{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BBH63TXUX2WFGMB3X3LZOLZSZA","short_pith_number":"pith:BBH63TXU","canonical_record":{"source":{"id":"2412.08979","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-12T06:26:02Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7f3366aa654c3f588980fed3523877543bb95503ab86b9e6d80727a6e0c6f19b","abstract_canon_sha256":"83ea78a688cba0401c9bf2afb9ed1829da64d37e012e84fd20665a75cf8732eb"},"schema_version":"1.0"},"canonical_sha256":"084fedcef4beac53303bbed7972f32c8301ec468c4100a499b2c3ac79630c679","source":{"kind":"arxiv","id":"2412.08979","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08979","created_at":"2026-07-05T09:48:04Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08979v1","created_at":"2026-07-05T09:48:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08979","created_at":"2026-07-05T09:48:04Z"},{"alias_kind":"pith_short_12","alias_value":"BBH63TXUX2WF","created_at":"2026-07-05T09:48:04Z"},{"alias_kind":"pith_short_16","alias_value":"BBH63TXUX2WFGMB3","created_at":"2026-07-05T09:48:04Z"},{"alias_kind":"pith_short_8","alias_value":"BBH63TXU","created_at":"2026-07-05T09:48:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BBH63TXUX2WFGMB3X3LZOLZSZA","target":"record","payload":{"canonical_record":{"source":{"id":"2412.08979","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-12T06:26:02Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7f3366aa654c3f588980fed3523877543bb95503ab86b9e6d80727a6e0c6f19b","abstract_canon_sha256":"83ea78a688cba0401c9bf2afb9ed1829da64d37e012e84fd20665a75cf8732eb"},"schema_version":"1.0"},"canonical_sha256":"084fedcef4beac53303bbed7972f32c8301ec468c4100a499b2c3ac79630c679","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:04.824177Z","signature_b64":"RWYgEArvgCg17Tv9fth80+bjVAr/19xvCPDahDyIHg8Zq4nt9k23awAUQHnhyFBlutAiQaASF1b+FwvDn26LDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"084fedcef4beac53303bbed7972f32c8301ec468c4100a499b2c3ac79630c679","last_reissued_at":"2026-07-05T09:48:04.823772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:04.823772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.08979","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:48:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AHv3ExV1ZvjD42SJTtwKrTiCcYBANQQrj2VgZuULdmcZDRViIXhAUiFhzOfbYInw2jmYZhT3Y755pzllnRdTBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T12:32:13.836860Z"},"content_sha256":"792a7790b7ac8412dbef190712739330cf505baac98e34c26b43a1ca92ac0682","schema_version":"1.0","event_id":"sha256:792a7790b7ac8412dbef190712739330cf505baac98e34c26b43a1ca92ac0682"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BBH63TXUX2WFGMB3X3LZOLZSZA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Wander Through the Multimodal Landscape: Efficient Transfer Learning via Low-rank Sequence Multimodal Adapter","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Tao Jin, Xize Cheng, Yangyang Wu, Zirun Guo","submitted_at":"2024-12-12T06:26:02Z","abstract_excerpt":"Efficient transfer learning methods such as adapter-based methods have shown great success in unimodal models and vision-language models. However, existing methods have two main challenges in fine-tuning multimodal models. Firstly, they are designed for vision-language tasks and fail to extend to situations where there are more than two modalities. Secondly, they exhibit limited exploitation of interactions between modalities and lack efficiency. To address these issues, in this paper, we propose the loW-rank sequence multimodal adapter (Wander). We first use the outer product to fuse the info"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08979","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/2412.08979/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":"2026-07-05T09:48:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lW7+ErxXw/07ImJ4dQBc0ChPoHG0PkeO0WbYMTTBo1kFlkZUxxW3nGdTthHLdt43LEmunGQyWGpMwMe0VjtYBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T12:32:13.837381Z"},"content_sha256":"525dffda6d0d39043532050c1b6f6db52f3bb9bff9bd5ab83b6787e6fb378650","schema_version":"1.0","event_id":"sha256:525dffda6d0d39043532050c1b6f6db52f3bb9bff9bd5ab83b6787e6fb378650"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BBH63TXUX2WFGMB3X3LZOLZSZA/bundle.json","state_url":"https://pith.science/pith/BBH