{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UKU6VZHOY2XGNPZ6OKFOZ7K3ZL","short_pith_number":"pith:UKU6VZHO","canonical_record":{"source":{"id":"2407.04675","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T17:38:03Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"b6d8e0f7582dfc6f531ec86b08f56de414e16759d6ec1fc946944fe9091e3fd6","abstract_canon_sha256":"525bee48dce5e3f1a662d236235b01d060e99ef78df32fe503eefff9ca95e280"},"schema_version":"1.0"},"canonical_sha256":"a2a9eae4eec6ae66bf3e728aecfd5bcaf863919d0d17e61171beea44ed5b55eb","source":{"kind":"arxiv","id":"2407.04675","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04675","created_at":"2026-07-05T08:42:05Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04675v2","created_at":"2026-07-05T08:42:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04675","created_at":"2026-07-05T08:42:05Z"},{"alias_kind":"pith_short_12","alias_value":"UKU6VZHOY2XG","created_at":"2026-07-05T08:42:05Z"},{"alias_kind":"pith_short_16","alias_value":"UKU6VZHOY2XGNPZ6","created_at":"2026-07-05T08:42:05Z"},{"alias_kind":"pith_short_8","alias_value":"UKU6VZHO","created_at":"2026-07-05T08:42:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UKU6VZHOY2XGNPZ6OKFOZ7K3ZL","target":"record","payload":{"canonical_record":{"source":{"id":"2407.04675","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T17:38:03Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"b6d8e0f7582dfc6f531ec86b08f56de414e16759d6ec1fc946944fe9091e3fd6","abstract_canon_sha256":"525bee48dce5e3f1a662d236235b01d060e99ef78df32fe503eefff9ca95e280"},"schema_version":"1.0"},"canonical_sha256":"a2a9eae4eec6ae66bf3e728aecfd5bcaf863919d0d17e61171beea44ed5b55eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:05.460692Z","signature_b64":"nb8l9Wdk4HOpMDdwEbLJvn2ollptt0TPA5eVw5wSGPxUxtk9qd3wY9rgsqPN0fTxdvPN3RKyfLbuypBNp62VCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2a9eae4eec6ae66bf3e728aecfd5bcaf863919d0d17e61171beea44ed5b55eb","last_reissued_at":"2026-07-05T08:42:05.460200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:05.460200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.04675","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:42:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Valvoj42DGPM+2mf/i7TfkEFUMb9W7xFkC1N7HGdAhU9Gt6CifFkIpPL8Hu16Yt2d46E/UKxiqDPBxEMxHbdDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:30:14.454361Z"},"content_sha256":"273f7a0effd94cca3f2c200cfef69de0b2e861e3162c4c3f4e7a78f612cc8407","schema_version":"1.0","event_id":"sha256:273f7a0effd94cca3f2c200cfef69de0b2e861e3162c4c3f4e7a78f612cc8407"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UKU6VZHOY2XGNPZ6OKFOZ7K3ZL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bihong Zhang, Bo Wang, Chen Shen, Chuang Ding, Deyu Hua, Fanliu Kong, Hanzhang Xia, Hao Wang, Hongmin Xu, Jingping Chen, Jingting Ma, Jishuo Jin, Jitong Chen, Jun Zhang, Kepan Gao, Linhao Dong, Lu Gao, Lu Huang, Lu Lu, Meng Yang, Mingkun Huang, Minglun Han, Ming Tu, Ming Zou, Qianqian Dong, Rui Liu, Rui Xia, Shengtao Ma, Shouda Liu, Shuangyi Xie, Tian Tan, Tianyu Li, Ting Han, Wanyi Zhang, Wei Chen, Wenchao Hu, Xiaogang Tian, Xiaoyang Li, Xinying Hu, Yang Zhang, Yawei Zhang, Ye Bai, Yi Guo, Yijie Zheng, Yizhou Lu, Youjia Huang, Yujiao Du, Yulin Pei, Yuping Wang, Yuxiang Hu, Yuxuan Wang, Zehua Lin, Zeyang Li, Zhuo Chen, Zongwei Lan","submitted_at":"2024-07-05T17:38:03Z","abstract_excerpt":"Modern automatic speech recognition (ASR) model is required to accurately transcribe diverse speech signals (from different domains, languages, accents, etc) given the specific contextual information in various application scenarios. Classic end-to-end models fused with extra language models perform well, but mainly in data matching scenarios and are gradually approaching a bottleneck. In this work, we introduce Seed-ASR, a large language model (LLM) based speech recognition model. Seed-ASR is developed based on the framework of audio conditioned LLM (AcLLM), leveraging the capabilities of LLM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04675","kind":"arxiv","version":2},"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/2407.04675/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":"2026-07-05T08:42:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e+iB0anxRAqHTF0pEIQTfr0cLynncVoWgrhKd65aak5spXam6YjhlWDI5mOaJwq+rNaK07lp4/9V+OAcu67IAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:30:14.455280Z"},"content_sha256":"0f59fef630b129f7862f2945c107a9f006fe771e176b66a2c51af71624880d1a","schema_version":"1.0","event_id":"sha256:0f59fef630b129f7862f2945c107a9f006fe771e176b66a2c51af71624880d1a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UKU6VZHOY2XGNPZ6OKFOZ7K3ZL/bundle.json","state_url":"https://pith.science/pith/UKU6VZHOY2XGNPZ6OKFOZ7K3ZL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UKU6VZHOY2XGNPZ6OKFOZ7K3ZL/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":"2026-08-11T19:30:14Z","links":{"resolver":"https://pith.science/pith/UKU6VZHOY2XGNPZ6OKFOZ7K3ZL","bundle":"https://pith.science/pith/UKU6VZHOY2XGNPZ6OKFOZ7K3ZL/bundle.json","state":"https://pith.science/pith/UKU6VZHOY2XGNPZ6OKFOZ7K3ZL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UKU6VZHOY2XGNPZ6OKFOZ7K3ZL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UKU6VZHOY2XGNPZ6OKFOZ7K3ZL","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":"525bee48dce5e3f1a662d236235b01d060e99ef78df32fe503eefff9ca95e280","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T17:38:03Z","title_canon_sha256":"b6d8e0f7582dfc6f531ec86b08f56de414e16759d6ec1fc946944fe9091e3fd6"},"schema_version":"1.0","source":{"id":"2407.04675","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04675","created_at":"2026-07-05T08:42:05Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04675v2","created_at":"2026-07-05T08:42:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04675","created_at":"2026-07-05T08:42:05Z"},{"alias_kind":"pith_short_12","alias_value":"UKU6VZHOY2XG","created_at":"2026-07-05T08:42:05Z"},{"alias_kind":"pith_short_16","alias_value":"UKU6VZHOY2XGNPZ6","created_at":"2026-07-05T08:42:05Z"},{"alias_kind":"pith_short_8","alias_value":"UKU6VZHO","created_at":"2026-07-05T08:42:05Z"}],"graph_snapshots":[{"event_id":"sha256:0f59fef630b129f7862f2945c107a9f006fe771e176b66a2c51af71624880d1a","target":"graph","created_at":"2026-07-05T08:42:05Z","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/2407.04675/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern automatic speech recognition (ASR) model is required to accurately transcribe diverse speech signals (from different domains, languages, accents, etc) given the specific contextual information in various application scenarios. Classic end-to-end models fused with extra language models perform well, but mainly in data matching scenarios and are gradually approaching a bottleneck. In this work, we introduce Seed-ASR, a large language model (LLM) based speech recognition model. Seed-ASR is developed based on the framework of audio conditioned LLM (AcLLM), leveraging the capabilities of LLM","authors_text":"Bihong Zhang, Bo Wang, Chen Shen, Chuang Ding, Deyu Hua, Fanliu Kong, Hanzhang Xia, Hao Wang, Hongmin Xu, Jingping Chen, Jingting Ma, Jishuo Jin, Jitong Chen, Jun Zhang, Kepan Gao, Linhao Dong, Lu Gao, Lu Huang, Lu Lu, Meng Yang, Mingkun Huang, Minglun Han, Ming Tu, Ming Zou, Qianqian Dong, Rui Liu, Rui Xia, Shengtao Ma, Shouda Liu, Shuangyi Xie, Tian Tan, Tianyu Li, Ting Han, Wanyi Zhang, Wei Chen, Wenchao Hu, Xiaogang Tian, Xiaoyang Li, Xinying Hu, Yang Zhang, Yawei Zhang, Ye Bai, Yi Guo, Yijie Zheng, Yizhou Lu, Youjia Huang, Yujiao Du, Yulin Pei, Yuping Wang, Yuxiang Hu, Yuxuan Wang, Zehua Lin, Zeyang Li, Zhuo Chen, Zongwei Lan","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T17:38:03Z","title":"Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04675","kind":"arxiv","version":2},"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":"sha256:273f7a0effd94cca3f2c200cfef69de0b2e861e3162c4c3f4e7a78f612cc8407","target":"record","created_at":"2026-07-05T08:42:05Z","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":"525bee48dce5e3f1a662d236235b01d060e99ef78df32fe503eefff9ca95e280","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T17:38:03Z","title_canon_sha256":"b6d8e0f7582dfc6f531ec86b08f56de414e16759d6ec1fc946944fe9091e3fd6"},"schema_version":"1.0","source":{"id":"2407.04675","kind":"arxiv","version":2}},"canonical_sha256":"a2a9eae4eec6ae66bf3e728aecfd5bcaf863919d0d17e61171beea44ed5b55eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2a9eae4eec6ae66bf3e728aecfd5bcaf863919d0d17e61171beea44ed5b55eb","first_computed_at":"2026-07-05T08:42:05.460200Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:05.460200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nb8l9Wdk4HOpMDdwEbLJvn2ollptt0TPA5eVw5wSGPxUxtk9qd3wY9rgsqPN0fTxdvPN3RKyfLbuypBNp62VCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:05.460692Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.04675","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:273f7a0effd94cca3f2c200cfef69de0b2e861e3162c4c3f4e7a78f612cc8407","sha256:0f59fef630b129f7862f2945c107a9f006fe771e176b66a2c51af71624880d1a"],"state_sha256":"ef9baf07066bdbc9c6583caab31280cd29d9c251ff4443ae0369f1b9a2c74edd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7KCVsYDrkg7f26e+Xos705buwrE7cx+5Jd+ThKmVcTbYMHs7kt3qSTKgPjfUexfaHhVZPo5lvdFpU7ZY4HDOCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T19:30:14.460123Z","bundle_sha256":"13ed9cd05a4ea772787a86fc7d5923e33b147a091553593f8bfb8016ad393051"}}