{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L33PU7T2IMYOKVLUNE6CY6QH2S","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":"52e330f2de0851ade7ed80c8578fc62fd5ce9181a92fcf2a65e6f62b16636b30","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-11T15:24:02Z","title_canon_sha256":"9818acc7ee65be87e23422d8d33bf8e0cd5c7f3ac02d59f82ab64a5851df4748"},"schema_version":"1.0","source":{"id":"2503.08533","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08533","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08533v1","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08533","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"pith_short_12","alias_value":"L33PU7T2IMYO","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"pith_short_16","alias_value":"L33PU7T2IMYOKVLU","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"pith_short_8","alias_value":"L33PU7T2","created_at":"2026-07-05T10:29:01Z"}],"graph_snapshots":[{"event_id":"sha256:c392d604e0e2666cd66774adcf0b998a53ce848b8c53db312c7905174983ea40","target":"graph","created_at":"2026-07-05T10:29:01Z","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/2503.08533/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Advancements in audio foundation models (FMs) have fueled interest in end-to-end (E2E) spoken dialogue systems, but different web interfaces for each system makes it challenging to compare and contrast them effectively. Motivated by this, we introduce an open-source, user-friendly toolkit designed to build unified web interfaces for various cascaded and E2E spoken dialogue systems. Our demo further provides users with the option to get on-the-fly automated evaluation metrics such as (1) latency, (2) ability to understand user input, (3) coherence, diversity, and relevance of system response, a","authors_text":"Emiru Tsunoo, Hayato Futami, Jiatong Shi, Jinchuan Tian, Shikhar Bharadwaj, Shinji Watanabe, Shuichiro Shimizu, Siddhant Arora, Vaibhav Srivastav, William Chen, Yifan Peng, Yosuke Kashiwagi","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-11T15:24:02Z","title":"ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08533","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":"sha256:45d8bccaf7e5d26559cf3d59493f923c5331c20508487e0318c6fe3da8e09d48","target":"record","created_at":"2026-07-05T10:29:01Z","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":"52e330f2de0851ade7ed80c8578fc62fd5ce9181a92fcf2a65e6f62b16636b30","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-11T15:24:02Z","title_canon_sha256":"9818acc7ee65be87e23422d8d33bf8e0cd5c7f3ac02d59f82ab64a5851df4748"},"schema_version":"1.0","source":{"id":"2503.08533","kind":"arxiv","version":1}},"canonical_sha256":"5ef6fa7e7a4330e55574693c2c7a07d4ae0905cf3db9e49be81948877d4929f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ef6fa7e7a4330e55574693c2c7a07d4ae0905cf3db9e49be81948877d4929f0","first_computed_at":"2026-07-05T10:29:01.671287Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:01.671287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sO0ACHIfhS3ywbTWo6UTw88YNUCrJDScSqwlpq5bYuzbpA5gTebp2Xv7gSq3R7HLt3CErxSdwuraJOlnZb5BAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:01.671743Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.08533","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45d8bccaf7e5d26559cf3d59493f923c5331c20508487e0318c6fe3da8e09d48","sha256:c392d604e0e2666cd66774adcf0b998a53ce848b8c53db312c7905174983ea40"],"state_sha256":"e155db1fabd028fa24f4a9de4c68b3893268bb2b056adce0135beadb07309841"}