{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DS43EYNDOHO7Z4BZU5IMF4HBJK","short_pith_number":"pith:DS43EYND","schema_version":"1.0","canonical_sha256":"1cb9b261a371ddfcf039a750c2f0e14aab4ffb5f4e991aa92a9aaa9a48cf0915","source":{"kind":"arxiv","id":"2407.12508","version":2},"attestation_state":"computed","paper":{"title":"MERLIN: Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipeline","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Adam Lee, Donghoon Han, Eunhwan Park, Gisang Lee, Nojun Kwak","submitted_at":"2024-07-17T11:45:02Z","abstract_excerpt":"The rapid expansion of multimedia content has made accurately retrieving relevant videos from large collections increasingly challenging. Recent advancements in text-video retrieval have focused on cross-modal interactions, large-scale foundation model training, and probabilistic modeling, yet often neglect the crucial user perspective, leading to discrepancies between user queries and the content retrieved. To address this, we introduce MERLIN (Multimodal Embedding Refinement via LLM-based Iterative Navigation), a novel, training-free pipeline that leverages Large Language Models (LLMs) for i"},"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":"2407.12508","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T11:45:02Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"240cfcdd2fe04f3928df4e0fe2fdafc162c75f00e2b973554d3d86a0e921caf2","abstract_canon_sha256":"3d6f55a160a035844f7d3ccc06e50c199cf91bcd865ee4c57edad91e6094ac15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:06.600835Z","signature_b64":"XIqwaLi9oNqxrUK4LDWgCcPtpwqV7BYXgPqcsBmjLyWhPt3eWS4oOB3Vbw0+acHZF4Cny6NRaZQYDXhRkCQ/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cb9b261a371ddfcf039a750c2f0e14aab4ffb5f4e991aa92a9aaa9a48cf0915","last_reissued_at":"2026-07-05T09:21:06.600329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:06.600329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MERLIN: Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipeline","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Adam Lee, Donghoon Han, Eunhwan Park, Gisang Lee, Nojun Kwak","submitted_at":"2024-07-17T11:45:02Z","abstract_excerpt":"The rapid expansion of multimedia content has made accurately retrieving relevant videos from large collections increasingly challenging. Recent advancements in text-video retrieval have focused on cross-modal interactions, large-scale foundation model training, and probabilistic modeling, yet often neglect the crucial user perspective, leading to discrepancies between user queries and the content retrieved. To address this, we introduce MERLIN (Multimodal Embedding Refinement via LLM-based Iterative Navigation), a novel, training-free pipeline that leverages Large Language Models (LLMs) for i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12508","kind":"arxiv","version":2},"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/2407.12508/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":"2407.12508","created_at":"2026-07-05T09:21:06.600389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12508v2","created_at":"2026-07-05T09:21:06.600389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12508","created_at":"2026-07-05T09:21:06.600389+00:00"},{"alias_kind":"pith_short_12","alias_value":"DS43EYNDOHO7","created_at":"2026-07-05T09:21:06.600389+00:00"},{"alias_kind":"pith_short_16","alias_value":"DS43EYNDOHO7Z4BZ","created_at":"2026-07-05T09:21:06.600389+00:00"},{"alias_kind":"pith_short_8","alias_value":"DS43EYND","created_at":"2026-07-05T09:21:06.600389+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09641","citing_title":"MAVIS: Multi-Agent Video Retrieval via Structured Video Understanding","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2505.11237","citing_title":"Concept Drift Guided LayerNorm Tuning for Efficient Multimodal Metaphor Identification","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DS43EYNDOHO7Z4BZU5IMF4HBJK","json":"https://pith.science/pith/DS43EYNDOHO7Z4BZU5IMF4HBJK.json","graph_json":"https://pith.science/api/pith-number/DS43EYNDOHO7Z4BZU5IMF4HBJK/graph.json","events_json":"https://pith.science/api/pith-number/DS43EYNDOHO7Z4BZU5IMF4HBJK/events.json","paper":"https://pith.science/paper/DS43EYND"},"agent_actions":{"view_html":"https://pith.science/pith/DS43EYNDOHO7Z4BZU5IMF4HBJK","download_json":"https://pith.science/pith/DS43EYNDOHO7Z4BZU5IMF4HBJK.json","view_paper":"https://pith.science/paper/DS43EYND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12508&json=true","fetch_graph":"https://pith.science/api/pith-number/DS43EYNDOHO7Z4BZU5IMF4HBJK/graph.json","fetch_events":"https://pith.science/api/pith-number/DS43EYNDOHO7Z4BZU5IMF4HBJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DS43EYNDOHO7Z4BZU5IMF4HBJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DS43EYNDOHO7Z4BZU5IMF4HBJK/action/storage_attestation","attest_author":"https://pith.science/pith/DS43EYNDOHO7Z4BZU5IMF4HBJK/action/author_attestation","sign_citation":"https://pith.science/pith/DS43EYNDOHO7Z4BZU5IMF4HBJK/action/citation_signature","submit_replication":"https://pith.science/pith/DS43EYNDOHO7Z4BZU5IMF4HBJK/action/replication_record"}},"created_at":"2026-07-05T09:21:06.600389+00:00","updated_at":"2026-07-05T09:21:06.600389+00:00"}