{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2WHMRR5YRNUZXMCIRUQ4DD4LSX","short_pith_number":"pith:2WHMRR5Y","canonical_record":{"source":{"id":"2507.08603","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-11T13:55:45Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"5c31a1bc692b129204a2ad778c50a284e7db5ab1e3828e04f83989f3cae390a3","abstract_canon_sha256":"4309480634be966ab06d284166bec1ea440c68ba5635472e88e6f817d0d7463b"},"schema_version":"1.0"},"canonical_sha256":"d58ec8c7b88b699bb0488d21c18f8b95ecde38b52c096c70e178ee4ffabcf75d","source":{"kind":"arxiv","id":"2507.08603","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08603","created_at":"2026-07-05T11:35:43Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08603v1","created_at":"2026-07-05T11:35:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08603","created_at":"2026-07-05T11:35:43Z"},{"alias_kind":"pith_short_12","alias_value":"2WHMRR5YRNUZ","created_at":"2026-07-05T11:35:43Z"},{"alias_kind":"pith_short_16","alias_value":"2WHMRR5YRNUZXMCI","created_at":"2026-07-05T11:35:43Z"},{"alias_kind":"pith_short_8","alias_value":"2WHMRR5Y","created_at":"2026-07-05T11:35:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2WHMRR5YRNUZXMCIRUQ4DD4LSX","target":"record","payload":{"canonical_record":{"source":{"id":"2507.08603","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-11T13:55:45Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"5c31a1bc692b129204a2ad778c50a284e7db5ab1e3828e04f83989f3cae390a3","abstract_canon_sha256":"4309480634be966ab06d284166bec1ea440c68ba5635472e88e6f817d0d7463b"},"schema_version":"1.0"},"canonical_sha256":"d58ec8c7b88b699bb0488d21c18f8b95ecde38b52c096c70e178ee4ffabcf75d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:43.124697Z","signature_b64":"Omfq3KbLQDSnwIrDL1qI8anN/sNw+h9ckXo50zvO0Yn85dsIUeNB9Yfk4oJHBA/0KlD/RFZzkNwcY3+tD1IbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d58ec8c7b88b699bb0488d21c18f8b95ecde38b52c096c70e178ee4ffabcf75d","last_reissued_at":"2026-07-05T11:35:43.124251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:43.124251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.08603","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":"2026-07-05T11:35:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/JcQROaTAyw5Hjvo/dOH9Sj93hNjKMO2/0u2yrkriWL3bbFZPWd+Ram5Itf/PR5qTjjSaCw79bm3EjSU3NcBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:29:33.905893Z"},"content_sha256":"d2b61200ee6c2e0016d255ea8f7c9f1dd4b232908a4ab6b33b457c9bbb733fbd","schema_version":"1.0","event_id":"sha256:d2b61200ee6c2e0016d255ea8f7c9f1dd4b232908a4ab6b33b457c9bbb733fbd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2WHMRR5YRNUZXMCIRUQ4DD4LSX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unlocking Speech Instruction Data Potential with Query Rewriting","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.AI","authors_text":"Huiyu Zhou, Linfeng Zhang, Shuliang Liu, Xuming Hu, Yibo Yan, Yonghua Hei","submitted_at":"2025-07-11T13:55:45Z","abstract_excerpt":"End-to-end Large Speech Language Models~(\\textbf{LSLMs}) demonstrate strong potential in response latency and speech comprehension capabilities, showcasing general intelligence across speech understanding tasks. However, the ability to follow speech instructions has not been fully realized due to the lack of datasets and heavily biased training tasks. Leveraging the rich ASR datasets, previous approaches have used Large Language Models~(\\textbf{LLMs}) to continue the linguistic information of speech to construct speech instruction datasets. Yet, due to the gap between LLM-generated results and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08603","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/2507.08603/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":"2026-07-05T11:35:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HZrkEGzAkz72fdNCuPnod/zlpn2RS50Fu/zF8eN+ZdPdodEnGE7Ptaq5JK7DKhJVLKsyMb7GgCbGDtLqr1wSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:29:33.906786Z"},"content_sha256":"4b62ef9192260f6843b69709cbf755b28cba749057939d3505edebf63ce41df3","schema_version":"1.0","event_id":"sha256:4b62ef9192260f6843b69709cbf755b28cba749057939d3505edebf63ce41df3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2WHMRR5YRNUZXMCIRUQ4DD4LSX/bundle.json","state