{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KXHKNAXW776YNISCA4BK5GDXKS","short_pith_number":"pith:KXHKNAXW","canonical_record":{"source":{"id":"2308.15930","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-30T10:12:39Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"b173d16be86c559239b749c4fa58cbb00126c3ed51ee381d7711204c0927eea2","abstract_canon_sha256":"49234925751706a376d01f116fce2770e6243b917694ba017b5866144fc774d6"},"schema_version":"1.0"},"canonical_sha256":"55cea682f6fffd86a2420702ae987754a873a60f6fd23574e7da7815f6ee985e","source":{"kind":"arxiv","id":"2308.15930","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.15930","created_at":"2026-07-05T06:51:28Z"},{"alias_kind":"arxiv_version","alias_value":"2308.15930v3","created_at":"2026-07-05T06:51:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15930","created_at":"2026-07-05T06:51:28Z"},{"alias_kind":"pith_short_12","alias_value":"KXHKNAXW776Y","created_at":"2026-07-05T06:51:28Z"},{"alias_kind":"pith_short_16","alias_value":"KXHKNAXW776YNISC","created_at":"2026-07-05T06:51:28Z"},{"alias_kind":"pith_short_8","alias_value":"KXHKNAXW","created_at":"2026-07-05T06:51:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KXHKNAXW776YNISCA4BK5GDXKS","target":"record","payload":{"canonical_record":{"source":{"id":"2308.15930","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-30T10:12:39Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"b173d16be86c559239b749c4fa58cbb00126c3ed51ee381d7711204c0927eea2","abstract_canon_sha256":"49234925751706a376d01f116fce2770e6243b917694ba017b5866144fc774d6"},"schema_version":"1.0"},"canonical_sha256":"55cea682f6fffd86a2420702ae987754a873a60f6fd23574e7da7815f6ee985e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:28.962208Z","signature_b64":"TAQrQFTUPuhcBIN5tHoIouJISw3AID4ZhilbYB4ium4jn9E7yiX1PZbxH0x6n16UZ0n0Sd3W/kLtS5/K8pMpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55cea682f6fffd86a2420702ae987754a873a60f6fd23574e7da7815f6ee985e","last_reissued_at":"2026-07-05T06:51:28.961730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:28.961730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.15930","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:51:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GPKybRfr1WWWkVoZqBemNkSgEM2c8dV0TkhfgtgZDi5vkktNUog7WDdPC1oR2BVekgTctlwJcycefF4hkM34Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:27:36.981529Z"},"content_sha256":"26fabc9ebb51bf3519c2e4e0f116c7f49c2dc8cae6a4a8f646f9e4c642fec182","schema_version":"1.0","event_id":"sha256:26fabc9ebb51bf3519c2e4e0f116c7f49c2dc8cae6a4a8f646f9e4c642fec182"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KXHKNAXW776YNISCA4BK5GDXKS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaSM: Large Language and Speech Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Daochen Shi, Guangyao Chen, Qiqi Xiang, Ruihua Zhang, Siwei Dong, Wenhao Huang, Yemin Shi, Yu Shu","submitted_at":"2023-08-30T10:12:39Z","abstract_excerpt":"Multi-modal large language models have garnered significant interest recently. Though, most of the works focus on vision-language multi-modal models providing strong capabilities in following vision-and-language instructions. However, we claim that speech is also an important modality through which humans interact with the world. Hence, it is crucial for a general-purpose assistant to be able to follow multi-modal speech-and-language instructions. In this work, we propose Large Language and Speech Model (LLaSM). LLaSM is an end-to-end trained large multi-modal speech-language model with cross-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15930","kind":"arxiv","version":3},"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/2308.15930/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":"2026-07-05T06:51:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rb0h8A3HI68/LxMf08pZbJ8bmR6HuGEhVr4cVjLYUgPZnmsJms+/y2UqhA2DmFSoUw1JEh4ekXK6BCr1q42sBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:27:36.982032Z"},"content_sha256":"7bcfa546a9b5d61157798ccf2332ff2b7ede620135ec15120b409751f2b30b0f","schema_version":"1.0","event_id":"sha256:7bcfa546a9b5d61157798ccf2332ff2b7ede620135ec15120b409751f2b30b0f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KXHKNAXW776YNISCA4BK5GDXKS/bundle.json","state_url":"https://pith.science