{"as_of":"2026-08-16T23:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:73f1af44e12b14712d943346a345451dfde5d2647f5c992c0868c0e0f241d4fe","coverage":[{"denominator":35,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":35,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T15:22:18.839404Z","state":"measured"},{"denominator":36,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":36,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T15:22:16.346725Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.19817","snapshot_observed_at":"2026-08-04T15:22:16.346725Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:16.346725Z"},"links":{"cited_paper":"/paper/2509.19817","citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:f4b0a259706460e6d48103d3bd55ece36eb3a32220f07bcea601871d14d87be2","observation_id":"01416b95-20cd-45e2-b428-7ea445bf9c33","resolution":{"observed_at":"2026-08-04T15:22:16.346725Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2509.19817/citation-record","integrity":"/paper/2509.19817/integrity","json":"/paper/2509.19817/citation-record.json","paper":"/paper/2509.19817"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.19817","snapshot_observed_at":"2026-08-04T15:22:16.346725Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:16.346725Z"},"links":{"cited_paper":"/paper/2509.19817","citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:f4b0a259706460e6d48103d3bd55ece36eb3a32220f07bcea601871d14d87be2","observation_id":"01416b95-20cd-45e2-b428-7ea445bf9c33","resolution":{"observed_at":"2026-08-04T15:22:16.346725Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:16.374793Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:16.374793Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:7b595bbce6014fb5ef5d4cea4fbac9632b048b7ea1b4dd8199c7de44a895015e","observation_id":"649911c2-2ac0-4b9f-bea2-32b0920535c6","resolution":{"observed_at":"2026-08-04T15:22:16.374793Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:16.395436Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:16.395436Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:841397dc4ad62bb4cad1865f33ccbab07dbd85a7012f4ba1c90d98721522affb","observation_id":"c1b527c2-278d-41df-b688-e1cf3bb93fa7","resolution":{"observed_at":"2026-08-04T15:22:16.395436Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:16.413873Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:16.413873Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:239ef936f8d72762b2c40963a077886b3add24fa861d279b431727a9a646b864","observation_id":"8fa8267e-00f7-46d3-91eb-1db53ad5b906","resolution":{"observed_at":"2026-08-04T15:22:16.413873Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:16.421986Z","title":"Data Acquisition We collected speech from a full-duplex healthcare assistant during internal testing (beta version)","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:16.421986Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:940a8697342505918c9b343895c2cd291ce1ed845166fa0db2796c13249351f3","observation_id":"3beceeed-091e-47f7-8c22-36fe5b4c48c9","resolution":{"observed_at":"2026-08-04T15:22:16.421986Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:16.440505Z","title":"Experimental Setups We fine-tuned Whisper-small [14] end-to-end on the Chinese training split for automatic speech recognition in healthcare dialogue","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:16.440505Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:8a1e058019701f766c0d4dc408913ae16c3eb13f5e1ff2af429b73f9a52ee088","observation_id":"39c74ce4-1db1-445c-9c16-f10957b32bc8","resolution":{"observed_at":"2026-08-04T15:22:16.440505Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:16.459548Z","title":"Benchmark Description MMedFD is a benchmark for Chinese healthcare spoken di- alogue constructed from live user–agent interactions under full-duplex conditions","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:16.459548Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:c78cde26aa6b73f948cf82924420998df0a9bc271751f3fe9d7b006e2dd49b84","observation_id":"2139dc29-1c71-4c84-b24b-95e52315d078","resolution":{"observed_at":"2026-08-04T15:22:16.459548Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:16.479683Z","title":"LLM-judged results for healthcare queries using PairEval and G-Eval with a consistent GPT-5 