{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SX27NOVPNSQFPMPBKPKQMEARGG","short_pith_number":"pith:SX27NOVP","schema_version":"1.0","canonical_sha256":"95f5f6baaf6ca057b1e153d506101131bfb5d7e0249b809edfa4aac2da7418ec","source":{"kind":"arxiv","id":"2401.03149","version":3},"attestation_state":"computed","paper":{"title":"CaMML: Context-Aware Multimodal Learner for Large Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Li, Boran Han, Shuai Zhang, Tong He, Yixin Chen","submitted_at":"2024-01-06T07:54:58Z","abstract_excerpt":"In this work, we introduce Context-Aware MultiModal Learner (CaMML), for tuning large multimodal models (LMMs). CaMML, a lightweight module, is crafted to seamlessly integrate multimodal contextual samples into large models, thereby empowering the model to derive knowledge from analogous, domain-specific, up-to-date information and make grounded inferences. Importantly, CaMML is highly scalable and can efficiently handle lengthy multimodal context examples owing to its hierarchical design. Based on CaMML, we have developed two multimodal models, CaMML-7B and CaMML-13B, that have shown exceptio"},"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":"2401.03149","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-06T07:54:58Z","cross_cats_sorted":[],"title_canon_sha256":"d1111712e68011ea0cbb4b6da09aeec21cc13f387d0fe5e119b4882d99c91613","abstract_canon_sha256":"57783cf45fb7f709416ec5014d01bc294150568fc19ef8d60ae59ed4e172e2d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:09.673536Z","signature_b64":"ns93RKPuyzFupNzX06hF1ZSMS/GsUABFk1+f6s10eQoyJd7+brlx6aG85lmJ6bBkVhV1v1t24mJHkHp81zcEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95f5f6baaf6ca057b1e153d506101131bfb5d7e0249b809edfa4aac2da7418ec","last_reissued_at":"2026-07-05T08:34:09.672239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:09.672239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CaMML: Context-Aware Multimodal Learner for Large Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Li, Boran Han, Shuai Zhang, Tong He, Yixin Chen","submitted_at":"2024-01-06T07:54:58Z","abstract_excerpt":"In this work, we introduce Context-Aware MultiModal Learner (CaMML), for tuning large multimodal models (LMMs). CaMML, a lightweight module, is crafted to seamlessly integrate multimodal contextual samples into large models, thereby empowering the model to derive knowledge from analogous, domain-specific, up-to-date information and make grounded inferences. Importantly, CaMML is highly scalable and can efficiently handle lengthy multimodal context examples owing to its hierarchical design. Based on CaMML, we have developed two multimodal models, CaMML-7B and CaMML-13B, that have shown exceptio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03149","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/2401.03149/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":"2401.03149","created_at":"2026-07-05T08:34:09.672306+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.03149v3","created_at":"2026-07-05T08:34:09.672306+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03149","created_at":"2026-07-05T08:34:09.672306+00:00"},{"alias_kind":"pith_short_12","alias_value":"SX27NOVPNSQF","created_at":"2026-07-05T08:34:09.672306+00:00"},{"alias_kind":"pith_short_16","alias_value":"SX27NOVPNSQFPMPB","created_at":"2026-07-05T08:34:09.672306+00:00"},{"alias_kind":"pith_short_8","alias_value":"SX27NOVP","created_at":"2026-07-05T08:34:09.672306+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.12263","citing_title":"Region-Level Context-Aware Multimodal Understanding","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SX27NOVPNSQFPMPBKPKQMEARGG","json":"https://pith.science/pith/SX27NOVPNSQFPMPBKPKQMEARGG.json","graph_json":"https://pith.science/api/pith-number/SX27NOVPNSQFPMPBKPKQMEARGG/graph.json","events_json":"https://pith.science/api/pith-number/SX27NOVPNSQFPMPBKPKQMEARGG/events.json","paper":"https://pith.science/paper/SX27NOVP"},"agent_actions":{"view_html":"https://pith.science/pith/SX27NOVPNSQFPMPBKPKQMEARGG","download_json":"https://pith.science/pith/SX27NOVPNSQFPMPBKPKQMEARGG.json","view_paper":"https://pith.science/paper/SX27NOVP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.03149&json=true","fetch_graph":"https://pith.science/api/pith-number/SX27NOVPNSQFPMPBKPKQMEARGG/graph.json","fetch_events":"https://pith.science/api/pith-number/SX27NOVPNSQFPMPBKPKQMEARGG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SX27NOVPNSQFPMPBKPKQMEARGG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SX27NOVPNSQFPMPBKPKQMEARGG/action/storage_attestation","attest_author":"https://pith.science/pith/SX27NOVPNSQFPMPBKPKQMEARGG/action/author_attestation","sign_citation":"https://pith.science/pith/SX27NOVPNSQFPMPBKPKQMEARGG/action/citation_signature","submit_replication":"https://pith.science/pith/SX27NOVPNSQFPMPBKPKQMEARGG/action/replication_record"}},"created_at":"2026-07-05T08:34:09.672306+00:00","updated_at":"2026-07-05T08:34:09.672306+00:00"}