{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RQVLMQOOMVIFSB3JTJJOYIH7SZ","short_pith_number":"pith:RQVLMQOO","canonical_record":{"source":{"id":"2309.13963","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-25T08:57:07Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"248bb5217f636418fab20b77591f489cca4dac1347f884a258004237aaaab1e6","abstract_canon_sha256":"46f0031864208963eab321ca7aa150c3885fd448122992401abc9116e18051ce"},"schema_version":"1.0"},"canonical_sha256":"8c2ab641ce65505907699a52ec20ff965aecf3d452bd03ded17739b2ad1de5ba","source":{"kind":"arxiv","id":"2309.13963","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.13963","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"arxiv_version","alias_value":"2309.13963v2","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13963","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"pith_short_12","alias_value":"RQVLMQOOMVIF","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"pith_short_16","alias_value":"RQVLMQOOMVIFSB3J","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"pith_short_8","alias_value":"RQVLMQOO","created_at":"2026-07-05T06:54:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RQVLMQOOMVIFSB3JTJJOYIH7SZ","target":"record","payload":{"canonical_record":{"source":{"id":"2309.13963","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-25T08:57:07Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"248bb5217f636418fab20b77591f489cca4dac1347f884a258004237aaaab1e6","abstract_canon_sha256":"46f0031864208963eab321ca7aa150c3885fd448122992401abc9116e18051ce"},"schema_version":"1.0"},"canonical_sha256":"8c2ab641ce65505907699a52ec20ff965aecf3d452bd03ded17739b2ad1de5ba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:24.048105Z","signature_b64":"9QGys32P04x0mqmIZi5GNbjRcif7Fd6jFIJ+Vk+HLtd+GuDe9aLzc3JYYkwYtULd1eTByj0UWHFf0MgSdEEXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c2ab641ce65505907699a52ec20ff965aecf3d452bd03ded17739b2ad1de5ba","last_reissued_at":"2026-07-05T06:54:24.047614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:24.047614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.13963","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":"2026-07-05T06:54:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"In8BwItpOFAC7mFhEHHD8aS7tHxuk3gneoWYR3h8FcNpLxsiIz5tBE0Krli+ra+OXJDG79yciOS9hX+CnTuKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:15:12.654854Z"},"content_sha256":"7f5f3bde4686b246a4dda7544c39d21b7ae60f668f0f44a6dbb90fa5565ca32b","schema_version":"1.0","event_id":"sha256:7f5f3bde4686b246a4dda7544c39d21b7ae60f668f0f44a6dbb90fa5565ca32b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RQVLMQOOMVIFSB3JTJJOYIH7SZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Connecting Speech Encoder and Large Language Model for ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Changli Tang, Chao Zhang, Guangzhi Sun, Lu Lu, Tian Tan, Wei Li, Wenyi Yu, Xianzhao Chen, Zejun Ma","submitted_at":"2023-09-25T08:57:07Z","abstract_excerpt":"The impressive capability and versatility of large language models (LLMs) have aroused increasing attention in automatic speech recognition (ASR), with several pioneering studies attempting to build integrated ASR models by connecting a speech encoder with an LLM. This paper presents a comparative study of three commonly used structures as connectors, including fully connected layers, multi-head cross-attention, and Q-Former. Speech encoders from the Whisper model series as well as LLMs from the Vicuna model series with different model sizes were studied. Experiments were performed on the comm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13963","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/2309.13963/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":"2026-07-05T06:54:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iQWd+a3k4cOAPgg/zTJXr82jTh7YRq6b/+DNw8C9JdnKxilI8iiXOc8iuRiR1+hAqtAq9g4kYObCLwNjd5hmDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:15:12.655620Z"},"content_sha256":"0d48ef78353f2a75d03cc3893fd41aeac60bbdea1ccf6c076949bb7a0e7b561d","schema_version":"1.0","event_id":"sha256:0d48ef78353f2a75d03cc3893fd41aeac60bbdea1ccf6c076949bb7a0e7b561d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RQVLMQOOMVIFSB3JTJJOYIH7SZ/bundle.json","state_url":"https://pith