63TXUX2WFGMB3X3LZOLZSZA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BBH63TXUX2WFGMB3X3LZOLZSZA/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":"2026-08-16T12:32:13Z","links":{"resolver":"https://pith.science/pith/BBH63TXUX2WFGMB3X3LZOLZSZA","bundle":"https://pith.science/pith/BBH63TXUX2WFGMB3X3LZOLZSZA/bundle.json","state":"https://pith.science/pith/BBH63TXUX2WFGMB3X3LZOLZSZA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BBH63TXUX2WFGMB3X3LZOLZSZA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BBH63TXUX2WFGMB3X3LZOLZSZA","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":"83ea78a688cba0401c9bf2afb9ed1829da64d37e012e84fd20665a75cf8732eb","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-12T06:26:02Z","title_canon_sha256":"7f3366aa654c3f588980fed3523877543bb95503ab86b9e6d80727a6e0c6f19b"},"schema_version":"1.0","source":{"id":"2412.08979","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08979","created_at":"2026-07-05T09:48:04Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08979v1","created_at":"2026-07-05T09:48:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08979","created_at":"2026-07-05T09:48:04Z"},{"alias_kind":"pith_short_12","alias_value":"BBH63TXUX2WF","created_at":"2026-07-05T09:48:04Z"},{"alias_kind":"pith_short_16","alias_value":"BBH63TXUX2WFGMB3","created_at":"2026-07-05T09:48:04Z"},{"alias_kind":"pith_short_8","alias_value":"BBH63TXU","created_at":"2026-07-05T09:48:04Z"}],"graph_snapshots":[{"event_id":"sha256:525dffda6d0d39043532050c1b6f6db52f3bb9bff9bd5ab83b6787e6fb378650","target":"graph","created_at":"2026-07-05T09:48:04Z","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/2412.08979/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient transfer learning methods such as adapter-based methods have shown great success in unimodal models and vision-language models. However, existing methods have two main challenges in fine-tuning multimodal models. Firstly, they are designed for vision-language tasks and fail to extend to situations where there are more than two modalities. Secondly, they exhibit limited exploitation of interactions between modalities and lack efficiency. To address these issues, in this paper, we propose the loW-rank sequence multimodal adapter (Wander). We first use the outer product to fuse the info","authors_text":"Tao Jin, Xize Cheng, Yangyang Wu, Zirun Guo","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-12T06:26:02Z","title":"A Wander Through the Multimodal Landscape: Efficient Transfer Learning via Low-rank Sequence Multimodal Adapter"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08979","kind":"arxiv","version":1},"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":"sha256:792a7790b7ac8412dbef190712739330cf505baac98e34c26b43a1ca92ac0682","target":"record","created_at":"2026-07-05T09:48:04Z","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":"83ea78a688cba0401c9bf2afb9ed1829da64d37e012e84fd20665a75cf8732eb","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-12T06:26:02Z","title_canon_sha256":"7f3366aa654c3f588980fed3523877543bb95503ab86b9e6d80727a6e0c6f19b"},"schema_version":"1.0","source":{"id":"2412.08979","kind":"arxiv","version":1}},"canonical_sha256":"084fedcef4beac53303bbed7972f32c8301ec468c4100a499b2c3ac79630c679","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"084fedcef4beac53303bbed7972f32c8301ec468c4100a499b2c3ac79630c679","first_computed_at":"2026-07-05T09:48:04.823772Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:04.823772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RWYgEArvgCg17Tv9fth80+bjVAr/19xvCPDahDyIHg8Zq4nt9k23awAUQHnhyFBlutAiQaASF1b+FwvDn26LDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:04.824177Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08979","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:792a7790b7ac8412dbef190712739330cf505baac98e34c26b43a1ca92ac0682","sha256:525dffda6d0d39043532050c1b6f6db52f3bb9bff9bd5ab83b6787e6fb378650"],"state_sha256":"921f41c64bc151ee1e854473bda49381d7f974dbb3a8c31de8991c896d231bc0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XcvM+KwoCBTKlGepgsumoOCL9WSnnmQLVxc7Mc2+4HzXooo03tvxUABLIEZNM1cRAvltyqXHOOHFuIsxxcVDAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T12:32:13.841025Z","bundle_sha256":"fe8719b133dda69b3c766f90e00699f6106b083aa683e59c7e402cdf70ac7756"}}