{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GYZUMNMYBXNO2DPSTH2DWOBDED","short_pith_number":"pith:GYZUMNMY","schema_version":"1.0","canonical_sha256":"36334635980ddaed0df299f43b382320e9f65f29e0bfe605e68b8422d9f54995","source":{"kind":"arxiv","id":"2309.01516","version":3},"attestation_state":"computed","paper":{"title":"MultiWay-Adapater: Adapting large-scale multi-modal models for scalable image-text retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"George Killick, Gerardo Aragon Camarasa, Richard McCreadie, Zijun Long","submitted_at":"2023-09-04T10:48:29Z","abstract_excerpt":"As Multimodal Large Language Models (MLLMs) grow in size, adapting them to specialized tasks becomes increasingly challenging due to high computational and memory demands. Indeed, traditional fine-tuning methods are costly, due to the need for extensive, task-specific training. While efficient adaptation methods exist that aim to reduce these costs, in practice they suffer from shallow inter-modal alignment, which severely hurts model effectiveness. To tackle these computational challenges and improve inter-modal alignment, we introduce the MultiWay-Adapter (MWA), a novel framework featuring a"},"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":"2309.01516","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-04T10:48:29Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"fa5e952867161a53a4b4f28f3c76880d481daa001b2616b90a234b217b3462db","abstract_canon_sha256":"f0ca900c93fe5c39bf06b47b5e875e6ee5a38411cb80623425eaece9eb57c9e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:42.428291Z","signature_b64":"9gmeHRleejs9LL4wputvimqXr8T9gPxpxrCw65dMVYrWtXqnP54oS8JjD6z7qDFWlhqb0DndA+kz+PeK788TAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36334635980ddaed0df299f43b382320e9f65f29e0bfe605e68b8422d9f54995","last_reissued_at":"2026-07-05T07:41:42.427765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:42.427765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MultiWay-Adapater: Adapting large-scale multi-modal models for scalable image-text retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"George Killick, Gerardo Aragon Camarasa, Richard McCreadie, Zijun Long","submitted_at":"2023-09-04T10:48:29Z","abstract_excerpt":"As Multimodal Large Language Models (MLLMs) grow in size, adapting them to specialized tasks becomes increasingly challenging due to high computational and memory demands. Indeed, traditional fine-tuning methods are costly, due to the need for extensive, task-specific training. While efficient adaptation methods exist that aim to reduce these costs, in practice they suffer from shallow inter-modal alignment, which severely hurts model effectiveness. To tackle these computational challenges and improve inter-modal alignment, we introduce the MultiWay-Adapter (MWA), a novel framework featuring a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01516","kind":"arxiv","version":3},"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/2309.01516/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":"2309.01516","created_at":"2026-07-05T07:41:42.427829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.01516v3","created_at":"2026-07-05T07:41:42.427829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01516","created_at":"2026-07-05T07:41:42.427829+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYZUMNMYBXNO","created_at":"2026-07-05T07:41:42.427829+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYZUMNMYBXNO2DPS","created_at":"2026-07-05T07:41:42.427829+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYZUMNMY","created_at":"2026-07-05T07:41:42.427829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.19288","citing_title":"Da Yu: Towards USV-Based Image Captioning for Waterway Surveillance and Scene Understanding","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYZUMNMYBXNO2DPSTH2DWOBDED","json":"https://pith.science/pith/GYZUMNMYBXNO2DPSTH2DWOBDED.json","graph_json":"https://pith.science/api/pith-number/GYZUMNMYBXNO2DPSTH2DWOBDED/graph.json","events_json":"https://pith.science/api/pith-number/GYZUMNMYBXNO2DPSTH2DWOBDED/events.json","paper":"https://pith.science/paper/GYZUMNMY"},"agent_actions":{"view_html":"https://pith.science/pith/GYZUMNMYBXNO2DPSTH2DWOBDED","download_json":"https://pith.science/pith/GYZUMNMYBXNO2DPSTH2DWOBDED.json","view_paper":"https://pith.science/paper/GYZUMNMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.01516&json=true","fetch_graph":"https://pith.science/api/pith-number/GYZUMNMYBXNO2DPSTH2DWOBDED/graph.json","fetch_events":"https://pith.science/api/pith-number/GYZUMNMYBXNO2DPSTH2DWOBDED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYZUMNMYBXNO2DPSTH2DWOBDED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYZUMNMYBXNO2DPSTH2DWOBDED/action/storage_attestation","attest_author":"https://pith.science/pith/GYZUMNMYBXNO2DPSTH2DWOBDED/action/author_attestation","sign_citation":"https://pith.science/pith/GYZUMNMYBXNO2DPSTH2DWOBDED/action/citation_signature","submit_replication":"https://pith.science/pith/GYZUMNMYBXNO2DPSTH2DWOBDED/action/replication_record"}},"created_at":"2026-07-05T07:41:42.427829+00:00","updated_at":"2026-07-05T07:41:42.427829+00:00"}