.science/pith/RQVLMQOOMVIFSB3JTJJOYIH7SZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RQVLMQOOMVIFSB3JTJJOYIH7SZ/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":"2026-08-08T13:15:12Z","links":{"resolver":"https://pith.science/pith/RQVLMQOOMVIFSB3JTJJOYIH7SZ","bundle":"https://pith.science/pith/RQVLMQOOMVIFSB3JTJJOYIH7SZ/bundle.json","state":"https://pith.science/pith/RQVLMQOOMVIFSB3JTJJOYIH7SZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RQVLMQOOMVIFSB3JTJJOYIH7SZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RQVLMQOOMVIFSB3JTJJOYIH7SZ","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":"46f0031864208963eab321ca7aa150c3885fd448122992401abc9116e18051ce","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-25T08:57:07Z","title_canon_sha256":"248bb5217f636418fab20b77591f489cca4dac1347f884a258004237aaaab1e6"},"schema_version":"1.0","source":{"id":"2309.13963","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.13963","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"arxiv_version","alias_value":"2309.13963v2","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13963","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"pith_short_12","alias_value":"RQVLMQOOMVIF","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"pith_short_16","alias_value":"RQVLMQOOMVIFSB3J","created_at":"2026-07-05T06:54:24Z"},{"alias_kind":"pith_short_8","alias_value":"RQVLMQOO","created_at":"2026-07-05T06:54:24Z"}],"graph_snapshots":[{"event_id":"sha256:0d48ef78353f2a75d03cc3893fd41aeac60bbdea1ccf6c076949bb7a0e7b561d","target":"graph","created_at":"2026-07-05T06:54:24Z","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/2309.13963/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The impressive capability and versatility of large language models (LLMs) have aroused increasing attention in automatic speech recognition (ASR), with several pioneering studies attempting to build integrated ASR models by connecting a speech encoder with an LLM. This paper presents a comparative study of three commonly used structures as connectors, including fully connected layers, multi-head cross-attention, and Q-Former. Speech encoders from the Whisper model series as well as LLMs from the Vicuna model series with different model sizes were studied. Experiments were performed on the comm","authors_text":"Changli Tang, Chao Zhang, Guangzhi Sun, Lu Lu, Tian Tan, Wei Li, Wenyi Yu, Xianzhao Chen, Zejun Ma","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-25T08:57:07Z","title":"Connecting Speech Encoder and Large Language Model for ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13963","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":"sha256:7f5f3bde4686b246a4dda7544c39d21b7ae60f668f0f44a6dbb90fa5565ca32b","target":"record","created_at":"2026-07-05T06:54:24Z","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":"46f0031864208963eab321ca7aa150c3885fd448122992401abc9116e18051ce","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-25T08:57:07Z","title_canon_sha256":"248bb5217f636418fab20b77591f489cca4dac1347f884a258004237aaaab1e6"},"schema_version":"1.0","source":{"id":"2309.13963","kind":"arxiv","version":2}},"canonical_sha256":"8c2ab641ce65505907699a52ec20ff965aecf3d452bd03ded17739b2ad1de5ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c2ab641ce65505907699a52ec20ff965aecf3d452bd03ded17739b2ad1de5ba","first_computed_at":"2026-07-05T06:54:24.047614Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:54:24.047614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9QGys32P04x0mqmIZi5GNbjRcif7Fd6jFIJ+Vk+HLtd+GuDe9aLzc3JYYkwYtULd1eTByj0UWHFf0MgSdEEXAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:54:24.048105Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.13963","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f5f3bde4686b246a4dda7544c39d21b7ae60f668f0f44a6dbb90fa5565ca32b","sha256:0d48ef78353f2a75d03cc3893fd41aeac60bbdea1ccf6c076949bb7a0e7b561d"],"state_sha256":"6e3ce2bdec0b40f438e9865c5b8f0073f48e785a8b42222cae70ca50f2eb559b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JSJe610BERTkmQ4Ye8EC+LL9ovz8ldfHU4QEBQz+CbiBP64VVeaVCrOwGgoG7vKoQVIh/YDWRhODWHOEAf3dBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:15:12.661857Z","bundle_sha256":"24c415112ef1d8e5aff564aebfaf78fcb7a9eaebd901c297c1dd69a96b56778e"}}