{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NML4NKJS2E3IN34I5XCUXLPKS2","short_pith_number":"pith:NML4NKJS","canonical_record":{"source":{"id":"2402.01828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T18:23:09Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"145d06f4bf585624fc84500cf3bfe37f39831c079dccacb958bc5d184e0a088a","abstract_canon_sha256":"73a2c7b02adaf14e40894d0d61b8ab5a4143c75183d2a3ce497542a200905e79"},"schema_version":"1.0"},"canonical_sha256":"6b17c6a932d13686ef88edc54badea96ab326ef5193082acaedb66e859999f51","source":{"kind":"arxiv","id":"2402.01828","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01828","created_at":"2026-07-05T07:42:24Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01828v1","created_at":"2026-07-05T07:42:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01828","created_at":"2026-07-05T07:42:24Z"},{"alias_kind":"pith_short_12","alias_value":"NML4NKJS2E3I","created_at":"2026-07-05T07:42:24Z"},{"alias_kind":"pith_short_16","alias_value":"NML4NKJS2E3IN34I","created_at":"2026-07-05T07:42:24Z"},{"alias_kind":"pith_short_8","alias_value":"NML4NKJS","created_at":"2026-07-05T07:42:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NML4NKJS2E3IN34I5XCUXLPKS2","target":"record","payload":{"canonical_record":{"source":{"id":"2402.01828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T18:23:09Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"145d06f4bf585624fc84500cf3bfe37f39831c079dccacb958bc5d184e0a088a","abstract_canon_sha256":"73a2c7b02adaf14e40894d0d61b8ab5a4143c75183d2a3ce497542a200905e79"},"schema_version":"1.0"},"canonical_sha256":"6b17c6a932d13686ef88edc54badea96ab326ef5193082acaedb66e859999f51","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:24.093018Z","signature_b64":"HeCNj2/RRD6vXbzTWmFAw0j2SJUke93zn1XUa9siQVsQ47ppu9ZpmTo9hEQY7I5sXr1dAEN3BEAqce1gh5EOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b17c6a932d13686ef88edc54badea96ab326ef5193082acaedb66e859999f51","last_reissued_at":"2026-07-05T07:42:24.092538Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:24.092538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.01828","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:42:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nlbISgwzaucPdDilhQ919ze0bxDYUCIgS0HQKx5bCvRKWsndJzKSw88tb0wU+tkd+sHcdbLO77e48rxQq+DlBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:01:34.845887Z"},"content_sha256":"2c9612c52688beeb594fc5d1be7f324cce94782d75a57143f90383d1f04532cc","schema_version":"1.0","event_id":"sha256:2c9612c52688beeb594fc5d1be7f324cce94782d75a57143f90383d1f04532cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NML4NKJS2E3IN34I5XCUXLPKS2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Retrieval Augmented End-to-End Spoken Dialog Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dian Yu, Hagen Soltau, Izhak Shafran, Laurent El Shafey, Mingqiu Wang, Wei Han, Yuan Cao","submitted_at":"2024-02-02T18:23:09Z","abstract_excerpt":"We recently developed SLM, a joint speech and language model, which fuses a pretrained foundational speech model and a large language model (LLM), while preserving the in-context learning capability intrinsic to the pretrained LLM. In this paper, we apply SLM to speech dialog applications where the dialog states are inferred directly from the audio signal.\n  Task-oriented dialogs often contain domain-specific entities, i.e., restaurants, hotels, train stations, and city names, which are difficult to recognize, however, critical for the downstream applications. Inspired by the RAG (retrieval-au"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01828","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/2402.01828/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:42:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QkNWzfhDe5aff9NpKGK43QFOQyCR091dHol6KyhZwKXdYwIGiNnPS/y5G9p8iwv8S8dDuMCbYg3mXjJsYvG9Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:01:34.846423Z"},"content_sha256":"4ba9d163813d1a49f1d77927f6ee7e30d8457fe4abf3775899466d4cb26ddddb","schema_version":"1.0","event_id":"sha256:4ba9d163813d1a49f1d77927f6ee7e30d8457fe4abf3775899466d4cb26ddddb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NML4NKJS2E3IN34I5XCUXLPKS2/bundle.json","state_url":"https://pith.science/pith