{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:A5YDA6LL5OKCZEHTCDKMW3OSNS","short_pith_number":"pith:A5YDA6LL","canonical_record":{"source":{"id":"2505.22063","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-28T07:39:25Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"322133dddfa8d3809405f835f266aa1e57d7f7ef6576a06336974508ebbc45ea","abstract_canon_sha256":"62e14480cc673baf27489fbf4418dc10c52a507c51022f7b3eee455e8fdb90f8"},"schema_version":"1.0"},"canonical_sha256":"077030796beb942c90f310d4cb6dd26c8649e3400cd2a8277626e068ad493104","source":{"kind":"arxiv","id":"2505.22063","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22063","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22063v1","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22063","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"pith_short_12","alias_value":"A5YDA6LL5OKC","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"pith_short_16","alias_value":"A5YDA6LL5OKCZEHT","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"pith_short_8","alias_value":"A5YDA6LL","created_at":"2026-07-05T11:11:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:A5YDA6LL5OKCZEHTCDKMW3OSNS","target":"record","payload":{"canonical_record":{"source":{"id":"2505.22063","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-28T07:39:25Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"322133dddfa8d3809405f835f266aa1e57d7f7ef6576a06336974508ebbc45ea","abstract_canon_sha256":"62e14480cc673baf27489fbf4418dc10c52a507c51022f7b3eee455e8fdb90f8"},"schema_version":"1.0"},"canonical_sha256":"077030796beb942c90f310d4cb6dd26c8649e3400cd2a8277626e068ad493104","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:09.041113Z","signature_b64":"m7aoIB0A8Y+3evgrPwHV8zOsD3iuASRS6eHb36Af0Lpgp9N0P/r4k82726EvLYoD9muvvNaMfiEnlGe1EMc1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"077030796beb942c90f310d4cb6dd26c8649e3400cd2a8277626e068ad493104","last_reissued_at":"2026-07-05T11:11:09.040581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:09.040581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.22063","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":"2026-07-05T11:11:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ril/IbVY1JgUS1qVrlJTvzrr6r2H0K+NmPUakni6MaPZEjNt6jBG/KAm2NsZlg9iL2faGb2Uk1bKvFsBZIDrDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:49:51.065960Z"},"content_sha256":"329ac5b3f28c590450c1cbb51afcb562a4ea3d0e695d65d84455b2bf1632fa8b","schema_version":"1.0","event_id":"sha256:329ac5b3f28c590450c1cbb51afcb562a4ea3d0e695d65d84455b2bf1632fa8b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:A5YDA6LL5OKCZEHTCDKMW3OSNS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Weakly Supervised Data Refinement and Flexible Sequence Compression for Efficient Thai LLM-based ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bingshen Mu, Chengyou Wang, Danming Xie, Hai Li, Junhui Liu, Lei Xie, Mingchen Shao, Xinfa Zhu, Ying Yan","submitted_at":"2025-05-28T07:39:25Z","abstract_excerpt":"Despite remarkable achievements, automatic speech recognition (ASR) in low-resource scenarios still faces two challenges: high-quality data scarcity and high computational demands. This paper proposes EThai-ASR, the first to apply large language models (LLMs) to Thai ASR and create an efficient LLM-based ASR system. EThai-ASR comprises a speech encoder, a connection module and a Thai LLM decoder. To address the data scarcity and obtain a powerful speech encoder, EThai-ASR introduces a self-evolving data refinement strategy to refine weak labels, yielding an enhanced speech encoder. Moreover, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22063","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/2505.22063/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":"2026-07-05T11:11:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zo6E2OrH82NUgB7jw7H5abE9RExtm+AS3KfStdrUnstTLvL+ccbDSVJomqAVeHbPWCZxJ6dmyqW0hZkuWZhuAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:49:51.066459Z"},"content_sha256":"adfd3530648f5cfd48c0aef6dcbddd7bec07b93adc842c76b99663bc0429fe7b","schema_version":"1.0","event_id":"sha256:adfd3530648f5cfd48c0aef6dcbddd7bec07b93adc842c76b99663bc0429fe7b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A5YDA6LL5OKCZEHTCDKMW3OSNS/bundle.json","state_url":"https://pith.science/pith/A5YDA6LL5OKCZEHTCDKMW3OSNS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A5YDA6LL5OKCZEHTCDKMW3OSNS/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":"2026-08-03T20:49:51Z","links":{"resolver":"https://pith.science/pith/A5YDA6LL5OKCZEHTCDKMW3OSNS","bundle":"https://pith.science/pith/A5YDA6LL5OKCZEHTCDKMW3OSNS/bundle.json","state":"https://pith.science/pith/A5YDA6LL5OKCZEHTCDKMW3OSNS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A5YDA6LL5OKCZEHTCDKMW3OSNS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:A5YDA6LL5OKCZEHTCDKMW3OSNS","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":"62e14480cc673baf27489fbf4418dc10c52a507c51022f7b3eee455e8fdb90f8","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-28T07:39:25Z","title_canon_sha256":"322133dddfa8d3809405f835f266aa1e57d7f7ef6576a06336974508ebbc45ea"},"schema_version":"1.0","source":{"id":"2505.22063","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22063","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22063v1","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22063","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"pith_short_12","alias_value":"A5YDA6LL5OKC","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"pith_short_16","alias_value":"A5YDA6LL5OKCZEHT","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"pith_short_8","alias_value":"A5YDA6LL","created_at":"2026-07-05T11:11:09Z"}],"graph_snapshots":[{"event_id":"sha256:adfd3530648f5cfd48c0aef6dcbddd7bec07b93adc842c76b99663bc0429fe7b","target":"graph","created_at":"2026-07-05T11:11:09Z","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/2505.22063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite remarkable achievements, automatic speech recognition (ASR) in low-resource scenarios still faces two challenges: high-quality data scarcity and high computational demands. This paper proposes EThai-ASR, the first to apply large language models (LLMs) to Thai ASR and create an efficient LLM-based ASR system. EThai-ASR comprises a speech encoder, a connection module and a Thai LLM decoder. To address the data scarcity and obtain a powerful speech encoder, EThai-ASR introduces a self-evolving data refinement strategy to refine weak labels, yielding an enhanced speech encoder. Moreover, w","authors_text":"Bingshen Mu, Chengyou Wang, Danming Xie, Hai Li, Junhui Liu, Lei Xie, Mingchen Shao, Xinfa Zhu, Ying Yan","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-28T07:39:25Z","title":"Weakly Supervised Data Refinement and Flexible Sequence Compression for Efficient Thai LLM-based ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22063","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":"sha256:329ac5b3f28c590450c1cbb51afcb562a4ea3d0e695d65d84455b2bf1632fa8b","target":"record","created_at":"2026-07-05T11:11:09Z","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":"62e14480cc673baf27489fbf4418dc10c52a507c51022f7b3eee455e8fdb90f8","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-28T07:39:25Z","title_canon_sha256":"322133dddfa8d3809405f835f266aa1e57d7f7ef6576a06336974508ebbc45ea"},"schema_version":"1.0","source":{"id":"2505.22063","kind":"arxiv","version":1}},"canonical_sha256":"077030796beb942c90f310d4cb6dd26c8649e3400cd2a8277626e068ad493104","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"077030796beb942c90f310d4cb6dd26c8649e3400cd2a8277626e068ad493104","first_computed_at":"2026-07-05T11:11:09.040581Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:09.040581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m7aoIB0A8Y+3evgrPwHV8zOsD3iuASRS6eHb36Af0Lpgp9N0P/r4k82726EvLYoD9muvvNaMfiEnlGe1EMc1DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:09.041113Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22063","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:329ac5b3f28c590450c1cbb51afcb562a4ea3d0e695d65d84455b2bf1632fa8b","sha256:adfd3530648f5cfd48c0aef6dcbddd7bec07b93adc842c76b99663bc0429fe7b"],"state_sha256":"80d02d7a42492142d86f9bec67ed4602839f35d9bc59f6b584fbbc5e6d89fe7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UxUDchexcgd9zlMlnFzP6W73+1Ke2PI/ytGKPqeM5rODJSHWtDvaASyfNJWZvEDbUy9hq20wO/XgboAma3tXCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:49:51.071738Z","bundle_sha256":"18bd7e04f023636459eb12497c078ba5a52009e067b6d6f2b0962ca749278a69"}}