{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RGJ7MLSK3MFOERYPRPLR3C6IX4","short_pith_number":"pith:RGJ7MLSK","canonical_record":{"source":{"id":"2408.06610","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T03:45:11Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"5a56854ab0bd4f49ad3c4e5ccee8bd6c740a2bc24561b8284c06b5183ffed04a","abstract_canon_sha256":"c373871f1315eeecb3d6d96f2ae6052041c7d8fe9d44389c4f7d60adfcac880f"},"schema_version":"1.0"},"canonical_sha256":"8993f62e4adb0ae2470f8bd71d8bc8bf2dbb65d0d4ac4113ee07120a21628766","source":{"kind":"arxiv","id":"2408.06610","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06610","created_at":"2026-07-05T08:54:59Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06610v1","created_at":"2026-07-05T08:54:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06610","created_at":"2026-07-05T08:54:59Z"},{"alias_kind":"pith_short_12","alias_value":"RGJ7MLSK3MFO","created_at":"2026-07-05T08:54:59Z"},{"alias_kind":"pith_short_16","alias_value":"RGJ7MLSK3MFOERYP","created_at":"2026-07-05T08:54:59Z"},{"alias_kind":"pith_short_8","alias_value":"RGJ7MLSK","created_at":"2026-07-05T08:54:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RGJ7MLSK3MFOERYPRPLR3C6IX4","target":"record","payload":{"canonical_record":{"source":{"id":"2408.06610","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T03:45:11Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"5a56854ab0bd4f49ad3c4e5ccee8bd6c740a2bc24561b8284c06b5183ffed04a","abstract_canon_sha256":"c373871f1315eeecb3d6d96f2ae6052041c7d8fe9d44389c4f7d60adfcac880f"},"schema_version":"1.0"},"canonical_sha256":"8993f62e4adb0ae2470f8bd71d8bc8bf2dbb65d0d4ac4113ee07120a21628766","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:59.710949Z","signature_b64":"Cm/MiBBYS/lqaKFg0t6iIEyBk3jb2vnn2MeTxf/7fYPQWheurL2GjQh7XSykYjMRJWbEcHcTbCmT22s0OGnfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8993f62e4adb0ae2470f8bd71d8bc8bf2dbb65d0d4ac4113ee07120a21628766","last_reissued_at":"2026-07-05T08:54:59.710520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:59.710520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.06610","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":"2026-07-05T08:54:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VsALjLzOKYpW5Hd5zXiL9Xb3GPfaKRSjaHBtAb7GSs6UNjWeR1xYe9Q7yQqXYLGpqTlQP8+rtpSqXXBVBEJ1DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T12:45:56.394887Z"},"content_sha256":"10b4d2e2940a293531220639e1191ada0ff372b50a8b2ac829a7d7e826e1c75a","schema_version":"1.0","event_id":"sha256:10b4d2e2940a293531220639e1191ada0ff372b50a8b2ac829a7d7e826e1c75a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RGJ7MLSK3MFOERYPRPLR3C6IX4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CROME: Cross-Modal Adapters for Efficient Multimodal LLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Sayna Ebrahimi, Sercan O. Arik, Tejas Nama, Tomas Pfister","submitted_at":"2024-08-13T03:45:11Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) demonstrate remarkable image-language capabilities, but their widespread use faces challenges in cost-effective training and adaptation. Existing approaches often necessitate expensive language model retraining and limited adaptability. Additionally, the current focus on zero-shot performance improvements offers insufficient guidance for task-specific tuning. We propose CROME, an efficient vision-language instruction tuning framework. It features a novel gated cross-modal adapter that effectively combines visual and textual representations prior to inpu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06610","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/2408.06610/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":"2026-07-05T08:54:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aIbBT86H3b5pFIEq4ZnY/4ZqHG2edxNwc7gTAiwjBiFwPjTN5UHjbg3uitf1oMyg2R3q7ALRa5cT5Ld+fr4OBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T12:45:56.395268Z"},"content_sha256":"9d86d97876689bfc61bac03050bca87c6230e39a17876ce4a81ae6525c700da9","schema_version":"1.0","event_id":"sha256:9d86d97876689bfc61bac03050bca87c6230e39a17876ce4a81ae6525c700da9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RGJ7MLSK3MFOERYPRPLR3C6IX4/bundle.json","state_