{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2UCQLK357JGHRQ7ZGEMVMUEENK","short_pith_number":"pith:2UCQLK35","schema_version":"1.0","canonical_sha256":"d50505ab7dfa4c78c3f931195650846abfa32efce7d03c603d2f6b2e9776fed4","source":{"kind":"arxiv","id":"2607.16560","version":1},"attestation_state":"computed","paper":{"title":"From Modalities to Propositions: A Language-Centric Framework for Multimodal Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.AI","authors_text":"Jialiang Wang, Jingde Chen, Jose M. Alvarez, Maying Shen, Nadine Chang, Pavlo Molchanov, Rafid Mahmood, Shizhe Diao, Thomas Breuel","submitted_at":"2026-07-18T00:08:47Z","abstract_excerpt":"We propose a language representation for multimodal data in which any observation, whether image, video, or text, is expressed as a bag of atomic propositions, simple statements about the entities, actions, and relations in a scene. A global semantic codebook unifies these into a shared vocabulary of canonical atomic propositions, placing every modality and observation into one interpretable space that spans fine grained facts to high level concepts and composes into richer ones. This brings interpretability with reasoning, cross-modal understanding and retrieval, and compositionality that ena"},"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":"2607.16560","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-18T00:08:47Z","cross_cats_sorted":["cs.CV","cs.LG","cs.MM"],"title_canon_sha256":"838bd09b733fc705143e98e4356bbcee70bd9ffc25f6597ffda69749b67e3e5a","abstract_canon_sha256":"ce5c4bffebc1201302785cf49f38cfc9a78af9fc3cb6299d68f94bd8d2ca0855"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T00:20:25.419786Z","signature_b64":"knEMe/VqjLC+qMIzSyLcfy6i+S2pteCPvWM1VY0gh0fNnDYDBFbuw1s6dd2+IBPj+XlJK2qfeAg1LZ1VebgyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d50505ab7dfa4c78c3f931195650846abfa32efce7d03c603d2f6b2e9776fed4","last_reissued_at":"2026-07-21T00:20:25.418812Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T00:20:25.418812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Modalities to Propositions: A Language-Centric Framework for Multimodal Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.AI","authors_text":"Jialiang Wang, Jingde Chen, Jose M. Alvarez, Maying Shen, Nadine Chang, Pavlo Molchanov, Rafid Mahmood, Shizhe Diao, Thomas Breuel","submitted_at":"2026-07-18T00:08:47Z","abstract_excerpt":"We propose a language representation for multimodal data in which any observation, whether image, video, or text, is expressed as a bag of atomic propositions, simple statements about the entities, actions, and relations in a scene. A global semantic codebook unifies these into a shared vocabulary of canonical atomic propositions, placing every modality and observation into one interpretable space that spans fine grained facts to high level concepts and composes into richer ones. This brings interpretability with reasoning, cross-modal understanding and retrieval, and compositionality that ena"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16560","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/2607.16560/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":"2607.16560","created_at":"2026-07-21T00:20:25.419247+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.16560v1","created_at":"2026-07-21T00:20:25.419247+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16560","created_at":"2026-07-21T00:20:25.419247+00:00"},{"alias_kind":"pith_short_12","alias_value":"2UCQLK357JGH","created_at":"2026-07-21T00:20:25.419247+00:00"},{"alias_kind":"pith_short_16","alias_value":"2UCQLK357JGHRQ7Z","created_at":"2026-07-21T00:20:25.419247+00:00"},{"alias_kind":"pith_short_8","alias_value":"2UCQLK35","created_at":"2026-07-21T00:20:25.419247+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/2UCQLK357JGHRQ7ZGEMVMUEENK","json":"https://pith.science/pith/2UCQLK357JGHRQ7ZGEMVMUEENK.json","graph_json":"https://pith.science/api/pith-number/2UCQLK357JGHRQ7ZGEMVMUEENK/graph.json","events_json":"https://pith.science/api/pith-number/2UCQLK357JGHRQ7ZGEMVMUEENK/events.json","paper":"https://pith.science/paper/2UCQLK35"},"agent_actions":{"view_html":"https://pith.science/pith/2UCQLK357JGHRQ7ZGEMVMUEENK","download_json":"https://pith.science/pith/2UCQLK357JGHRQ7ZGEMVMUEENK.json","view_paper":"https://pith.science/paper/2UCQLK35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.16560&json=true","fetch_graph":"https://pith.science/api/pith-number/2UCQLK357JGHRQ7ZGEMVMUEENK/graph.json","fetch_events":"https://pith.science/api/pith-number/2UCQLK357JGHRQ7ZGEMVMUEENK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2UCQLK357JGHRQ7ZGEMVMUEENK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2UCQLK357JGHRQ7ZGEMVMUEENK/action/storage_attestation","attest_author":"https://pith.science/pith/2UCQLK357JGHRQ7ZGEMVMUEENK/action/author_attestation","sign_citation":"https://pith.science/pith/2UCQLK357JGHRQ7ZGEMVMUEENK/action/citation_signature","submit_replication":"https://pith.science/pith/2UCQLK357JGHRQ7ZGEMVMUEENK/action/replication_record"}},"created_at":"2026-07-21T00:20:25.419247+00:00","updated_at":"2026-07-21T00:20:25.419247+00:00"}