{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:S67USAQQBSJG6Z6TVTH73ANM3D","short_pith_number":"pith:S67USAQQ","canonical_record":{"source":{"id":"2311.00697","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T17:55:09Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"849d79ead613c259a53e7d194ad24624595396c9d6b55ee913d92d96b3a7576f","abstract_canon_sha256":"a392fedeb839b3a70cc2b9772a97e7a86444035bd8f2b02bc76ab5585d8a8802"},"schema_version":"1.0"},"canonical_sha256":"97bf4902100c926f67d3accffd81acd8c6d734ef0f1064908f8e2eb96ea2aba7","source":{"kind":"arxiv","id":"2311.00697","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00697","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00697v1","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00697","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_12","alias_value":"S67USAQQBSJG","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_16","alias_value":"S67USAQQBSJG6Z6T","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_8","alias_value":"S67USAQQ","created_at":"2026-07-05T07:08:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:S67USAQQBSJG6Z6TVTH73ANM3D","target":"record","payload":{"canonical_record":{"source":{"id":"2311.00697","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T17:55:09Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"849d79ead613c259a53e7d194ad24624595396c9d6b55ee913d92d96b3a7576f","abstract_canon_sha256":"a392fedeb839b3a70cc2b9772a97e7a86444035bd8f2b02bc76ab5585d8a8802"},"schema_version":"1.0"},"canonical_sha256":"97bf4902100c926f67d3accffd81acd8c6d734ef0f1064908f8e2eb96ea2aba7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:01.766675Z","signature_b64":"dCTEMhFyQ8+PlVd/12yGmorZ8xqOCT76pw/pfq7PDnzhfq7csV094KtYUQrkmB8ukJOHhAI7i9BjLgXCIMP0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97bf4902100c926f67d3accffd81acd8c6d734ef0f1064908f8e2eb96ea2aba7","last_reissued_at":"2026-07-05T07:08:01.766239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:01.766239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.00697","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":"2026-07-05T07:08:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FmYIC6XDbR+s6qgtokDzELbgD7HUXP3kT16NMPv/GBGL2A3NNcOMnxjeUvFoIih0HTOD2auZtjtHRSrXG34/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:19:18.135044Z"},"content_sha256":"2c84ff1a983799c1df674d6f9433bfb44759e1b47acdfd41180b79c086f6dab1","schema_version":"1.0","event_id":"sha256:2c84ff1a983799c1df674d6f9433bfb44759e1b47acdfd41180b79c086f6dab1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:S67USAQQBSJG6Z6TVTH73ANM3D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Brian Thompson, Juan Zuluaga-Gomez, Marcello Federico, Prashant Mathur, Rohit Paturi, Sundararajan Srinivasan, Xing Niu, Zhaocheng Huang","submitted_at":"2023-11-01T17:55:09Z","abstract_excerpt":"Conventional speech-to-text translation (ST) systems are trained on single-speaker utterances, and they may not generalize to real-life scenarios where the audio contains conversations by multiple speakers. In this paper, we tackle single-channel multi-speaker conversational ST with an end-to-end and multi-task training model, named Speaker-Turn Aware Conversational Speech Translation, that combines automatic speech recognition, speech translation and speaker turn detection using special tokens in a serialized labeling format. We run experiments on the Fisher-CALLHOME corpus, which we adapted "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00697","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/2311.00697/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":"2026-07-05T07:08:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wv2ylUE0F+j/KG4lz6jRkIlt+N8Hi1vYxZ509Vrvqkt1JZmecgNY+QcU1SSb56jQuuYcyZ5Kz6wAzmLYAXuADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:19:18.135628Z"},"content_sha256":"cfdbac743a6ab77994c8160936d79349471722d7b21a2bbd88693b3c91a44339","schema_version":"1.0","event_id":"sha256:cfdbac743a6ab77994c8160936d79349471722d7b21a2bbd88693b3c91a44339"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S67USAQQBSJG6Z6TVTH73ANM3D/bundle.json","state_url":"https://pith.science/pith/S67USAQQBSJG6Z6TVTH73ANM3D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S67USAQQBSJG6Z6TVTH73ANM3D/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":"2026-08-18T04:19:18Z","links":{"resolver":"https://pith.science/pith/S67USAQQBSJG6Z6TVTH73ANM3D","bundle":"https://pith.science/pith/S67USAQQBSJG6Z6TVTH73ANM3D/bundle.json","state":"https://pith.science/pith/S67USAQQBSJG6Z6TVTH73ANM3D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S67USAQQBSJG6Z6TVTH73ANM3D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:S67USAQQBSJG6Z6TVTH73ANM3D","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":"a392fedeb839b3a70cc2b9772a97e7a86444035bd8f2b02bc76ab5585d8a8802","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T17:55:09Z","title_canon_sha256":"849d79ead613c259a53e7d194ad24624595396c9d6b55ee913d92d96b3a7576f"},"schema_version":"1.0","source":{"id":"2311.00697","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00697","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00697v1","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00697","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_12","alias_value":"S67USAQQBSJG","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_16","alias_value":"S67USAQQBSJG6Z6T","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_8","alias_value":"S67USAQQ","created_at":"2026-07-05T07:08:01Z"}],"graph_snapshots":[{"event_id":"sha256:cfdbac743a6ab77994c8160936d79349471722d7b21a2bbd88693b3c91a44339","target":"graph","created_at":"2026-07-05T07:08:01Z","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/2311.00697/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conventional speech-to-text translation (ST) systems are trained on single-speaker utterances, and they may not generalize to real-life scenarios where the audio contains conversations by multiple speakers. In this paper, we tackle single-channel multi-speaker conversational ST with an end-to-end and multi-task training model, named Speaker-Turn Aware Conversational Speech Translation, that combines automatic speech recognition, speech translation and speaker turn detection using special tokens in a serialized labeling format. We run experiments on the Fisher-CALLHOME corpus, which we adapted ","authors_text":"Brian Thompson, Juan Zuluaga-Gomez, Marcello Federico, Prashant Mathur, Rohit Paturi, Sundararajan Srinivasan, Xing Niu, Zhaocheng Huang","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T17:55:09Z","title":"End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00697","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":"sha256:2c84ff1a983799c1df674d6f9433bfb44759e1b47acdfd41180b79c086f6dab1","target":"record","created_at":"2026-07-05T07:08:01Z","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":"a392fedeb839b3a70cc2b9772a97e7a86444035bd8f2b02bc76ab5585d8a8802","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T17:55:09Z","title_canon_sha256":"849d79ead613c259a53e7d194ad24624595396c9d6b55ee913d92d96b3a7576f"},"schema_version":"1.0","source":{"id":"2311.00697","kind":"arxiv","version":1}},"canonical_sha256":"97bf4902100c926f67d3accffd81acd8c6d734ef0f1064908f8e2eb96ea2aba7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97bf4902100c926f67d3accffd81acd8c6d734ef0f1064908f8e2eb96ea2aba7","first_computed_at":"2026-07-05T07:08:01.766239Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:01.766239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dCTEMhFyQ8+PlVd/12yGmorZ8xqOCT76pw/pfq7PDnzhfq7csV094KtYUQrkmB8ukJOHhAI7i9BjLgXCIMP0DA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:01.766675Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.00697","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c84ff1a983799c1df674d6f9433bfb44759e1b47acdfd41180b79c086f6dab1","sha256:cfdbac743a6ab77994c8160936d79349471722d7b21a2bbd88693b3c91a44339"],"state_sha256":"de0884865e9b6504452d45be721d8a8c671a8e96153c80c8cb09c39d537a3147"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6yxAm2NWVEOyruUKl/OtCcnZAP/wC3k7YFxsBtfeHcT/UXCBFq+BuBpVzsTrNp+Phg0d50EMkZGnahutLPmYDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T04:19:18.141945Z","bundle_sha256":"fb14f7f19d5cbc088cec723ae64b7d1a63b34a70365d066b0f705fc0d001ee8c"}}