03:47.482853Z"},"content_sha256":"ccb8b90cc9bb5725ce7f57058e3cefbae1738a752e95879b299ff64f54ef4c91","schema_version":"1.0","event_id":"sha256:ccb8b90cc9bb5725ce7f57058e3cefbae1738a752e95879b299ff64f54ef4c91"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6DGZ2E2ZS7FMH7XXBC4C37BB4D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unleash the Potential of CLIP for Video Highlight Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Donghoon Han, Eunhwan Park, Nojun Kwak, Seong-Uk Nam, Seunghyeon Seo","submitted_at":"2024-04-02T09:01:58Z","abstract_excerpt":"Multimodal and large language models (LLMs) have revolutionized the utilization of open-world knowledge, unlocking novel potentials across various tasks and applications. Among these domains, the video domain has notably benefited from their capabilities. In this paper, we present Highlight-CLIP (HL-CLIP), a method designed to excel in the video highlight detection task by leveraging the pre-trained knowledge embedded in multimodal models. By simply fine-tuning the multimodal encoder in combination with our innovative saliency pooling technique, we have achieved the state-of-the-art performanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01745","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/2404.01745/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:03:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZFmZgGacVdamkbYGkTUIxZGBZdWViNAsHDKZuG3d3ej3y7ODys3o3E89AqHfmlyf1Ij7YKuCh1mKlGrnXvW9Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:03:47.483353Z"},"content_sha256":"d30549cea50fffa20415a685c7237dfd5e403a95574867d6454fad9813ab80a2","schema_version":"1.0","event_id":"sha256:d30549cea50fffa20415a685c7237dfd5e403a95574867d6454fad9813ab80a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6DGZ2E2ZS7FMH7XXBC4C37BB4D/bundle.json","state_url":"https://pith.science/pith/6DGZ2E2ZS7FMH7XXBC4C37BB4D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6DGZ2E2ZS7FMH7XXBC4C37BB4D/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-12T13:03:47Z","links":{"resolver":"https://pith.science/pith/6DGZ2E2ZS7FMH7XXBC4C37BB4D","bundle":"https://pith.science/pith/6DGZ2E2ZS7FMH7XXBC4C37BB4D/bundle.json","state":"https://pith.science/pith/6DGZ2E2ZS7FMH7XXBC4C37BB4D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6DGZ2E2ZS7FMH7XXBC4C37BB4D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6DGZ2E2ZS7FMH7XXBC4C37BB4D","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":"2091b910a838e14f2f3bab05195c384801afa694fcfcee9e24995eb94dc3190f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T09:01:58Z","title_canon_sha256":"929f0750db7cbd7f77dd37a53d9b1bc2a2e3bc7bbc4a0bcc0322e8e33a3141b8"},"schema_version":"1.0","source":{"id":"2404.01745","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01745","created_at":"2026-07-05T08:03:19Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01745v1","created_at":"2026-07-05T08:03:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01745","created_at":"2026-07-05T08:03:19Z"},{"alias_kind":"pith_short_12","alias_value":"6DGZ2E2ZS7FM","created_at":"2026-07-05T08:03:19Z"},{"alias_kind":"pith_short_16","alias_value":"6DGZ2E2ZS7FMH7XX","created_at":"2026-07-05T08:03:19Z"},{"alias_kind":"pith_short_8","alias_value":"6DGZ2E2Z","created_at":"2026-07-05T08:03:19Z"}],"graph_snapshots":[{"event_id":"sha256:d30549cea50fffa20415a685c7237dfd5e403a95574867d6454fad9813ab80a2","target":"graph","created_at":"2026-07-05T08:03:19Z","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/2404.01745/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal and large language models (LLMs) have revolutionized the utilization of open-world knowledge, unlocking novel potentials across various tasks and applications. Among these domains, the video domain has notably benefited from their capabilities. In this paper, we present Highlight-CLIP (HL-CLIP), a method designed to excel in the video highlight detection task by leveraging the pre-trained knowledge embedded in multimodal models. By simply fine-tuning the multimodal encoder in combination with our innovative saliency pooling technique, we have achieved the state-of-the-art performanc","authors_text":"Donghoon Han, Eunhwan Park, Nojun Kwak, Seong-Uk Nam, Seunghyeon Seo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T09:01:58Z","title":"Unleash the Potential of CLIP for Video Highlight Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01745","kind":"arxiv","version":1},"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:ccb8b90cc9bb5725ce7f57058e3cefbae1738a752e95879b299ff64f54ef4c91","target":"record","created_at":"2026-07-05T08:03:19Z","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":"2091b910a838e14f2f3bab05195c384801afa694fcfcee9e24995eb94dc3190f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T09:01:58Z","title_canon_sha256":"929f0750db7cbd7f77dd37a53d9b1bc2a2e3bc7bbc4a0bcc0322e8e33a3141b8"},"schema_version":"1.0","source":{"id":"2404.01745","kind":"arxiv","version":1}},"canonical_sha256":"f0cd9d135997cac3fef708b82dfc21e0e8adb203ba3ecf36ce8bdffa977722aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0cd9d135997cac3fef708b82dfc21e0e8adb203ba3ecf36ce8bdffa977722aa","first_computed_at":"2026-07-05T08:03:19.022128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:19.022128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uXPRiZoAFB8jSdZZ67nAdB7u9K6xKOmdU0FDxfnRFvC8STC3EvRf6JRvX7rChoklV3IWa8zlkWzM5RQqtmuGAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:19.022492Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.01745","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccb8b90cc9bb5725ce7f57058e3cefbae1738a752e95879b299ff64f54ef4c91","sha256:d30549cea50fffa20415a685c7237dfd5e403a95574867d6454fad9813ab80a2"],"state_sha256":"f46a2a3d57b8ea1acc6813d300335f4b183f81b5b686930141bcd880060aca10"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AuHkId3E0wFVYXN35c23inOpj0YYEoj2+wspRLwGSFF8EZu59q/xu+8jlE1dIZwUOUm3XLiSYhqhtW2VuZADCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T13:03:47.488864Z","bundle_sha256":"7010859b5bf69f591ce3d2742f799c96ffd2908bf5466a8c3a6ef59770c04acc"}}