/NML4NKJS2E3IN34I5XCUXLPKS2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NML4NKJS2E3IN34I5XCUXLPKS2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T03:01:34Z","links":{"resolver":"https://pith.science/pith/NML4NKJS2E3IN34I5XCUXLPKS2","bundle":"https://pith.science/pith/NML4NKJS2E3IN34I5XCUXLPKS2/bundle.json","state":"https://pith.science/pith/NML4NKJS2E3IN34I5XCUXLPKS2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NML4NKJS2E3IN34I5XCUXLPKS2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NML4NKJS2E3IN34I5XCUXLPKS2","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":"73a2c7b02adaf14e40894d0d61b8ab5a4143c75183d2a3ce497542a200905e79","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T18:23:09Z","title_canon_sha256":"145d06f4bf585624fc84500cf3bfe37f39831c079dccacb958bc5d184e0a088a"},"schema_version":"1.0","source":{"id":"2402.01828","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01828","created_at":"2026-07-05T07:42:24Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01828v1","created_at":"2026-07-05T07:42:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01828","created_at":"2026-07-05T07:42:24Z"},{"alias_kind":"pith_short_12","alias_value":"NML4NKJS2E3I","created_at":"2026-07-05T07:42:24Z"},{"alias_kind":"pith_short_16","alias_value":"NML4NKJS2E3IN34I","created_at":"2026-07-05T07:42:24Z"},{"alias_kind":"pith_short_8","alias_value":"NML4NKJS","created_at":"2026-07-05T07:42:24Z"}],"graph_snapshots":[{"event_id":"sha256:4ba9d163813d1a49f1d77927f6ee7e30d8457fe4abf3775899466d4cb26ddddb","target":"graph","created_at":"2026-07-05T07:42:24Z","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/2402.01828/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We recently developed SLM, a joint speech and language model, which fuses a pretrained foundational speech model and a large language model (LLM), while preserving the in-context learning capability intrinsic to the pretrained LLM. In this paper, we apply SLM to speech dialog applications where the dialog states are inferred directly from the audio signal.\n  Task-oriented dialogs often contain domain-specific entities, i.e., restaurants, hotels, train stations, and city names, which are difficult to recognize, however, critical for the downstream applications. Inspired by the RAG (retrieval-au","authors_text":"Dian Yu, Hagen Soltau, Izhak Shafran, Laurent El Shafey, Mingqiu Wang, Wei Han, Yuan Cao","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T18:23:09Z","title":"Retrieval Augmented End-to-End Spoken Dialog Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01828","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":"sha256:2c9612c52688beeb594fc5d1be7f324cce94782d75a57143f90383d1f04532cc","target":"record","created_at":"2026-07-05T07:42:24Z","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":"73a2c7b02adaf14e40894d0d61b8ab5a4143c75183d2a3ce497542a200905e79","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T18:23:09Z","title_canon_sha256":"145d06f4bf585624fc84500cf3bfe37f39831c079dccacb958bc5d184e0a088a"},"schema_version":"1.0","source":{"id":"2402.01828","kind":"arxiv","version":1}},"canonical_sha256":"6b17c6a932d13686ef88edc54badea96ab326ef5193082acaedb66e859999f51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b17c6a932d13686ef88edc54badea96ab326ef5193082acaedb66e859999f51","first_computed_at":"2026-07-05T07:42:24.092538Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:42:24.092538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HeCNj2/RRD6vXbzTWmFAw0j2SJUke93zn1XUa9siQVsQ47ppu9ZpmTo9hEQY7I5sXr1dAEN3BEAqce1gh5EOCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:42:24.093018Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01828","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c9612c52688beeb594fc5d1be7f324cce94782d75a57143f90383d1f04532cc","sha256:4ba9d163813d1a49f1d77927f6ee7e30d8457fe4abf3775899466d4cb26ddddb"],"state_sha256":"94e10ec87e6edf355fe1deb49a675bd8c7b7e859f947dab1c060d6a772462636"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LtErz1fVhagok3Bh2uaM/DPxaI3dzXP/uVTTfzvw8Of8i1M7e8PQR9BQZPIAAYBTF2a0fRvAV3SvLf18g+0jDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:01:34.849746Z","bundle_sha256":"2554e22001dd3b3b017dbe4a26a35072dea8fe03574a43888a19be3447afab82"}}