{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YS63IM62GIKNMXRGU43UBJTIVC","short_pith_number":"pith:YS63IM62","canonical_record":{"source":{"id":"2304.14933","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-28T15:43:21Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"eb044cac57a0dfc352622c0c0eb55307bab11088370df1fb5afdb15c20ff0ea3","abstract_canon_sha256":"10c41d53942379ca73b0be6295d28d286b0358ea6974c4d3a002be3f63614472"},"schema_version":"1.0"},"canonical_sha256":"c4bdb433da3214d65e26a73740a668a8939a4ca6ab537589735a260e2b94381c","source":{"kind":"arxiv","id":"2304.14933","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14933","created_at":"2026-07-05T06:59:31Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14933v2","created_at":"2026-07-05T06:59:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14933","created_at":"2026-07-05T06:59:31Z"},{"alias_kind":"pith_short_12","alias_value":"YS63IM62GIKN","created_at":"2026-07-05T06:59:31Z"},{"alias_kind":"pith_short_16","alias_value":"YS63IM62GIKNMXRG","created_at":"2026-07-05T06:59:31Z"},{"alias_kind":"pith_short_8","alias_value":"YS63IM62","created_at":"2026-07-05T06:59:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YS63IM62GIKNMXRGU43UBJTIVC","target":"record","payload":{"canonical_record":{"source":{"id":"2304.14933","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-28T15:43:21Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"eb044cac57a0dfc352622c0c0eb55307bab11088370df1fb5afdb15c20ff0ea3","abstract_canon_sha256":"10c41d53942379ca73b0be6295d28d286b0358ea6974c4d3a002be3f63614472"},"schema_version":"1.0"},"canonical_sha256":"c4bdb433da3214d65e26a73740a668a8939a4ca6ab537589735a260e2b94381c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:31.626652Z","signature_b64":"o/tsfhBeQ5RQqw2Nljqqk28pRabEUXgyu/aeeETzZBiqyAJ52af+M32TdOY25oVjzFD1OYxQHTx8Vqdv39X9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4bdb433da3214d65e26a73740a668a8939a4ca6ab537589735a260e2b94381c","last_reissued_at":"2026-07-05T06:59:31.626162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:31.626162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.14933","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":"2026-07-05T06:59:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/AZ/3VCwL5kZjIc4rTk29BrZIX0u5FCrNy17VtIRNd8ZzHdBNHzyuoEebMXeicfW7rtLNOmpivZGoWiJEP+QCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:37:46.097041Z"},"content_sha256":"ad5087c8655ab4e1dfd7d29bc5a1a0afc44b242aa641b15239ae8617c4e6fabd","schema_version":"1.0","event_id":"sha256:ad5087c8655ab4e1dfd7d29bc5a1a0afc44b242aa641b15239ae8617c4e6fabd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YS63IM62GIKNMXRGU43UBJTIVC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Empirical Study of Multimodal Model Merging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Kevin Lin, Lijuan Wang, Linjie Li, Mohit Bansal, Yi-Lin Sung, Zhe Gan","submitted_at":"2023-04-28T15:43:21Z","abstract_excerpt":"Model merging (e.g., via interpolation or task arithmetic) fuses multiple models trained on different tasks to generate a multi-task solution. The technique has been proven successful in previous studies, where the models are trained on similar tasks and with the same initialization. In this paper, we expand on this concept to a multimodal setup by merging transformers trained on different modalities. Furthermore, we conduct our study for a novel goal where we can merge vision, language, and cross-modal transformers of a modality-specific architecture to create a parameter-efficient modality-a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14933","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/2304.14933/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":"2026-07-05T06:59:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"plEO8dxTg/M9a3cZTUk2AVlDR4wJ3mBW9H6jnMI9AavHdyLjV/GLWyT56x1q/Tp1I2qkmI61VFj4BEZOkCDuDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:37:46.097670Z"},"content_sha256":"63e1cb2b6a0f488251d52b297bd627670bfc1b90bb49bd1141b7103b5583c687","schema_version":"1.0","event_id":"sha256:63e1cb2b6a0f488251d52b297bd627670bfc1b90bb49bd1141b7103b5583c687"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YS63IM62GIKNMXRGU43UBJTIVC/bundle.json","state_url":"https://