judge","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:16.479683Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:7b2ab563cfe095d4c32b4989b398dfbe16ad9fceaf5ce68346ce37aee6f3cd6e","observation_id":"e8541f26-1d29-4030-a3b6-61de438dca0c","resolution":{"observed_at":"2026-08-04T15:22:16.479683Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:16.498586Z","title":"P0051278, Jung Sun Yoo) and by the Research Grants Council of the Hong Kong Special Administrative Region, China (General Re- search Fund, Project No","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:16.498586Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:532c6decf7fcb439b6275b1a332e345872bb8f12fa306b0ddabb76d9431bce07","observation_id":"e48a6ac4-9485-4a54-a45d-823edc0ccaf4","resolution":{"observed_at":"2026-08-04T15:22:16.498586Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07658","last_updated":"2024-02-12T14:01:12Z","snapshot_observed_at":"2026-08-16T14:19:20.741255Z","submitted_at":"2024-02-12T14:01:12Z","title":"The Sound of Healthcare: Improving Medical Transcription ASR Accuracy with Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.07658","snapshot_observed_at":"2026-08-04T15:22:16.516308Z","title":"The sound of healthcare: Improving medical transcription asr accuracy with large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:16.516308Z"},"links":{"cited_paper":"/paper/2402.07658","citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:06e9511c2c5c5b5992d5aa73d12e9f5b24b81d03ba36fb86255c27f61bf71a69","observation_id":"1f285f29-c215-4f79-a973-9a3dfb789d4b","resolution":{"observed_at":"2026-08-04T15:22:16.516308Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:16.533560Z","title":"Medical dialogue system: A survey of cat- egories, methods, evaluation and challenges,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:16.533560Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:c969c6d770e9e02d4ed97b4dd6c2dd84e1b88fd4ec9896a5c897a7db248ae33f","observation_id":"5e74c4ea-0f3a-4e9d-ba0f-e1a8147d0af9","resolution":{"observed_at":"2026-08-04T15:22:16.533560Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:16.542090Z","title":"Multimed: Multilingual medi- cal speech recognition via attention encoder decoder,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:16.542090Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:9daf3d62db7bd569e1c371b31fc88e24eed02bc7a1076d98191383ea04afefd7","observation_id":"0b5aef1e-162a-4672-9479-ac6746e7ece1","resolution":{"observed_at":"2026-08-04T15:22:16.542090Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:16.554319Z","title":"The AI doctor is in: A survey of task-oriented dialogue systems for healthcare appli- cations,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:16.554319Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:6be2150e0dd889d80a0cd884838dd8c101f77b594103344acb41f4fd086d72cd","observation_id":"e4f1f9e1-5cb7-43aa-8714-bfe04932987f","resolution":{"observed_at":"2026-08-04T15:22:16.554319Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:16.618816Z","title":"A full-duplex speech dialogue scheme based on large language model,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:16.618816Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:43038bab8be28c8f733ebc70ca8a40711fcc4e3ecb4a65ceee61314ff73b6bcf","observation_id":"5f00b907-f0b3-47d6-bca7-738c349cf809","resolution":{"observed_at":"2026-08-04T15:22:16.618816Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:16.779249Z","title":"Primock57: A dataset of primary care mock consultations,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:16.779249Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:e52cbf6aee79ca3b8a2640962870ae0a039827acb052ff70dfe972cfabbc9b6a","observation_id":"1d54ba5c-a68b-46f1-ada7-435d97fdf422","resolution":{"observed_at":"2026-08-04T15:22:16.779249Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:16.839554Z","title":"Mtalk-bench: Evaluating speech-to- speech models in multi-turn dialogues via arena-style and rubrics protocols,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:16.839554Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:2aa5a900aa88e2a7376e8b70681fce48ff6ca39b2e7c4372bb0aad1b057d4fd1","observation_id":"3f14d887-cffa-4a98-bf23-b5228285741a","resolution":{"observed_at":"2026-08-04T15:22:16.839554Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:16.923506Z","title":null,"venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:16.923506Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:622266d93c8444eb6347f298b183f20450b4cf38a8c17ff4ec45783985981093","observation_id":"ab8d67bf-2161-42f8-9cde-8ff01c3e3e80","resolution":{"observed_at":"2026-08-04T15:22:16.923506Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:17.094461Z","title":"KWS15 