{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:I4LLZRK2FQJEFZIRH26LAHOPGA","short_pith_number":"pith:I4LLZRK2","schema_version":"1.0","canonical_sha256":"4716bcc55a2c1242e5113ebcb01dcf3032c2fc124ffe9898e727a7382abfd199","source":{"kind":"arxiv","id":"2306.04539","version":2},"attestation_state":"computed","paper":{"title":"Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Obolenskiy, Alex Wilf, Chun Kai Ling, Louis-Philippe Morency, Paul Pu Liang, Rohan Pandey, Ruslan Salakhutdinov, Yudong Liu, Yun Cheng","submitted_at":"2023-06-07T15:44:53Z","abstract_excerpt":"In many machine learning systems that jointly learn from multiple modalities, a core research question is to understand the nature of multimodal interactions: how modalities combine to provide new task-relevant information that was not present in either alone. We study this challenge of interaction quantification in a semi-supervised setting with only labeled unimodal data and naturally co-occurring multimodal data (e.g., unlabeled images and captions, video and corresponding audio) but when labeling them is time-consuming. Using a precise information-theoretic definition of interactions, our "},"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":"2306.04539","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-07T15:44:53Z","cross_cats_sorted":["cs.CL","cs.CV","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"9b4fe778c7b4330704aec5a692d917e64640b0951a28673db01f1e436d9e8357","abstract_canon_sha256":"1d4b3d9d0783f4c848068d0c6b2e38e9823656001000d31c304c882a6d94aef6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:04.072131Z","signature_b64":"WcplRYZuUC1gqWTm660+4REZ/TEV+RHK81zywOdhj1HYFT0llzUsG2Vv9k0lZqnfAj2R6oB51rWaxpk4NsqpBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4716bcc55a2c1242e5113ebcb01dcf3032c2fc124ffe9898e727a7382abfd199","last_reissued_at":"2026-07-05T08:31:04.071645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:04.071645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Obolenskiy, Alex Wilf, Chun Kai Ling, Louis-Philippe Morency, Paul Pu Liang, Rohan Pandey, Ruslan Salakhutdinov, Yudong Liu, Yun Cheng","submitted_at":"2023-06-07T15:44:53Z","abstract_excerpt":"In many machine learning systems that jointly learn from multiple modalities, a core research question is to understand the nature of multimodal interactions: how modalities combine to provide new task-relevant information that was not present in either alone. We study this challenge of interaction quantification in a semi-supervised setting with only labeled unimodal data and naturally co-occurring multimodal data (e.g., unlabeled images and captions, video and corresponding audio) but when labeling them is time-consuming. Using a precise information-theoretic definition of interactions, our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04539","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/2306.04539/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":"2306.04539","created_at":"2026-07-05T08:31:04.071697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04539v2","created_at":"2026-07-05T08:31:04.071697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04539","created_at":"2026-07-05T08:31:04.071697+00:00"},{"alias_kind":"pith_short_12","alias_value":"I4LLZRK2FQJE","created_at":"2026-07-05T08:31:04.071697+00:00"},{"alias_kind":"pith_short_16","alias_value":"I4LLZRK2FQJEFZIR","created_at":"2026-07-05T08:31:04.071697+00:00"},{"alias_kind":"pith_short_8","alias_value":"I4LLZRK2","created_at":"2026-07-05T08:31:04.071697+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11614","citing_title":"Information-Theoretic Decomposition for Multimodal Interaction Learning","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I4LLZRK2FQJEFZIRH26LAHOPGA","json":"https://pith.science/pith/I4LLZRK2FQJEFZIRH26LAHOPGA.json","graph_json":"https://pith.science/api/pith-number/I4LLZRK2FQJEFZIRH26LAHOPGA/graph.json","events_json":"https://pith.science/api/pith-number/I4LLZRK2FQJEFZIRH26LAHOPGA/events.json","paper":"https://pith.science/paper/I4LLZRK2"},"agent_actions":{"view_html":"https://pith.science/pith/I4LLZRK2FQJEFZIRH26LAHOPGA","download_json":"https://pith.science/pith/I4LLZRK2FQJEFZIRH26LAHOPGA.json","view_paper":"https://pith.science/paper/I4LLZRK2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04539&json=true","fetch_graph":"https://pith.science/api/pith-number/I4LLZRK2FQJEFZIRH26LAHOPGA/graph.json","fetch_events":"https://pith.science/api/pith-number/I4LLZRK2FQJEFZIRH26LAHOPGA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I4LLZRK2FQJEFZIRH26LAHOPGA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I4LLZRK2FQJEFZIRH26LAHOPGA/action/storage_attestation","attest_author":"https://pith.science/pith/I4LLZRK2FQJEFZIRH26LAHOPGA/action/author_attestation","sign_citation":"https://pith.science/pith/I4LLZRK2FQJEFZIRH26LAHOPGA/action/citation_signature","submit_replication":"https://pith.science/pith/I4LLZRK2FQJEFZIRH26LAHOPGA/action/replication_record"}},"created_at":"2026-07-05T08:31:04.071697+00:00","updated_at":"2026-07-05T08:31:04.071697+00:00"}