{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KI7HKTPPP4RXDMB3FA45FC5PAX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9fda0c18f11735fd16038d66c9bd8176a1188577ceb86280a6c8e256258a505b","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-21T03:25:34Z","title_canon_sha256":"9af63ca58f32819503dcc6adf3fa3e5ccb516e29c28c40dfc353448145eff23c"},"schema_version":"1.0","source":{"id":"2607.18666","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18666","created_at":"2026-07-22T00:22:59Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18666v1","created_at":"2026-07-22T00:22:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18666","created_at":"2026-07-22T00:22:59Z"},{"alias_kind":"pith_short_12","alias_value":"KI7HKTPPP4RX","created_at":"2026-07-22T00:22:59Z"},{"alias_kind":"pith_short_16","alias_value":"KI7HKTPPP4RXDMB3","created_at":"2026-07-22T00:22:59Z"},{"alias_kind":"pith_short_8","alias_value":"KI7HKTPP","created_at":"2026-07-22T00:22:59Z"}],"graph_snapshots":[{"event_id":"sha256:05fb0fd317668abb0e0b6d3defc1f81b9084f0b8033a8b61db1a2f2cd3427c79","target":"graph","created_at":"2026-07-22T00:22:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.18666/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A single embedding space that covers text, images, video, and audio lets one index serve every query a user can pose. Embedding models built on vision-language backbones now lead text/image/video retrieval benchmarks but lack audio entirely, while audio-text retrieval is led by specialist systems that serve no other modality. We present the Fusion Embedding family, which adds audio to a frozen vision-language embedding base whose parameters are never updated: generation 1 (fusion-embedding-1) trains only a 16.4M-parameter connector between a frozen audio tower and the frozen base, and generati","authors_text":"Abdul Basit Tonmoy, Arman Luthra, Kazi Fardinul Hoque, Md. Shahrier Islam Arham","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-21T03:25:34Z","title":"Fusion Embedding: A Unified Embedding Space for Text, Image, Video, and Audio"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18666","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b192838dca8043e2687d50b41f35d693ad9703b8b38f4760f6ddacd154f3f587","target":"record","created_at":"2026-07-22T00:22:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9fda0c18f11735fd16038d66c9bd8176a1188577ceb86280a6c8e256258a505b","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-21T03:25:34Z","title_canon_sha256":"9af63ca58f32819503dcc6adf3fa3e5ccb516e29c28c40dfc353448145eff23c"},"schema_version":"1.0","source":{"id":"2607.18666","kind":"arxiv","version":1}},"canonical_sha256":"523e754def7f2371b03b2839d28baf05ce356a4152a9fbbe7fb11733ba8610c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"523e754def7f2371b03b2839d28baf05ce356a4152a9fbbe7fb11733ba8610c4","first_computed_at":"2026-07-22T00:22:59.399682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T00:22:59.399682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g7nCbHbzf77xfD+LZA75OWhLOcUGfnm/N03tomdLbneJVh8l/jBevN44LpRDDJzRipgFKmqVcD12Z3t0Gge0CA==","signature_status":"signed_v1","signed_at":"2026-07-22T00:22:59.400537Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18666","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b192838dca8043e2687d50b41f35d693ad9703b8b38f4760f6ddacd154f3f587","sha256:05fb0fd317668abb0e0b6d3defc1f81b9084f0b8033a8b61db1a2f2cd3427c79"],"state_sha256":"4a224a301bef1cf9f5b2de6ee8f7486666184f33d7bc5bbe284457373e9b62b7"}