url":"https://pith.science/pith/RGJ7MLSK3MFOERYPRPLR3C6IX4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RGJ7MLSK3MFOERYPRPLR3C6IX4/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":"2026-07-08T12:45:56Z","links":{"resolver":"https://pith.science/pith/RGJ7MLSK3MFOERYPRPLR3C6IX4","bundle":"https://pith.science/pith/RGJ7MLSK3MFOERYPRPLR3C6IX4/bundle.json","state":"https://pith.science/pith/RGJ7MLSK3MFOERYPRPLR3C6IX4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RGJ7MLSK3MFOERYPRPLR3C6IX4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RGJ7MLSK3MFOERYPRPLR3C6IX4","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":"c373871f1315eeecb3d6d96f2ae6052041c7d8fe9d44389c4f7d60adfcac880f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T03:45:11Z","title_canon_sha256":"5a56854ab0bd4f49ad3c4e5ccee8bd6c740a2bc24561b8284c06b5183ffed04a"},"schema_version":"1.0","source":{"id":"2408.06610","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06610","created_at":"2026-07-05T08:54:59Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06610v1","created_at":"2026-07-05T08:54:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06610","created_at":"2026-07-05T08:54:59Z"},{"alias_kind":"pith_short_12","alias_value":"RGJ7MLSK3MFO","created_at":"2026-07-05T08:54:59Z"},{"alias_kind":"pith_short_16","alias_value":"RGJ7MLSK3MFOERYP","created_at":"2026-07-05T08:54:59Z"},{"alias_kind":"pith_short_8","alias_value":"RGJ7MLSK","created_at":"2026-07-05T08:54:59Z"}],"graph_snapshots":[{"event_id":"sha256:9d86d97876689bfc61bac03050bca87c6230e39a17876ce4a81ae6525c700da9","target":"graph","created_at":"2026-07-05T08:54:59Z","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/2408.06610/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) demonstrate remarkable image-language capabilities, but their widespread use faces challenges in cost-effective training and adaptation. Existing approaches often necessitate expensive language model retraining and limited adaptability. Additionally, the current focus on zero-shot performance improvements offers insufficient guidance for task-specific tuning. We propose CROME, an efficient vision-language instruction tuning framework. It features a novel gated cross-modal adapter that effectively combines visual and textual representations prior to inpu","authors_text":"Sayna Ebrahimi, Sercan O. Arik, Tejas Nama, Tomas Pfister","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T03:45:11Z","title":"CROME: Cross-Modal Adapters for Efficient Multimodal LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06610","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":"sha256:10b4d2e2940a293531220639e1191ada0ff372b50a8b2ac829a7d7e826e1c75a","target":"record","created_at":"2026-07-05T08:54:59Z","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":"c373871f1315eeecb3d6d96f2ae6052041c7d8fe9d44389c4f7d60adfcac880f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T03:45:11Z","title_canon_sha256":"5a56854ab0bd4f49ad3c4e5ccee8bd6c740a2bc24561b8284c06b5183ffed04a"},"schema_version":"1.0","source":{"id":"2408.06610","kind":"arxiv","version":1}},"canonical_sha256":"8993f62e4adb0ae2470f8bd71d8bc8bf2dbb65d0d4ac4113ee07120a21628766","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8993f62e4adb0ae2470f8bd71d8bc8bf2dbb65d0d4ac4113ee07120a21628766","first_computed_at":"2026-07-05T08:54:59.710520Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:54:59.710520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cm/MiBBYS/lqaKFg0t6iIEyBk3jb2vnn2MeTxf/7fYPQWheurL2GjQh7XSykYjMRJWbEcHcTbCmT22s0OGnfDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:54:59.710949Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.06610","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10b4d2e2940a293531220639e1191ada0ff372b50a8b2ac829a7d7e826e1c75a","sha256:9d86d97876689bfc61bac03050bca87c6230e39a17876ce4a81ae6525c700da9"],"state_sha256":"d7c3b22bcc698bb002985a5a3ff2a26b4df581d2de94a06211a97449815078aa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6F3u/oqk/9IhACXkJXcPoszwoL18nVc6Q5BDv8HlZGG9GV4N9Vl0tObsG61YalRhxTUX0sZGmNW36yJo0s9iCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T12:45:56.399411Z","bundle_sha256":"6d4659e10f8ae38052fb88fe2a84ca561467077bb819aed0fe2a3dafb2aa9bdd"}}