{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z4LEITEJSP34TTCZOUQJX774CI","short_pith_number":"pith:Z4LEITEJ","schema_version":"1.0","canonical_sha256":"cf16444c8993f7c9cc5975209bfffc1237c387fc3dd03eb1bd191ee76db88ed8","source":{"kind":"arxiv","id":"2605.12872","version":1},"attestation_state":"computed","paper":{"title":"SMA: Submodular Modality Aligner For Data Efficient Multimodal Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"SMA aligns images and text by optimizing submodular mutual information over sets of descriptions rather than individual pairs, enabling strong zero-shot performance with only tens of thousands of samples.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anay Majee, Rishabh Iyer, Truong Pham","submitted_at":"2026-05-13T01:36:43Z","abstract_excerpt":"Despite the recent success of Multimodal Foundation Models (FMs), their reliance on massive paired datasets limits their applicability in low-data and rare-scenario settings where aligned data is scarce and expensive. A key bottleneck is the adoption of an instance-level formulation, which learns alignment by maximizing correlation between individual image-text pairs while neglecting the underlying geometric structure across modalities resulting in a modality gap across input modalities. In this paper, we propose a combinatorial paradigm for multimodal alignment that moves beyond pairwise lear"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.12872","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T01:36:43Z","cross_cats_sorted":[],"title_canon_sha256":"856537fdd4622b11ff2f965a6dfccd2428f52aac6093ff3c5b115f0a56176d62","abstract_canon_sha256":"37d5a4f6f6b6911af0a05b1e4044f37883fd1a23a1b84f1c93f8e54194e3ba4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:11.310326Z","signature_b64":"QemppQEjGbDDy8AHWLidV6Iuwq7I+AiosMiaHI2Ym/vKh4UwKHOZwY1nDOly0Lia+h4oKEkc/I5J2KL/m+VDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf16444c8993f7c9cc5975209bfffc1237c387fc3dd03eb1bd191ee76db88ed8","last_reissued_at":"2026-05-18T03:09:11.309725Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:11.309725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMA: Submodular Modality Aligner For Data Efficient Multimodal Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"SMA aligns images and text by optimizing submodular mutual information over sets of descriptions rather than individual pairs, enabling strong zero-shot performance with only tens of thousands of samples.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anay Majee, Rishabh Iyer, Truong Pham","submitted_at":"2026-05-13T01:36:43Z","abstract_excerpt":"Despite the recent success of Multimodal Foundation Models (FMs), their reliance on massive paired datasets limits their applicability in low-data and rare-scenario settings where aligned data is scarce and expensive. A key bottleneck is the adoption of an instance-level formulation, which learns alignment by maximizing correlation between individual image-text pairs while neglecting the underlying geometric structure across modalities resulting in a modality gap across input modalities. In this paper, we propose a combinatorial paradigm for multimodal alignment that moves beyond pairwise lear"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"SMA achieves strong multimodal generalization using only tens of thousands of samples. This is orders of magnitude fewer than standard approaches.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the set-based formulation with submodular mutual information captures richer cross-modal geometric structure and effectively utilizes multiple positive associations without introducing biases or requiring extensive post-hoc tuning that affects the reported gains.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SMA uses a submodular mutual information objective on data sets to deliver competitive zero-shot classification and retrieval performance on CLIP benchmarks with only tens of thousands of samples, orders of magnitude fewer than standard approaches.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SMA aligns images and text by optimizing submodular mutual information over sets of descriptions rather than individual pairs, enabling strong zero-shot performance with only tens of thousands of samples.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4e1704971da14415c7088e0a800e567c6c9ecf21f815d7685ecb04c04fdccea9"},"source":{"id":"2605.12872","kind":"arxiv","version":1},"verdict":{"id":"cca2a51a-d698-480c-944c-647333612a5b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:28:21.138946Z","strongest_claim":"SMA achieves strong multimodal generalization using only tens of thousands of samples. This is orders of magnitude fewer than standard approaches.","one_line_summary":"SMA uses a submodular mutual information objective on data sets to deliver competitive zero-shot classification and retrieval performance on CLIP benchmarks with only tens of thousands of samples, orders of magnitude fewer than standard approaches.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the set-based formulation with submodular mutual information captures richer cross-modal geometric structure and effectively utilizes multiple positive associations without introducing biases or requiring extensive post-hoc tuning that affects the reported gains.","pith_extraction_headline":"SMA aligns images and text by optimizing submodular mutual information over sets of descriptions rather than individual pairs, enabling strong zero-shot performance with only tens of thousands of samples."},"references":{"count":54,"sample":[{"doi":"","year":2026,"title":"Liteembed: Adapting clip to rare classes, 2026","work_id":"797ef698-5fd1-44b3-a38c-c6748e0bc479","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Theoretical analysis of submodular information measures for targeted data subset selection.ArXiv, abs/2402.13454, 2024","work_id":"8bdfc0a7-ae56-4245-bdf7-5394f7e823f8","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"arXiv preprint arXiv:2106.15324 , year=","work_id":"9e312208-7e3a-4663-ab37-1d9cc653c348","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Submodularity in machine learning and artificial intelligence","work_id":"83a2d723-7834-4f2a-a012-e49eae74b5c5","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2002,"title":"A Simple Framework for Contrastive Learning of Visual Representations","work_id":"77d995ce-c44e-4692-9c54-cf8ce771464a","ref_index":5,"cited_arxiv_id":"2002.05709","is_internal_anchor":true}],"resolved_work":54,"snapshot_sha256":"e71b506350c44a0670cbbd0109066f8555609e414a443a92e123ae756e78777e","internal_anchors":5},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4d4512cc3b4b824f742f870a1403d8342de3aae4e79768480a484bc57141d2d4"},"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":"2605.12872","created_at":"2026-05-18T03:09:11.309820+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12872v1","created_at":"2026-05-18T03:09:11.309820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12872","created_at":"2026-05-18T03:09:11.309820+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4LEITEJSP34","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4LEITEJSP34TTCZ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4LEITEJ","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z4LEITEJSP34TTCZOUQJX774CI","json":"https://pith.science/pith/Z4LEITEJSP34TTCZOUQJX774CI.json","graph_json":"https://pith.science/api/pith-number/Z4LEITEJSP34TTCZOUQJX774CI/graph.json","events_json":"https://pith.science/api/pith-number/Z4LEITEJSP34TTCZOUQJX774CI/events.json","paper":"https://pith.science/paper/Z4LEITEJ"},"agent_actions":{"view_html":"https://pith.science/pith/Z4LEITEJSP34TTCZOUQJX774CI","download_json":"https://pith.science/pith/Z4LEITEJSP34TTCZOUQJX774CI.json","view_paper":"https://pith.science/paper/Z4LEITEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12872&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4LEITEJSP34TTCZOUQJX774CI/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4LEITEJSP34TTCZOUQJX774CI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4LEITEJSP34TTCZOUQJX774CI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4LEITEJSP34TTCZOUQJX774CI/action/storage_attestation","attest_author":"https://pith.science/pith/Z4LEITEJSP34TTCZOUQJX774CI/action/author_attestation","sign_citation":"https://pith.science/pith/Z4LEITEJSP34TTCZOUQJX774CI/action/citation_signature","submit_replication":"https://pith.science/pith/Z4LEITEJSP34TTCZOUQJX774CI/action/replication_record"}},"created_at":"2026-05-18T03:09:11.309820+00:00","updated_at":"2026-05-18T03:09:11.309820+00:00"}