{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Q3F2ZTCF6JSMAKNQNEMZAXT336","short_pith_number":"pith:Q3F2ZTCF","canonical_record":{"source":{"id":"2306.07944","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-08T22:33:22Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"7628fcacce49793a085cf26b543c1abb3ed74dd6d5e6944fc558253095d352b2","abstract_canon_sha256":"7bb6e9a4baa1b5d23dff94700292d3d541db2ae9df5d7cad62a40406df21b608"},"schema_version":"1.0"},"canonical_sha256":"86cbaccc45f264c029b06919905e7bdf9637b9e963971ffa928b11ec11e50285","source":{"kind":"arxiv","id":"2306.07944","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07944","created_at":"2026-07-05T06:20:11Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07944v1","created_at":"2026-07-05T06:20:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07944","created_at":"2026-07-05T06:20:11Z"},{"alias_kind":"pith_short_12","alias_value":"Q3F2ZTCF6JSM","created_at":"2026-07-05T06:20:11Z"},{"alias_kind":"pith_short_16","alias_value":"Q3F2ZTCF6JSMAKNQ","created_at":"2026-07-05T06:20:11Z"},{"alias_kind":"pith_short_8","alias_value":"Q3F2ZTCF","created_at":"2026-07-05T06:20:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Q3F2ZTCF6JSMAKNQNEMZAXT336","target":"record","payload":{"canonical_record":{"source":{"id":"2306.07944","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-08T22:33:22Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"7628fcacce49793a085cf26b543c1abb3ed74dd6d5e6944fc558253095d352b2","abstract_canon_sha256":"7bb6e9a4baa1b5d23dff94700292d3d541db2ae9df5d7cad62a40406df21b608"},"schema_version":"1.0"},"canonical_sha256":"86cbaccc45f264c029b06919905e7bdf9637b9e963971ffa928b11ec11e50285","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:11.259384Z","signature_b64":"HjTdGYw0+COp530DKcolra+BEV4hpogSa6RcNw0JEkPUW+SLFApD8nU9hurvtm2fpQ8raIcaJ+VG8Yvg3juDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86cbaccc45f264c029b06919905e7bdf9637b9e963971ffa928b11ec11e50285","last_reissued_at":"2026-07-05T06:20:11.258915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:11.258915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.07944","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":"2026-07-05T06:20:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9kWUkFHI0PAGWSR/KvZ3cjicMNdyBRGJxQPjSljeYGq6cz03AHhG7V83IuOtgMuFYTbs6fO5FUHOBoFeLjonAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:45:33.983405Z"},"content_sha256":"a39c1588da86b2d467f3d613743c6c28c3b1112a8be7857b54d7ac656e68b99e","schema_version":"1.0","event_id":"sha256:a39c1588da86b2d467f3d613743c6c28c3b1112a8be7857b54d7ac656e68b99e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Q3F2ZTCF6JSMAKNQNEMZAXT336","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speech-to-Text Adapter and Speech-to-Entity Retriever Augmented LLMs for Speech Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"eess.AS","authors_text":"Dian Yu, Hagen Soltau, Izhak Shafran, Laurent El Shafey, Mingqiu Wang, Wei Han, Yuan Cao","submitted_at":"2023-06-08T22:33:22Z","abstract_excerpt":"Large Language Models (LLMs) have been applied in the speech domain, often incurring a performance drop due to misaligned between speech and language representations. To bridge this gap, we propose a joint speech and language model (SLM) using a Speech2Text adapter, which maps speech into text token embedding space without speech information loss. Additionally, using a CTC-based blank-filtering, we can reduce the speech sequence length to that of text. In speech MultiWoz dataset (DSTC11 challenge), SLM largely improves the dialog state tracking (DST) performance (24.7% to 28.4% accuracy). Furt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07944","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/2306.07944/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":"2026-07-05T06:20:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LtqtfiOGuNl9SlG9/Te4hny8xc4kEmK4RjkkG9RmFB0mj0JcFCOukvDwO6VoEWe5PRgZVoxyPBc+lg6AGkPXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:45:33.983796Z"},"content_sha256":"3bdbc7858fc32083a5f129f0c43882440cd2c599d04a2bf9629210cdb7801dba","schema_version":"1.0","event_id":"sha256:3bdbc7858fc32083a5f129f0c43882440cd2c599d04a2bf9629210cdb7801dba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q3F2ZTCF6JSMAKNQNEMZAXT336/bundle.json