keyword search evaluation plan,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:17.094461Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:b3e8f3758fbe39274ed34516f1da99bdb4cce6e02b16479590104c09764f3022","observation_id":"894c153e-c88d-43be-87d7-9d6aa087ae33","resolution":{"observed_at":"2026-08-04T15:22:17.094461Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:17.169949Z","title":"The bigscience roots corpus: A 1.6tb composite multilingual dataset,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:17.169949Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:477a61f496b4c83f6ec8010af6f5a6ba7958a415f29331349a58aaa8e1e3bb5a","observation_id":"34bedba4-41ea-4e66-8ea1-120ad1f891c4","resolution":{"observed_at":"2026-08-04T15:22:17.169949Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:17.285592Z","title":"Silero vad: Pre-trained enterprise- grade voice activity detector,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:17.285592Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:53cc482fdc008c344aa63b63bafabeb50d681f47ef2d805bd226933629409fb3","observation_id":"26840883-4ca7-46d8-b1ff-c12214ed482a","resolution":{"observed_at":"2026-08-04T15:22:17.285592Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.01255","last_updated":"2019-11-04T14:46:31Z","snapshot_observed_at":"2026-08-08T01:40:47.328408Z","submitted_at":"2019-11-04T14:46:31Z","title":"pyannote.audio: neural building blocks for speaker diarization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.01255","snapshot_observed_at":"2026-08-04T15:22:17.337394Z","title":"pyannote.audio: neural build- ing blocks for speaker diarization,","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:17.337394Z"},"links":{"cited_paper":"/paper/1911.01255","citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:023c2f8eaf1fa6fbea7a2dbcb258a0fe57d4f0b372f042a91bacaf9808516f02","observation_id":"0a4a3281-f989-4785-8070-a5c5ff17c8f6","resolution":{"observed_at":"2026-08-04T15:22:17.337394Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:17.461986Z","title":"Openasr21 challenge evaluation plan,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:17.461986Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:029c6ca7bb5a589b08d05936eda67149e3933d927602d4240d82e9560e1ebd15","observation_id":"33cd10b0-5940-4a70-b83d-30007e92a6e1","resolution":{"observed_at":"2026-08-04T15:22:17.461986Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:17.565485Z","title":"Robust speech recognition via large-scale weak supervision,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:17.565485Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:1f49d2723d7d76f3ac1aabc2e76392d1992917beef1833c0194cb718308decf7","observation_id":"bef2036b-edbb-46f9-9934-367d5a43e1f6","resolution":{"observed_at":"2026-08-04T15:22:17.565485Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:17.648500Z","title":"Paireval: Open-domain dialogue evaluation with pairwise comparison,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:17.648500Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:8edcc1ad345e3aceb6399155773b4781940fa433c0e6016d6e352b4924155225","observation_id":"6b0898ae-af83-4fcb-900a-f545ad8db60c","resolution":{"observed_at":"2026-08-04T15:22:17.648500Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:17.821686Z","title":"G-eval: NLG evaluation using GPT- 4 with better human alignment,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:17.821686Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:aa36e2ea9927bfb5291d7fd017f20d5e6ecb16e2f59dd9f7edc6f4fcd816bb9c","observation_id":"6acfa2f3-f6d1-4e1f-8ed6-b6f0cd6b5916","resolution":{"observed_at":"2026-08-04T15:22:17.821686Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:17.975254Z","title":"Vietmed: A dataset and benchmark for automatic speech recognition of vietnamese in the medical domain,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:17.975254Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:a5d134a645965e71aed15c1784b9c4981a28bc5a5da4f5f6095e57d243f24046","observation_id":"73297133-b368-4a9d-a926-db0b443bb430","resolution":{"observed_at":"2026-08-04T15:22:17.975254Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:18.044820Z","title":"A dataset of simulated patient- physician medical interviews with a focus on respiratory