{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:62MDZFM7VPICFBVU3SXT55IZD3","short_pith_number":"pith:62MDZFM7","schema_version":"1.0","canonical_sha256":"f6983c959fabd02286b4dcaf3ef5191ee68a993559c726d8e4d25f36fdb101cb","source":{"kind":"arxiv","id":"2607.25948","version":1},"attestation_state":"computed","paper":{"title":"MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Afshin Dehghan, Amir Zadeh, Amir Zamir, Chuan Li, David Mizrahi, Fran\\c{c}ois Fleuret, Jesse Allardice, Mingqiao Ye, O\\u{g}uzhan Fatih Kar, Roman Bachmann, Serge Belongie, Xian Liu, Zhaochong An, Zhitong Gao","submitted_at":"2026-07-28T16:34:23Z","abstract_excerpt":"Any-to-any models predict any modality from any combination of others within a single network, a formulation used in multimodal vision and vision-language models, and increasingly in scientific domains such as ecology and astronomy. Existing any-to-any models are typically trained from scratch using encoder-decoder or diffusion architectures, impacting their performance and preventing them from using strong pre-trained decoder-only models as a prior. In this work, we investigate decoder-only any-to-any multimodal modeling, which treats all modalities symmetrically and supports arbitrary modali"},"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":"2607.25948","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-28T16:34:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f27e2d5aa6088aa4ee089529306ac241df96788222b7e8d9adb3cfeaa935ae56","abstract_canon_sha256":"79e308e1c6e358c43b61d64d1b47720d9612736b11ca9119915d8597d5a821d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:26:12.713909Z","signature_b64":"ipkQEMoorDd4N5ROzMkFqPfakXT0mCNFORaMGU5gGsu8aSeWGFojfzpio8ygHirPb8e3IXUv4UwrjGzQ7C6hAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6983c959fabd02286b4dcaf3ef5191ee68a993559c726d8e4d25f36fdb101cb","last_reissued_at":"2026-07-29T01:26:12.712982Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:26:12.712982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Afshin Dehghan, Amir Zadeh, Amir Zamir, Chuan Li, David Mizrahi, Fran\\c{c}ois Fleuret, Jesse Allardice, Mingqiao Ye, O\\u{g}uzhan Fatih Kar, Roman Bachmann, Serge Belongie, Xian Liu, Zhaochong An, Zhitong Gao","submitted_at":"2026-07-28T16:34:23Z","abstract_excerpt":"Any-to-any models predict any modality from any combination of others within a single network, a formulation used in multimodal vision and vision-language models, and increasingly in scientific domains such as ecology and astronomy. Existing any-to-any models are typically trained from scratch using encoder-decoder or diffusion architectures, impacting their performance and preventing them from using strong pre-trained decoder-only models as a prior. In this work, we investigate decoder-only any-to-any multimodal modeling, which treats all modalities symmetrically and supports arbitrary modali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25948","kind":"arxiv","version":1},"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/2607.25948/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":"2607.25948","created_at":"2026-07-29T01:26:12.713454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.25948v1","created_at":"2026-07-29T01:26:12.713454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25948","created_at":"2026-07-29T01:26:12.713454+00:00"},{"alias_kind":"pith_short_12","alias_value":"62MDZFM7VPIC","created_at":"2026-07-29T01:26:12.713454+00:00"},{"alias_kind":"pith_short_16","alias_value":"62MDZFM7VPICFBVU","created_at":"2026-07-29T01:26:12.713454+00:00"},{"alias_kind":"pith_short_8","alias_value":"62MDZFM7","created_at":"2026-07-29T01:26:12.713454+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/62MDZFM7VPICFBVU3SXT55IZD3","json":"https://pith.science/pith/62MDZFM7VPICFBVU3SXT55IZD3.json","graph_json":"https://pith.science/api/pith-number/62MDZFM7VPICFBVU3SXT55IZD3/graph.json","events_json":"https://pith.science/api/pith-number/62MDZFM7VPICFBVU3SXT55IZD3/events.json","paper":"https://pith.science/paper/62MDZFM7"},"agent_actions":{"view_html":"https://pith.science/pith/62MDZFM7VPICFBVU3SXT55IZD3","download_json":"https://pith.science/pith/62MDZFM7VPICFBVU3SXT55IZD3.json","view_paper":"https://pith.science/paper/62MDZFM7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.25948&json=true","fetch_graph":"https://pith.science/api/pith-number/62MDZFM7VPICFBVU3SXT55IZD3/graph.json","fetch_events":"https://pith.science/api/pith-number/62MDZFM7VPICFBVU3SXT55IZD3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/62MDZFM7VPICFBVU3SXT55IZD3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/62MDZFM7VPICFBVU3SXT55IZD3/action/storage_attestation","attest_author":"https://pith.science/pith/62MDZFM7VPICFBVU3SXT55IZD3/action/author_attestation","sign_citation":"https://pith.science/pith/62MDZFM7VPICFBVU3SXT55IZD3/action/citation_signature","submit_replication":"https://pith.science/pith/62MDZFM7VPICFBVU3SXT55IZD3/action/replication_record"}},"created_at":"2026-07-29T01:26:12.713454+00:00","updated_at":"2026-07-29T01:26:12.713454+00:00"}