{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SWIGSIWIH3KPXUE7XIESG73EIV","short_pith_number":"pith:SWIGSIWI","schema_version":"1.0","canonical_sha256":"95906922c83ed4fbd09fba09237f6445508845c9ea7da56f51b6b3f591385cc4","source":{"kind":"arxiv","id":"2309.14118","version":2},"attestation_state":"computed","paper":{"title":"MultiModN- Multimodal, Multi-Task, Interpretable Modular Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jibril Frej, Malika Satayeva, Martin Jaggi, Mary-Anne Hartley, Tanja K\\\"aser, Thierry Bossy, Thijs Vogels, Vinitra Swamy","submitted_at":"2023-09-25T13:16:57Z","abstract_excerpt":"Predicting multiple real-world tasks in a single model often requires a particularly diverse feature space. Multimodal (MM) models aim to extract the synergistic predictive potential of multiple data types to create a shared feature space with aligned semantic meaning across inputs of drastically varying sizes (i.e. images, text, sound). Most current MM architectures fuse these representations in parallel, which not only limits their interpretability but also creates a dependency on modality availability. We present MultiModN, a multimodal, modular network that fuses latent representations in "},"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":"2309.14118","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-25T13:16:57Z","cross_cats_sorted":[],"title_canon_sha256":"93dd259d21098b7b1a17f3d80e8b329c5c8f095395317c7c59946e88e4c8d236","abstract_canon_sha256":"af44deca6751d079142faf009812982039d13c251f742babc89161ab1919597c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:31.450649Z","signature_b64":"x+EvH5yjCbyA3vicMbdHpWrBpyUwuHHbVQIuTTbaxsUwQRTqC6SQTsTiq6lBzg6a5Q2Qa4sHWy8bF43N1IP3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95906922c83ed4fbd09fba09237f6445508845c9ea7da56f51b6b3f591385cc4","last_reissued_at":"2026-07-05T07:09:31.450117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:31.450117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MultiModN- Multimodal, Multi-Task, Interpretable Modular Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jibril Frej, Malika Satayeva, Martin Jaggi, Mary-Anne Hartley, Tanja K\\\"aser, Thierry Bossy, Thijs Vogels, Vinitra Swamy","submitted_at":"2023-09-25T13:16:57Z","abstract_excerpt":"Predicting multiple real-world tasks in a single model often requires a particularly diverse feature space. Multimodal (MM) models aim to extract the synergistic predictive potential of multiple data types to create a shared feature space with aligned semantic meaning across inputs of drastically varying sizes (i.e. images, text, sound). Most current MM architectures fuse these representations in parallel, which not only limits their interpretability but also creates a dependency on modality availability. We present MultiModN, a multimodal, modular network that fuses latent representations in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.14118","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/2309.14118/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":"2309.14118","created_at":"2026-07-05T07:09:31.450180+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.14118v2","created_at":"2026-07-05T07:09:31.450180+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.14118","created_at":"2026-07-05T07:09:31.450180+00:00"},{"alias_kind":"pith_short_12","alias_value":"SWIGSIWIH3KP","created_at":"2026-07-05T07:09:31.450180+00:00"},{"alias_kind":"pith_short_16","alias_value":"SWIGSIWIH3KPXUE7","created_at":"2026-07-05T07:09:31.450180+00:00"},{"alias_kind":"pith_short_8","alias_value":"SWIGSIWI","created_at":"2026-07-05T07:09:31.450180+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/SWIGSIWIH3KPXUE7XIESG73EIV","json":"https://pith.science/pith/SWIGSIWIH3KPXUE7XIESG73EIV.json","graph_json":"https://pith.science/api/pith-number/SWIGSIWIH3KPXUE7XIESG73EIV/graph.json","events_json":"https://pith.science/api/pith-number/SWIGSIWIH3KPXUE7XIESG73EIV/events.json","paper":"https://pith.science/paper/SWIGSIWI"},"agent_actions":{"view_html":"https://pith.science/pith/SWIGSIWIH3KPXUE7XIESG73EIV","download_json":"https://pith.science/pith/SWIGSIWIH3KPXUE7XIESG73EIV.json","view_paper":"https://pith.science/paper/SWIGSIWI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.14118&json=true","fetch_graph":"https://pith.science/api/pith-number/SWIGSIWIH3KPXUE7XIESG73EIV/graph.json","fetch_events":"https://pith.science/api/pith-number/SWIGSIWIH3KPXUE7XIESG73EIV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SWIGSIWIH3KPXUE7XIESG73EIV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SWIGSIWIH3KPXUE7XIESG73EIV/action/storage_attestation","attest_author":"https://pith.science/pith/SWIGSIWIH3KPXUE7XIESG73EIV/action/author_attestation","sign_citation":"https://pith.science/pith/SWIGSIWIH3KPXUE7XIESG73EIV/action/citation_signature","submit_replication":"https://pith.science/pith/SWIGSIWIH3KPXUE7XIESG73EIV/action/replication_record"}},"created_at":"2026-07-05T07:09:31.450180+00:00","updated_at":"2026-07-05T07:09:31.450180+00:00"}