{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PAP3QSG4LLHTGEWY7UUDUUATUG","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":"cdbff23cbe4d81f8416c2db2d92b6f863a65df2467fb3a4bb513718a775f7076","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-02T11:46:05Z","title_canon_sha256":"d167c5b1de06a4977421ccc6e735cdc60aa998ab0249f9187efa70d681ea6e7b"},"schema_version":"1.0","source":{"id":"2309.00916","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.00916","created_at":"2026-07-05T08:23:54Z"},{"alias_kind":"arxiv_version","alias_value":"2309.00916v2","created_at":"2026-07-05T08:23:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.00916","created_at":"2026-07-05T08:23:54Z"},{"alias_kind":"pith_short_12","alias_value":"PAP3QSG4LLHT","created_at":"2026-07-05T08:23:54Z"},{"alias_kind":"pith_short_16","alias_value":"PAP3QSG4LLHTGEWY","created_at":"2026-07-05T08:23:54Z"},{"alias_kind":"pith_short_8","alias_value":"PAP3QSG4","created_at":"2026-07-05T08:23:54Z"}],"graph_snapshots":[{"event_id":"sha256:c8bce21b64fe4200b970277a4c1f08272937aeff333d02086ce9d52ac0900ced","target":"graph","created_at":"2026-07-05T08:23:54Z","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/2309.00916/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The emergence of large language models (LLMs) has sparked significant interest in extending their remarkable language capabilities to speech. However, modality alignment between speech and text still remains an open problem. Current solutions can be categorized into two strategies. One is a cascaded approach where outputs (tokens or states) of a separately trained speech recognition system are used as inputs for LLMs, which limits their potential in modeling alignment between speech and text. The other is an end-to-end approach that relies on speech instruction data, which is very difficult to","authors_text":"Chengqing Zong, Chen Wang, Jiajun Zhang, Jinliang Lu, Junhong Wu, Minpeng Liao, Yuchen Liu, Zhongqiang Huang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-02T11:46:05Z","title":"BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.00916","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:fc1d0a22746f6c46f953a26fd0131ecb984349fb83d70749b0c9506d41437bf8","target":"record","created_at":"2026-07-05T08:23:54Z","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":"cdbff23cbe4d81f8416c2db2d92b6f863a65df2467fb3a4bb513718a775f7076","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-02T11:46:05Z","title_canon_sha256":"d167c5b1de06a4977421ccc6e735cdc60aa998ab0249f9187efa70d681ea6e7b"},"schema_version":"1.0","source":{"id":"2309.00916","kind":"arxiv","version":2}},"canonical_sha256":"781fb848dc5acf3312d8fd283a5013a1a9f3020f1f89296f89190eab290f4865","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"781fb848dc5acf3312d8fd283a5013a1a9f3020f1f89296f89190eab290f4865","first_computed_at":"2026-07-05T08:23:54.894105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:54.894105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rn+VQk4pT4rhb7XQ6vE4cZlgPiZFtP3DpjdePcCiVOOSUAhlzczyrUU4p5Ix1TZgxA1Yl+iLe0xZhhEua9lDCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:54.894626Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.00916","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc1d0a22746f6c46f953a26fd0131ecb984349fb83d70749b0c9506d41437bf8","sha256:c8bce21b64fe4200b970277a4c1f08272937aeff333d02086ce9d52ac0900ced"],"state_sha256":"00b35155f908aff3d4c43eb4bcf857d9854bb042da1702ace1b7cb0f0f5a5c21"}