{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GYZUMNMYBXNO2DPSTH2DWOBDED","short_pith_number":"pith:GYZUMNMY","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"},"canonical_sha256":"36334635980ddaed0df299f43b382320e9f65f29e0bfe605e68b8422d9f54995","source":{"kind":"arxiv","id":"2309.01516","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.01516","created_at":"2026-07-05T07:41:42Z"},{"alias_kind":"arxiv_version","alias_value":"2309.01516v3","created_at":"2026-07-05T07:41:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01516","created_at":"2026-07-05T07:41:42Z"},{"alias_kind":"pith_short_12","alias_value":"GYZUMNMYBXNO","created_at":"2026-07-05T07:41:42Z"},{"alias_kind":"pith_short_16","alias_value":"GYZUMNMYBXNO2DPS","created_at":"2026-07-05T07:41:42Z"},{"alias_kind":"pith_short_8","alias_value":"GYZUMNMY","created_at":"2026-07-05T07:41:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GYZUMNMYBXNO2DPSTH2DWOBDED","target":"record","payload":{"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"},"canonical_sha256":"36334635980ddaed0df299f43b382320e9f65f29e0bfe605e68b8422d9f54995","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"},"source_kind":"arxiv","source_id":"2309.01516","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:41:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yZf1PvIwQ/0m+7l2X1V3TRTI7VA4uph4H3Mx1f/x2UZDk2V+DhljlmpBlFOWsenvkDmnZ4SD+t6VQ6CouigsAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:00:53.845217Z"},"content_sha256":"e00cd9e302c7236ff2f39c1ca5b135888b5ca69ebc78393fd986e41c9d4f178e","schema_version":"1.0","event_id":"sha256:e00cd9e302c7236ff2f39c1ca5b135888b5ca69ebc78393fd986e41c9d4f178e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GYZUMNMYBXNO2DPSTH2DWOBDED","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:41:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ElY0fNpZx5sODXHTrsXYZMFio0Iza3R9VllmnuW5VoVxYf01mqoBbTnWCh2bspIRIgzQWMhB6Q1d92fETxUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:00:53.845601Z"},"content_sha256":"c006860dbb4dc2e71f6ef44aee105384e6b4ef7839ccebb543bf6326e1954f8b","schema_version":"1.0","event_id":"sha256:c006860dbb4dc2e71f6ef44aee105384e6b4ef7839ccebb543bf6326e1954f8b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GYZUMNMYBXNO2DPSTH2DWOBDED/bundle.json","state_url":"https://pith.science/pith/GYZUMNMYBXNO2DPSTH2DWOBDED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GYZUMNMYBXNO2DPSTH2DWOBDED/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":"2026-07-07T06:00:53Z","links":{"resolver":"https://pith.science/pith/GYZUMNMYBXNO2DPSTH2DWOBDED","bundle":"https://pith.science/pith/GYZUMNMYBXNO2DPSTH2DWOBDED/bundle.json","state":"https://pith.science/pith/GYZUMNMYBXNO2DPSTH2DWOBDED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GYZUMNMYBXNO2DPSTH2DWOBDED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GYZUMNMYBXNO2DPSTH2DWOBDED","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":"f0ca900c93fe5c39bf06b47b5e875e6ee5a38411cb80623425eaece9eb57c9e8","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-04T10:48:29Z","title_canon_sha256":"fa5e952867161a53a4b4f28f3c76880d481daa001b2616b90a234b217b3462db"},"schema_version":"1.0","source":{"id":"2309.01516","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.01516","created_at":"2026-07-05T07:41:42Z"},{"alias_kind":"arxiv_version","alias_value":"2309.01516v3","created_at":"2026-07-05T07:41:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01516","created_at":"2026-07-05T07:41:42Z"},{"alias_kind":"pith_short_12","alias_value":"GYZUMNMYBXNO","created_at":"2026-07-05T07:41:42Z"},{"alias_kind":"pith_short_16","alias_value":"GYZUMNMYBXNO2DPS","created_at":"2026-07-05T07:41:42Z"},{"alias_kind":"pith_short_8","alias_value":"GYZUMNMY","created_at":"2026-07-05T07:41:42Z"}],"graph_snapshots":[{"event_id":"sha256:c006860dbb4dc2e71f6ef44aee105384e6b4ef7839ccebb543bf6326e1954f8b","target":"graph","created_at":"2026-07-05T07:41:42Z","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/2309.01516/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"George Killick, Gerardo Aragon Camarasa, Richard McCreadie, Zijun Long","cross_cats":["cs.AI","cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-04T10:48:29Z","title":"MultiWay-Adapater: Adapting large-scale multi-modal models for scalable image-text retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01516","kind":"arxiv","version":3},"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:e00cd9e302c7236ff2f39c1ca5b135888b5ca69ebc78393fd986e41c9d4f178e","target":"record","created_at":"2026-07-05T07:41:42Z","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":"f0ca900c93fe5c39bf06b47b5e875e6ee5a38411cb80623425eaece9eb57c9e8","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-04T10:48:29Z","title_canon_sha256":"fa5e952867161a53a4b4f28f3c76880d481daa001b2616b90a234b217b3462db"},"schema_version":"1.0","source":{"id":"2309.01516","kind":"arxiv","version":3}},"canonical_sha256":"36334635980ddaed0df299f43b382320e9f65f29e0bfe605e68b8422d9f54995","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36334635980ddaed0df299f43b382320e9f65f29e0bfe605e68b8422d9f54995","first_computed_at":"2026-07-05T07:41:42.427765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:42.427765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9gmeHRleejs9LL4wputvimqXr8T9gPxpxrCw65dMVYrWtXqnP54oS8JjD6z7qDFWlhqb0DndA+kz+PeK788TAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:42.428291Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.01516","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e00cd9e302c7236ff2f39c1ca5b135888b5ca69ebc78393fd986e41c9d4f178e","sha256:c006860dbb4dc2e71f6ef44aee105384e6b4ef7839ccebb543bf6326e1954f8b"],"state_sha256":"0fe4a29414480dfd0a4771035771363e3147c81e2c95f29eef357ff05d1a1ce1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XcdMxf0GU9ldTDLiK9mbebCSH0mrRwsbx/oruIqw/odV7dfc6R+Qoqa4TFHavS02lTr0jC+wHnstYstRDlVxCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:00:53.847496Z","bundle_sha256":"372280eca8f6cfd4acf3c8a02f294ca7896db6249b8befd9b3ffc2c77d48ecfc"}}