{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KYI6NQ54UCHIEXO6QKJ6AC4YDT","short_pith_number":"pith:KYI6NQ54","schema_version":"1.0","canonical_sha256":"5611e6c3bca08e825dde8293e00b981cf28dc1069da64b4ce820db48963a5c86","source":{"kind":"arxiv","id":"2410.23437","version":1},"attestation_state":"computed","paper":{"title":"Mind the Gap: A Generalized Approach for Cross-Modal Embedding Alignment","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Alan McMillan, Arihan Yadav","submitted_at":"2024-10-30T20:28:10Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems enhance text generation by incorporating external knowledge but often struggle when retrieving context across different text modalities due to semantic gaps. We introduce a generalized projection-based method, inspired by adapter modules in transfer learning, that efficiently bridges these gaps between various text types, such as programming code and pseudocode, or English and French sentences. Our approach emphasizes speed, accuracy, and data efficiency, requiring minimal resources for training and inference. By aligning embeddings from heterogeneo"},"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":"2410.23437","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T20:28:10Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"b042dbc542abcabe1f2dab1a2979f4f0f2a544cde18ddf8347528eada297fe9e","abstract_canon_sha256":"8d569f969a10009d20e306bbc7a410af78b82db9504beceed593cc4e679462ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:00.532531Z","signature_b64":"XXsBypv9kLglg3/WQJmbbr3zOaEkng90DZn4moKE6FPm7Ensvr8/ZWbi65QOYmP8obZe9TYsCZm3cRwXEbYkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5611e6c3bca08e825dde8293e00b981cf28dc1069da64b4ce820db48963a5c86","last_reissued_at":"2026-07-05T09:29:00.532015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:00.532015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mind the Gap: A Generalized Approach for Cross-Modal Embedding Alignment","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Alan McMillan, Arihan Yadav","submitted_at":"2024-10-30T20:28:10Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems enhance text generation by incorporating external knowledge but often struggle when retrieving context across different text modalities due to semantic gaps. We introduce a generalized projection-based method, inspired by adapter modules in transfer learning, that efficiently bridges these gaps between various text types, such as programming code and pseudocode, or English and French sentences. Our approach emphasizes speed, accuracy, and data efficiency, requiring minimal resources for training and inference. By aligning embeddings from heterogeneo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23437","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/2410.23437/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":"2410.23437","created_at":"2026-07-05T09:29:00.532091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23437v1","created_at":"2026-07-05T09:29:00.532091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23437","created_at":"2026-07-05T09:29:00.532091+00:00"},{"alias_kind":"pith_short_12","alias_value":"KYI6NQ54UCHI","created_at":"2026-07-05T09:29:00.532091+00:00"},{"alias_kind":"pith_short_16","alias_value":"KYI6NQ54UCHIEXO6","created_at":"2026-07-05T09:29:00.532091+00:00"},{"alias_kind":"pith_short_8","alias_value":"KYI6NQ54","created_at":"2026-07-05T09:29:00.532091+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/KYI6NQ54UCHIEXO6QKJ6AC4YDT","json":"https://pith.science/pith/KYI6NQ54UCHIEXO6QKJ6AC4YDT.json","graph_json":"https://pith.science/api/pith-number/KYI6NQ54UCHIEXO6QKJ6AC4YDT/graph.json","events_json":"https://pith.science/api/pith-number/KYI6NQ54UCHIEXO6QKJ6AC4YDT/events.json","paper":"https://pith.science/paper/KYI6NQ54"},"agent_actions":{"view_html":"https://pith.science/pith/KYI6NQ54UCHIEXO6QKJ6AC4YDT","download_json":"https://pith.science/pith/KYI6NQ54UCHIEXO6QKJ6AC4YDT.json","view_paper":"https://pith.science/paper/KYI6NQ54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23437&json=true","fetch_graph":"https://pith.science/api/pith-number/KYI6NQ54UCHIEXO6QKJ6AC4YDT/graph.json","fetch_events":"https://pith.science/api/pith-number/KYI6NQ54UCHIEXO6QKJ6AC4YDT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KYI6NQ54UCHIEXO6QKJ6AC4YDT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KYI6NQ54UCHIEXO6QKJ6AC4YDT/action/storage_attestation","attest_author":"https://pith.science/pith/KYI6NQ54UCHIEXO6QKJ6AC4YDT/action/author_attestation","sign_citation":"https://pith.science/pith/KYI6NQ54UCHIEXO6QKJ6AC4YDT/action/citation_signature","submit_replication":"https://pith.science/pith/KYI6NQ54UCHIEXO6QKJ6AC4YDT/action/replication_record"}},"created_at":"2026-07-05T09:29:00.532091+00:00","updated_at":"2026-07-05T09:29:00.532091+00:00"}