{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WABN624UPX3FU6HFE45LYFU4SU","short_pith_number":"pith:WABN624U","schema_version":"1.0","canonical_sha256":"b002df6b947df65a78e5273abc169c9506244fc2a075d61208c0f1a227eb50cf","source":{"kind":"arxiv","id":"2405.17613","version":2},"attestation_state":"computed","paper":{"title":"Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Divyam Madaan, Kyunghyun Cho, Sumit Chopra, Taro Makino","submitted_at":"2024-05-27T19:22:41Z","abstract_excerpt":"Supervised multi-modal learning involves mapping multiple modalities to a target label. Previous studies in this field have concentrated on capturing in isolation either the inter-modality dependencies (the relationships between different modalities and the label) or the intra-modality dependencies (the relationships within a single modality and the label). We argue that these conventional approaches that rely solely on either inter- or intra-modality dependencies may not be optimal in general. We view the multi-modal learning problem from the lens of generative models where we consider the ta"},"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":"2405.17613","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T19:22:41Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"64ab027ca068260a5abb98d8fd66433f14ccfc2440f084c151dbc08f4ccab2c6","abstract_canon_sha256":"ecfdf515374a4fee4ac9426d717430f611aca0398434be4d774529a2d8ded798"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:10.352233Z","signature_b64":"Da5onO+333s16/MacAHFTscvn8O+ZZLYBlZFj/1a4qzi35lbpa0Bv3AVct/waaT7666zCdlPCLUiMsqjFMjVCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b002df6b947df65a78e5273abc169c9506244fc2a075d61208c0f1a227eb50cf","last_reissued_at":"2026-07-05T09:45:10.351689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:10.351689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Divyam Madaan, Kyunghyun Cho, Sumit Chopra, Taro Makino","submitted_at":"2024-05-27T19:22:41Z","abstract_excerpt":"Supervised multi-modal learning involves mapping multiple modalities to a target label. Previous studies in this field have concentrated on capturing in isolation either the inter-modality dependencies (the relationships between different modalities and the label) or the intra-modality dependencies (the relationships within a single modality and the label). We argue that these conventional approaches that rely solely on either inter- or intra-modality dependencies may not be optimal in general. We view the multi-modal learning problem from the lens of generative models where we consider the ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17613","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/2405.17613/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":"2405.17613","created_at":"2026-07-05T09:45:10.351745+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17613v2","created_at":"2026-07-05T09:45:10.351745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17613","created_at":"2026-07-05T09:45:10.351745+00:00"},{"alias_kind":"pith_short_12","alias_value":"WABN624UPX3F","created_at":"2026-07-05T09:45:10.351745+00:00"},{"alias_kind":"pith_short_16","alias_value":"WABN624UPX3FU6HF","created_at":"2026-07-05T09:45:10.351745+00:00"},{"alias_kind":"pith_short_8","alias_value":"WABN624U","created_at":"2026-07-05T09:45:10.351745+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WABN624UPX3FU6HFE45LYFU4SU","json":"https://pith.science/pith/WABN624UPX3FU6HFE45LYFU4SU.json","graph_json":"https://pith.science/api/pith-number/WABN624UPX3FU6HFE45LYFU4SU/graph.json","events_json":"https://pith.science/api/pith-number/WABN624UPX3FU6HFE45LYFU4SU/events.json","paper":"https://pith.science/paper/WABN624U"},"agent_actions":{"view_html":"https://pith.science/pith/WABN624UPX3FU6HFE45LYFU4SU","download_json":"https://pith.science/pith/WABN624UPX3FU6HFE45LYFU4SU.json","view_paper":"https://pith.science/paper/WABN624U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17613&json=true","fetch_graph":"https://pith.science/api/pith-number/WABN624UPX3FU6HFE45LYFU4SU/graph.json","fetch_events":"https://pith.science/api/pith-number/WABN624UPX3FU6HFE45LYFU4SU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WABN624UPX3FU6HFE45LYFU4SU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WABN624UPX3FU6HFE45LYFU4SU/action/storage_attestation","attest_author":"https://pith.science/pith/WABN624UPX3FU6HFE45LYFU4SU/action/author_attestation","sign_citation":"https://pith.science/pith/WABN624UPX3FU6HFE45LYFU4SU/action/citation_signature","submit_replication":"https://pith.science/pith/WABN624UPX3FU6HFE45LYFU4SU/action/replication_record"}},"created_at":"2026-07-05T09:45:10.351745+00:00","updated_at":"2026-07-05T09:45:10.351745+00:00"}