pith.science/pith/YS63IM62GIKNMXRGU43UBJTIVC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YS63IM62GIKNMXRGU43UBJTIVC/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":"2026-08-03T21:37:46Z","links":{"resolver":"https://pith.science/pith/YS63IM62GIKNMXRGU43UBJTIVC","bundle":"https://pith.science/pith/YS63IM62GIKNMXRGU43UBJTIVC/bundle.json","state":"https://pith.science/pith/YS63IM62GIKNMXRGU43UBJTIVC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YS63IM62GIKNMXRGU43UBJTIVC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YS63IM62GIKNMXRGU43UBJTIVC","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":"10c41d53942379ca73b0be6295d28d286b0358ea6974c4d3a002be3f63614472","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-28T15:43:21Z","title_canon_sha256":"eb044cac57a0dfc352622c0c0eb55307bab11088370df1fb5afdb15c20ff0ea3"},"schema_version":"1.0","source":{"id":"2304.14933","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14933","created_at":"2026-07-05T06:59:31Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14933v2","created_at":"2026-07-05T06:59:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14933","created_at":"2026-07-05T06:59:31Z"},{"alias_kind":"pith_short_12","alias_value":"YS63IM62GIKN","created_at":"2026-07-05T06:59:31Z"},{"alias_kind":"pith_short_16","alias_value":"YS63IM62GIKNMXRG","created_at":"2026-07-05T06:59:31Z"},{"alias_kind":"pith_short_8","alias_value":"YS63IM62","created_at":"2026-07-05T06:59:31Z"}],"graph_snapshots":[{"event_id":"sha256:63e1cb2b6a0f488251d52b297bd627670bfc1b90bb49bd1141b7103b5583c687","target":"graph","created_at":"2026-07-05T06:59:31Z","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/2304.14933/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model merging (e.g., via interpolation or task arithmetic) fuses multiple models trained on different tasks to generate a multi-task solution. The technique has been proven successful in previous studies, where the models are trained on similar tasks and with the same initialization. In this paper, we expand on this concept to a multimodal setup by merging transformers trained on different modalities. Furthermore, we conduct our study for a novel goal where we can merge vision, language, and cross-modal transformers of a modality-specific architecture to create a parameter-efficient modality-a","authors_text":"Kevin Lin, Lijuan Wang, Linjie Li, Mohit Bansal, Yi-Lin Sung, Zhe Gan","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-28T15:43:21Z","title":"An Empirical Study of Multimodal Model Merging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14933","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:ad5087c8655ab4e1dfd7d29bc5a1a0afc44b242aa641b15239ae8617c4e6fabd","target":"record","created_at":"2026-07-05T06:59:31Z","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":"10c41d53942379ca73b0be6295d28d286b0358ea6974c4d3a002be3f63614472","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-28T15:43:21Z","title_canon_sha256":"eb044cac57a0dfc352622c0c0eb55307bab11088370df1fb5afdb15c20ff0ea3"},"schema_version":"1.0","source":{"id":"2304.14933","kind":"arxiv","version":2}},"canonical_sha256":"c4bdb433da3214d65e26a73740a668a8939a4ca6ab537589735a260e2b94381c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4bdb433da3214d65e26a73740a668a8939a4ca6ab537589735a260e2b94381c","first_computed_at":"2026-07-05T06:59:31.626162Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:31.626162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o/tsfhBeQ5RQqw2Nljqqk28pRabEUXgyu/aeeETzZBiqyAJ52af+M32TdOY25oVjzFD1OYxQHTx8Vqdv39X9Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:31.626652Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.14933","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad5087c8655ab4e1dfd7d29bc5a1a0afc44b242aa641b15239ae8617c4e6fabd","sha256:63e1cb2b6a0f488251d52b297bd627670bfc1b90bb49bd1141b7103b5583c687"],"state_sha256":"7aa85efa13955129d7e662113f7d6a4c2fc7fcc3bb50c7c4e125b19a59ab984f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lPpApRCVGit5u/TuNi/gLvughxntg24PB60QBrvlI7xcrMeqj+Ftjx7o7QQgcVVRyF/sVO7/3OR4y+3Wk3IwDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:37:46.102713Z","bundle_sha256":"5b378d0f6514ed9ff4963d13113a35fe8354ee719ca027d05947b9df64e1c6e5"}}