{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GNGQ76ZKWTGJ33WOS3DQLEGMDQ","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":"827f99eda7b083912fd3dadafe0ddfd20350284eaf9c0b22b6099a1435323ab8","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-22T22:42:40Z","title_canon_sha256":"6aa8286a004374c5976885b5431827a8f55b15ad6b02cff0e5f9b9f26e15ffa4"},"schema_version":"1.0","source":{"id":"2505.17326","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17326","created_at":"2026-07-05T11:49:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17326v1","created_at":"2026-07-05T11:49:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17326","created_at":"2026-07-05T11:49:54Z"},{"alias_kind":"pith_short_12","alias_value":"GNGQ76ZKWTGJ","created_at":"2026-07-05T11:49:54Z"},{"alias_kind":"pith_short_16","alias_value":"GNGQ76ZKWTGJ33WO","created_at":"2026-07-05T11:49:54Z"},{"alias_kind":"pith_short_8","alias_value":"GNGQ76ZK","created_at":"2026-07-05T11:49:54Z"}],"graph_snapshots":[{"event_id":"sha256:e9b902ee52da10c962e7671870f960d9e29a6a027a58630e8b3a415d06365170","target":"graph","created_at":"2026-07-05T11:49:54Z","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/2505.17326/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce VoxRAG, a modular speech-to-speech retrieval-augmented generation system that bypasses transcription to retrieve semantically relevant audio segments directly from spoken queries. VoxRAG employs silence-aware segmentation, speaker diarization, CLAP audio embeddings, and FAISS retrieval using L2-normalized cosine similarity. We construct a 50-query test set recorded as spoken input by a native English speaker. Retrieval quality was evaluated using LLM-as-a-judge annotations. For very relevant segments, cosine similarity achieved a Recall@10 of 0.34. For somewhat relevant segments, ","authors_text":"Julia Hirschberg, Zackary Rackauckas","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-22T22:42:40Z","title":"VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17326","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:b4b849ec7610adae0ca2b03b8d761ba06ed1b0779f473fc110fb35875778fbea","target":"record","created_at":"2026-07-05T11:49:54Z","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":"827f99eda7b083912fd3dadafe0ddfd20350284eaf9c0b22b6099a1435323ab8","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-22T22:42:40Z","title_canon_sha256":"6aa8286a004374c5976885b5431827a8f55b15ad6b02cff0e5f9b9f26e15ffa4"},"schema_version":"1.0","source":{"id":"2505.17326","kind":"arxiv","version":1}},"canonical_sha256":"334d0ffb2ab4cc9deece96c70590cc1c119f998a1739387ed562ea591e6b6bf2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"334d0ffb2ab4cc9deece96c70590cc1c119f998a1739387ed562ea591e6b6bf2","first_computed_at":"2026-07-05T11:49:54.962710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:54.962710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ifKa4kTmgWe/mZg1rWQKBetoUWZPTu78Ap8YITuvnreo/SL/+CUXpSsiJVByQMOg80NJGBfwQlZMiuSybPVDBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:54.963183Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17326","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4b849ec7610adae0ca2b03b8d761ba06ed1b0779f473fc110fb35875778fbea","sha256:e9b902ee52da10c962e7671870f960d9e29a6a027a58630e8b3a415d06365170"],"state_sha256":"29cefc86892789b474fa9a9c05428c9a89d1bc221d001bfcc053a55063ac03d8"}