cases,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:18.044820Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:ac361fc4569b7d118b96aea74bb3b76e777a68474691167a99d069a185c19ced","observation_id":"7d2f68ec-bbee-4fc7-9ba9-4f76d115b94b","resolution":{"observed_at":"2026-08-04T15:22:18.044820Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:18.164460Z","title":"mymedicon: End-to-end burmese automatic speech recognition for medical conversa- tions,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:18.164460Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:e99bb5ddd970dddcb1414d9bc342b8b9cf5cdceecb6777c62a0749ae899d4e43","observation_id":"f35f820f-5152-4e34-a199-613f2e0ef8ce","resolution":{"observed_at":"2026-08-04T15:22:18.164460Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:18.271000Z","title":"Afrispeech-200: Pan-african ac- cented speech dataset for clinical and general domain asr,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:18.271000Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:94ec5a2868d36ca0f649391c96876a1b749a7a3077c672afa8b70a476a0c57ca","observation_id":"aeddf85a-e2c2-44ba-b170-ec2c63c8b7d7","resolution":{"observed_at":"2026-08-04T15:22:18.271000Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:18.335130Z","title":"Spokenwoz: A large-scale speech-text benchmark for spoken task-oriented dia- logue agents,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:18.335130Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:40bf93b038f03d4ee6815c9a03cc8ad07af2242a2e9313c75b5afca724b43f39","observation_id":"2019cf75-acdf-4c93-99a1-332bdb30537d","resolution":{"observed_at":"2026-08-04T15:22:18.335130Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:18.435260Z","title":"V oxdialogue: Can spoken dialogue systems understand information beyond words?,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:18.435260Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:02785614a21d663c39656c033136d1f863e712f24582e3e3eb1428fd8657e6db","observation_id":"fec3f24b-48cb-4065-a351-4234d4267559","resolution":{"observed_at":"2026-08-04T15:22:18.435260Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:18.536910Z","title":"Gpt-5 system card,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:18.536910Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:d5be42b4561c1a019dde45eaf3c74d0c159375938522b933c910902f828894fc","observation_id":"1d1d5f7f-eb21-4e7e-a131-82ebec3e0d79","resolution":{"observed_at":"2026-08-04T15:22:18.536910Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T15:22:18.612090Z","title":"Claude opus 4.1 system card addendum,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:18.612090Z"},"links":{"citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:f343f6a8b9552227c382c8e2ca54817c6462edb9f4c9eec05d96ab9ec0cf3a69","observation_id":"79371a43-b042-462f-ac39-a0d86e6f3693","resolution":{"observed_at":"2026-08-04T15:22:18.612090Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.06261","last_updated":"2025-12-19T14:25:46Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-07-07T17:36:04Z","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.06261","snapshot_observed_at":"2026-08-04T15:22:18.751402Z","title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next-generation agentic capabilities,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:18.751402Z"},"links":{"cited_paper":"/paper/2507.06261","citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:382a2c0b32fca196e8f5fe8d939fa1bffd8f4fe3ce8e4aa59dba2c1df7f209bf","observation_id":"8efe0fc2-edff-4212-bb67-07352adbcf07","resolution":{"observed_at":"2026-08-04T15:22:18.751402Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-08-04T15:22:18.839404Z","title":"Qwen3 technical report,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-04T15:22:18.839404Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2509.19817"},"observation_digest":"sha256:4dc36bb9716364bda599559cd1726a129e8f411a36aea4eb1b0c056d2a6323dd","observation_id":"7b4e32d7-8939-4d87-8f45-d77b807548f1","resolution":{"observed_at":"2026-08-04T15:22:18.839404Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.19817","last_updated":"2026-07-29T06:28:54Z","latest_version":3,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-13T21:37:52.444766Z","submitted_at":"2025-09-24T06:56:26Z","title":"MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition"},"reference_resolution":{"displayed":35,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":34,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":35},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 1 inbound Pith citation observation for arXiv:2509.19817."}