/pith/KXHKNAXW776YNISCA4BK5GDXKS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KXHKNAXW776YNISCA4BK5GDXKS/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":"2026-08-04T19:27:36Z","links":{"resolver":"https://pith.science/pith/KXHKNAXW776YNISCA4BK5GDXKS","bundle":"https://pith.science/pith/KXHKNAXW776YNISCA4BK5GDXKS/bundle.json","state":"https://pith.science/pith/KXHKNAXW776YNISCA4BK5GDXKS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KXHKNAXW776YNISCA4BK5GDXKS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KXHKNAXW776YNISCA4BK5GDXKS","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":"49234925751706a376d01f116fce2770e6243b917694ba017b5866144fc774d6","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-30T10:12:39Z","title_canon_sha256":"b173d16be86c559239b749c4fa58cbb00126c3ed51ee381d7711204c0927eea2"},"schema_version":"1.0","source":{"id":"2308.15930","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.15930","created_at":"2026-07-05T06:51:28Z"},{"alias_kind":"arxiv_version","alias_value":"2308.15930v3","created_at":"2026-07-05T06:51:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15930","created_at":"2026-07-05T06:51:28Z"},{"alias_kind":"pith_short_12","alias_value":"KXHKNAXW776Y","created_at":"2026-07-05T06:51:28Z"},{"alias_kind":"pith_short_16","alias_value":"KXHKNAXW776YNISC","created_at":"2026-07-05T06:51:28Z"},{"alias_kind":"pith_short_8","alias_value":"KXHKNAXW","created_at":"2026-07-05T06:51:28Z"}],"graph_snapshots":[{"event_id":"sha256:7bcfa546a9b5d61157798ccf2332ff2b7ede620135ec15120b409751f2b30b0f","target":"graph","created_at":"2026-07-05T06:51:28Z","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/2308.15930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal large language models have garnered significant interest recently. Though, most of the works focus on vision-language multi-modal models providing strong capabilities in following vision-and-language instructions. However, we claim that speech is also an important modality through which humans interact with the world. Hence, it is crucial for a general-purpose assistant to be able to follow multi-modal speech-and-language instructions. In this work, we propose Large Language and Speech Model (LLaSM). LLaSM is an end-to-end trained large multi-modal speech-language model with cross-","authors_text":"Daochen Shi, Guangyao Chen, Qiqi Xiang, Ruihua Zhang, Siwei Dong, Wenhao Huang, Yemin Shi, Yu Shu","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-30T10:12:39Z","title":"LLaSM: Large Language and Speech Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15930","kind":"arxiv","version":3},"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":"sha256:26fabc9ebb51bf3519c2e4e0f116c7f49c2dc8cae6a4a8f646f9e4c642fec182","target":"record","created_at":"2026-07-05T06:51:28Z","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":"49234925751706a376d01f116fce2770e6243b917694ba017b5866144fc774d6","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-30T10:12:39Z","title_canon_sha256":"b173d16be86c559239b749c4fa58cbb00126c3ed51ee381d7711204c0927eea2"},"schema_version":"1.0","source":{"id":"2308.15930","kind":"arxiv","version":3}},"canonical_sha256":"55cea682f6fffd86a2420702ae987754a873a60f6fd23574e7da7815f6ee985e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55cea682f6fffd86a2420702ae987754a873a60f6fd23574e7da7815f6ee985e","first_computed_at":"2026-07-05T06:51:28.961730Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:51:28.961730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TAQrQFTUPuhcBIN5tHoIouJISw3AID4ZhilbYB4ium4jn9E7yiX1PZbxH0x6n16UZ0n0Sd3W/kLtS5/K8pMpAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:51:28.962208Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.15930","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26fabc9ebb51bf3519c2e4e0f116c7f49c2dc8cae6a4a8f646f9e4c642fec182","sha256:7bcfa546a9b5d61157798ccf2332ff2b7ede620135ec15120b409751f2b30b0f"],"state_sha256":"3d02ba0977ee4632508a4f34a124a416f64b7bc969445c2e7e06d895e6e87f89"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y7N1/UShi/8WZvbZWZN8ptsrtbLMFX2kHnDRATP21orLhLECXYIrb1LPL04NW37lQj6U4qs3YrwLkKY7KEwiBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:27:36.985598Z","bundle_sha256":"d73938e2e601b0286283500536057eb22e5300df27a99382236c3cf04883fbc0"}}