","state_url":"https://pith.science/pith/Q3F2ZTCF6JSMAKNQNEMZAXT336/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q3F2ZTCF6JSMAKNQNEMZAXT336/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":"2026-08-04T01:45:33Z","links":{"resolver":"https://pith.science/pith/Q3F2ZTCF6JSMAKNQNEMZAXT336","bundle":"https://pith.science/pith/Q3F2ZTCF6JSMAKNQNEMZAXT336/bundle.json","state":"https://pith.science/pith/Q3F2ZTCF6JSMAKNQNEMZAXT336/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q3F2ZTCF6JSMAKNQNEMZAXT336/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Q3F2ZTCF6JSMAKNQNEMZAXT336","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":"7bb6e9a4baa1b5d23dff94700292d3d541db2ae9df5d7cad62a40406df21b608","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-08T22:33:22Z","title_canon_sha256":"7628fcacce49793a085cf26b543c1abb3ed74dd6d5e6944fc558253095d352b2"},"schema_version":"1.0","source":{"id":"2306.07944","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07944","created_at":"2026-07-05T06:20:11Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07944v1","created_at":"2026-07-05T06:20:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07944","created_at":"2026-07-05T06:20:11Z"},{"alias_kind":"pith_short_12","alias_value":"Q3F2ZTCF6JSM","created_at":"2026-07-05T06:20:11Z"},{"alias_kind":"pith_short_16","alias_value":"Q3F2ZTCF6JSMAKNQ","created_at":"2026-07-05T06:20:11Z"},{"alias_kind":"pith_short_8","alias_value":"Q3F2ZTCF","created_at":"2026-07-05T06:20:11Z"}],"graph_snapshots":[{"event_id":"sha256:3bdbc7858fc32083a5f129f0c43882440cd2c599d04a2bf9629210cdb7801dba","target":"graph","created_at":"2026-07-05T06:20:11Z","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/2306.07944/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have been applied in the speech domain, often incurring a performance drop due to misaligned between speech and language representations. To bridge this gap, we propose a joint speech and language model (SLM) using a Speech2Text adapter, which maps speech into text token embedding space without speech information loss. Additionally, using a CTC-based blank-filtering, we can reduce the speech sequence length to that of text. In speech MultiWoz dataset (DSTC11 challenge), SLM largely improves the dialog state tracking (DST) performance (24.7% to 28.4% accuracy). Furt","authors_text":"Dian Yu, Hagen Soltau, Izhak Shafran, Laurent El Shafey, Mingqiu Wang, Wei Han, Yuan Cao","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-08T22:33:22Z","title":"Speech-to-Text Adapter and Speech-to-Entity Retriever Augmented LLMs for Speech Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07944","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:a39c1588da86b2d467f3d613743c6c28c3b1112a8be7857b54d7ac656e68b99e","target":"record","created_at":"2026-07-05T06:20:11Z","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":"7bb6e9a4baa1b5d23dff94700292d3d541db2ae9df5d7cad62a40406df21b608","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-08T22:33:22Z","title_canon_sha256":"7628fcacce49793a085cf26b543c1abb3ed74dd6d5e6944fc558253095d352b2"},"schema_version":"1.0","source":{"id":"2306.07944","kind":"arxiv","version":1}},"canonical_sha256":"86cbaccc45f264c029b06919905e7bdf9637b9e963971ffa928b11ec11e50285","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86cbaccc45f264c029b06919905e7bdf9637b9e963971ffa928b11ec11e50285","first_computed_at":"2026-07-05T06:20:11.258915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:11.258915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HjTdGYw0+COp530DKcolra+BEV4hpogSa6RcNw0JEkPUW+SLFApD8nU9hurvtm2fpQ8raIcaJ+VG8Yvg3juDAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:11.259384Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07944","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a39c1588da86b2d467f3d613743c6c28c3b1112a8be7857b54d7ac656e68b99e","sha256:3bdbc7858fc32083a5f129f0c43882440cd2c599d04a2bf9629210cdb7801dba"],"state_sha256":"8674fc180dee16ca8d2d48b5cee3efdb32ae8fdc7abfe948275c677b2d6c6494"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eDiW7Bu7vqmoMISfyixnvUn3dQQ+hrS/tlFF8OYwGI0t5WiZ96jgxOjtG7lT+IFkc9h2hBcg7Lyf5E+O16sZAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T01:45:33.986602Z","bundle_sha256":"2f75fb6fd44dd60c5a277546e64f7bbdb2284045d3a9f8461a24b5e650be36d6"}}