_url":"https://pith.science/pith/2WHMRR5YRNUZXMCIRUQ4DD4LSX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2WHMRR5YRNUZXMCIRUQ4DD4LSX/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":"2026-08-04T23:29:33Z","links":{"resolver":"https://pith.science/pith/2WHMRR5YRNUZXMCIRUQ4DD4LSX","bundle":"https://pith.science/pith/2WHMRR5YRNUZXMCIRUQ4DD4LSX/bundle.json","state":"https://pith.science/pith/2WHMRR5YRNUZXMCIRUQ4DD4LSX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2WHMRR5YRNUZXMCIRUQ4DD4LSX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2WHMRR5YRNUZXMCIRUQ4DD4LSX","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":"4309480634be966ab06d284166bec1ea440c68ba5635472e88e6f817d0d7463b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-11T13:55:45Z","title_canon_sha256":"5c31a1bc692b129204a2ad778c50a284e7db5ab1e3828e04f83989f3cae390a3"},"schema_version":"1.0","source":{"id":"2507.08603","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08603","created_at":"2026-07-05T11:35:43Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08603v1","created_at":"2026-07-05T11:35:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08603","created_at":"2026-07-05T11:35:43Z"},{"alias_kind":"pith_short_12","alias_value":"2WHMRR5YRNUZ","created_at":"2026-07-05T11:35:43Z"},{"alias_kind":"pith_short_16","alias_value":"2WHMRR5YRNUZXMCI","created_at":"2026-07-05T11:35:43Z"},{"alias_kind":"pith_short_8","alias_value":"2WHMRR5Y","created_at":"2026-07-05T11:35:43Z"}],"graph_snapshots":[{"event_id":"sha256:4b62ef9192260f6843b69709cbf755b28cba749057939d3505edebf63ce41df3","target":"graph","created_at":"2026-07-05T11:35:43Z","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/2507.08603/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end Large Speech Language Models~(\\textbf{LSLMs}) demonstrate strong potential in response latency and speech comprehension capabilities, showcasing general intelligence across speech understanding tasks. However, the ability to follow speech instructions has not been fully realized due to the lack of datasets and heavily biased training tasks. Leveraging the rich ASR datasets, previous approaches have used Large Language Models~(\\textbf{LLMs}) to continue the linguistic information of speech to construct speech instruction datasets. Yet, due to the gap between LLM-generated results and","authors_text":"Huiyu Zhou, Linfeng Zhang, Shuliang Liu, Xuming Hu, Yibo Yan, Yonghua Hei","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-11T13:55:45Z","title":"Unlocking Speech Instruction Data Potential with Query Rewriting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08603","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:d2b61200ee6c2e0016d255ea8f7c9f1dd4b232908a4ab6b33b457c9bbb733fbd","target":"record","created_at":"2026-07-05T11:35:43Z","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":"4309480634be966ab06d284166bec1ea440c68ba5635472e88e6f817d0d7463b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-11T13:55:45Z","title_canon_sha256":"5c31a1bc692b129204a2ad778c50a284e7db5ab1e3828e04f83989f3cae390a3"},"schema_version":"1.0","source":{"id":"2507.08603","kind":"arxiv","version":1}},"canonical_sha256":"d58ec8c7b88b699bb0488d21c18f8b95ecde38b52c096c70e178ee4ffabcf75d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d58ec8c7b88b699bb0488d21c18f8b95ecde38b52c096c70e178ee4ffabcf75d","first_computed_at":"2026-07-05T11:35:43.124251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:43.124251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Omfq3KbLQDSnwIrDL1qI8anN/sNw+h9ckXo50zvO0Yn85dsIUeNB9Yfk4oJHBA/0KlD/RFZzkNwcY3+tD1IbAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:43.124697Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.08603","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2b61200ee6c2e0016d255ea8f7c9f1dd4b232908a4ab6b33b457c9bbb733fbd","sha256:4b62ef9192260f6843b69709cbf755b28cba749057939d3505edebf63ce41df3"],"state_sha256":"c7e3211dd016612b56cc2a580aac756ba5a16b2fa1c754c06df5838934f8a9f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VuqRgnI4qDiantYcGjm+/Ks7QhWA+WufAyyMHVx3G+A+KGYJPKrdUMIDs8U9xlrn1o4Cwb1TqpuRHDfK+tf5Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:29:33.926615Z","bundle_sha256":"ab698cdbe60d9fe1f4ee4bf611e02957e6339e9c487a4a78da24b5d9cb1cc7f9"}}