{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DS43EYNDOHO7Z4BZU5IMF4HBJK","short_pith_number":"pith:DS43EYND","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"},"canonical_sha256":"1cb9b261a371ddfcf039a750c2f0e14aab4ffb5f4e991aa92a9aaa9a48cf0915","source":{"kind":"arxiv","id":"2407.12508","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12508","created_at":"2026-07-05T09:21:06Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12508v2","created_at":"2026-07-05T09:21:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12508","created_at":"2026-07-05T09:21:06Z"},{"alias_kind":"pith_short_12","alias_value":"DS43EYNDOHO7","created_at":"2026-07-05T09:21:06Z"},{"alias_kind":"pith_short_16","alias_value":"DS43EYNDOHO7Z4BZ","created_at":"2026-07-05T09:21:06Z"},{"alias_kind":"pith_short_8","alias_value":"DS43EYND","created_at":"2026-07-05T09:21:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DS43EYNDOHO7Z4BZU5IMF4HBJK","target":"record","payload":{"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"},"canonical_sha256":"1cb9b261a371ddfcf039a750c2f0e14aab4ffb5f4e991aa92a9aaa9a48cf0915","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"},"source_kind":"arxiv","source_id":"2407.12508","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:21:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hHA0uIwt3t5sAJZzuZr5HPjb+BYMjd2jlHqwdDoliMH2rADD3Jg0Rke6/BqaLa1f2AWJlZOq4qoBoDaHIvUGAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:28:41.560376Z"},"content_sha256":"1d075cdc5fce66e9b44944166a06e59c2bb2dd2239cdd659aec0690fd7d405c3","schema_version":"1.0","event_id":"sha256:1d075cdc5fce66e9b44944166a06e59c2bb2dd2239cdd659aec0690fd7d405c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DS43EYNDOHO7Z4BZU5IMF4HBJK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:21:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CDbVjCh5S0iYYsmc2wmNiCbQzIVDQeOaHUUO1cN4QbmSLD3Zb5X5aeKJQXnIe3u8WSVHoqZ7d3TSewMkJhi9CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:28:41.561003Z"},"content_sha256":"4264b8f2351440f7e0a9a76ad689568972ad221e6c05d41818914206100571aa","schema_version":"1.0","event_id":"sha256:4264b8f2351440f7e0a9a76ad689568972ad221e6c05d41818914206100571aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DS43EYNDOHO7Z4BZU5IMF4HBJK/bundle.json","state_url":"https://pith.science/pith/DS43EYNDOHO7Z4BZU5IMF4HBJK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DS43EYNDOHO7Z4BZU5IMF4HBJK/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":"2026-08-03T16:28:41Z","links":{"resolver":"https://pith.science/pith/DS43EYNDOHO7Z4BZU5IMF4HBJK","bundle":"https://pith.science/pith/DS43EYNDOHO7Z4BZU5IMF4HBJK/bundle.json","state":"https://pith.science/pith/DS43EYNDOHO7Z4BZU5IMF4HBJK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DS43EYNDOHO7Z4BZU5IMF4HBJK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DS43EYNDOHO7Z4BZU5IMF4HBJK","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":"3d6f55a160a035844f7d3ccc06e50c199cf91bcd865ee4c57edad91e6094ac15","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T11:45:02Z","title_canon_sha256":"240cfcdd2fe04f3928df4e0fe2fdafc162c75f00e2b973554d3d86a0e921caf2"},"schema_version":"1.0","source":{"id":"2407.12508","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12508","created_at":"2026-07-05T09:21:06Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12508v2","created_at":"2026-07-05T09:21:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12508","created_at":"2026-07-05T09:21:06Z"},{"alias_kind":"pith_short_12","alias_value":"DS43EYNDOHO7","created_at":"2026-07-05T09:21:06Z"},{"alias_kind":"pith_short_16","alias_value":"DS43EYNDOHO7Z4BZ","created_at":"2026-07-05T09:21:06Z"},{"alias_kind":"pith_short_8","alias_value":"DS43EYND","created_at":"2026-07-05T09:21:06Z"}],"graph_snapshots":[{"event_id":"sha256:4264b8f2351440f7e0a9a76ad689568972ad221e6c05d41818914206100571aa","target":"graph","created_at":"2026-07-05T09:21:06Z","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/2407.12508/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Adam Lee, Donghoon Han, Eunhwan Park, Gisang Lee, Nojun Kwak","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T11:45:02Z","title":"MERLIN: Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipeline"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12508","kind":"arxiv","version":2},"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":"sha256:1d075cdc5fce66e9b44944166a06e59c2bb2dd2239cdd659aec0690fd7d405c3","target":"record","created_at":"2026-07-05T09:21:06Z","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":"3d6f55a160a035844f7d3ccc06e50c199cf91bcd865ee4c57edad91e6094ac15","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T11:45:02Z","title_canon_sha256":"240cfcdd2fe04f3928df4e0fe2fdafc162c75f00e2b973554d3d86a0e921caf2"},"schema_version":"1.0","source":{"id":"2407.12508","kind":"arxiv","version":2}},"canonical_sha256":"1cb9b261a371ddfcf039a750c2f0e14aab4ffb5f4e991aa92a9aaa9a48cf0915","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1cb9b261a371ddfcf039a750c2f0e14aab4ffb5f4e991aa92a9aaa9a48cf0915","first_computed_at":"2026-07-05T09:21:06.600329Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:06.600329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XIqwaLi9oNqxrUK4LDWgCcPtpwqV7BYXgPqcsBmjLyWhPt3eWS4oOB3Vbw0+acHZF4Cny6NRaZQYDXhRkCQ/CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:06.600835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12508","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d075cdc5fce66e9b44944166a06e59c2bb2dd2239cdd659aec0690fd7d405c3","sha256:4264b8f2351440f7e0a9a76ad689568972ad221e6c05d41818914206100571aa"],"state_sha256":"7aef49f5c21d7ea5f100c778b803101517eca4142a1374208a09a7c942601ad2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J0zHgZJ8Ol/4m288oSqLRDxBotMsvfyLaxiM+9EhaEZ3Ur1qy6oEWK6L/QYCeIR4Z+2ZFhjcuT3stSHW3ot8Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:28:41.566194Z","bundle_sha256":"1c51a683496ab4decd2a51c168cad777be845a937963d4edba4c5c02d5ad1523"}}