{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MFCG4KQNCR2UCG3NGO4EIT6BNF","short_pith_number":"pith:MFCG4KQN","canonical_record":{"source":{"id":"2406.19954","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T14:40:03Z","cross_cats_sorted":["cs.HC","cs.SD","eess.AS"],"title_canon_sha256":"56dffc1cf4c93b11b3c74e4d05efc11122f27bc371c7260ef94ca14777266a46","abstract_canon_sha256":"728d3122e6b2f4cffc9ebd0a42540e2b0d7aa5a550d6ab02a3559151a1078243"},"schema_version":"1.0"},"canonical_sha256":"61446e2a0d1475411b6d33b8444fc16945a2db31635fce82bc67f03e6ea31703","source":{"kind":"arxiv","id":"2406.19954","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19954","created_at":"2026-07-05T08:37:57Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19954v1","created_at":"2026-07-05T08:37:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19954","created_at":"2026-07-05T08:37:57Z"},{"alias_kind":"pith_short_12","alias_value":"MFCG4KQNCR2U","created_at":"2026-07-05T08:37:57Z"},{"alias_kind":"pith_short_16","alias_value":"MFCG4KQNCR2UCG3N","created_at":"2026-07-05T08:37:57Z"},{"alias_kind":"pith_short_8","alias_value":"MFCG4KQN","created_at":"2026-07-05T08:37:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MFCG4KQNCR2UCG3NGO4EIT6BNF","target":"record","payload":{"canonical_record":{"source":{"id":"2406.19954","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T14:40:03Z","cross_cats_sorted":["cs.HC","cs.SD","eess.AS"],"title_canon_sha256":"56dffc1cf4c93b11b3c74e4d05efc11122f27bc371c7260ef94ca14777266a46","abstract_canon_sha256":"728d3122e6b2f4cffc9ebd0a42540e2b0d7aa5a550d6ab02a3559151a1078243"},"schema_version":"1.0"},"canonical_sha256":"61446e2a0d1475411b6d33b8444fc16945a2db31635fce82bc67f03e6ea31703","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:57.354496Z","signature_b64":"H5jYDHzFyPwX2aVub8DGcfnbthX0Dav3Deamt5E0MF4wLyt8oR1J2tLUX/dXOWNKxjtPM8L4xCn78LmTxSJPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61446e2a0d1475411b6d33b8444fc16945a2db31635fce82bc67f03e6ea31703","last_reissued_at":"2026-07-05T08:37:57.353913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:57.353913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.19954","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":"2026-07-05T08:37:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B5wyMBINMnZ0mLmYMWXFdUPS4KxG5i4iGkkCQbtRXPrmgGhljhFDLPoldT8u9VJaraN+9ncgoOqPHwql7FRaAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:17:13.439404Z"},"content_sha256":"9028244c092e2a3592b3840d2ff5113448e93e594c1b722b9a1469c14c562ae5","schema_version":"1.0","event_id":"sha256:9028244c092e2a3592b3840d2ff5113448e93e594c1b722b9a1469c14c562ae5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MFCG4KQNCR2UCG3NGO4EIT6BNF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Boris Ginsburg, He Huang, Jagadeesh Balam, Krishna C. Puvvada, Nithin Rao Koluguri, Oleksii Hrinchuk, Piotr \\.Zelasko, Zhehuai Chen","submitted_at":"2024-06-28T14:40:03Z","abstract_excerpt":"Incorporating speech understanding capabilities into pretrained large-language models has become a vital research direction (SpeechLLM). The previous architectures can be categorized as: i) GPT-style, prepend speech prompts to the text prompts as a sequence of LLM inputs like a decoder-only model; ii) T5-style, introduce speech cross-attention to each layer of the pretrained LLMs. We propose BESTOW architecture to bring the BESt features from TwO Worlds into a single model that is highly efficient and has strong multitask capabilities. Moreover, there is no clear streaming solution for either "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19954","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/2406.19954/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":"2026-07-05T08:37:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dg3Ip/lDtI2H6QrnOwz2S4ZZ0aMePzSwKKz85G0TzyWW9/zXT6gj9YnfvW+zqUjIX9Hz6PRU2yzo94f9+55XCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:17:13.439795Z"},"content_sha256":"498cd01450518a53e57b7f42ebe45fc9e9fece4f37d6c0672c6cb542c488c199","schema_version":"1.0","event_id":"sha256:498cd01450518a53e57b7f42ebe45fc9e9fece4f37d6c0672c6cb542c488c199"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MFCG4KQNCR2UCG3NGO4EIT6BNF/bundle.json","state_url":"https://pith.science/pith/MFCG4KQNCR2UCG3NGO4EIT6BNF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MFCG4KQNCR2UCG3NGO4EIT6BNF/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":"2026-07-07T11:17:13Z","links":{"resolver":"https://pith.science/pith/MFCG4KQNCR2UCG3NGO4EIT6BNF","bundle":"https://pith.science/pith/MFCG4KQNCR2UCG3NGO4EIT6BNF/bundle.json","state":"https://pith.science/pith/MFCG4KQNCR2UCG3NGO4EIT6BNF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MFCG4KQNCR2UCG3NGO4EIT6BNF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MFCG4KQNCR2UCG3NGO4EIT6BNF","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":"728d3122e6b2f4cffc9ebd0a42540e2b0d7aa5a550d6ab02a3559151a1078243","cross_cats_sorted":["cs.HC","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T14:40:03Z","title_canon_sha256":"56dffc1cf4c93b11b3c74e4d05efc11122f27bc371c7260ef94ca14777266a46"},"schema_version":"1.0","source":{"id":"2406.19954","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19954","created_at":"2026-07-05T08:37:57Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19954v1","created_at":"2026-07-05T08:37:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19954","created_at":"2026-07-05T08:37:57Z"},{"alias_kind":"pith_short_12","alias_value":"MFCG4KQNCR2U","created_at":"2026-07-05T08:37:57Z"},{"alias_kind":"pith_short_16","alias_value":"MFCG4KQNCR2UCG3N","created_at":"2026-07-05T08:37:57Z"},{"alias_kind":"pith_short_8","alias_value":"MFCG4KQN","created_at":"2026-07-05T08:37:57Z"}],"graph_snapshots":[{"event_id":"sha256:498cd01450518a53e57b7f42ebe45fc9e9fece4f37d6c0672c6cb542c488c199","target":"graph","created_at":"2026-07-05T08:37:57Z","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/2406.19954/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Incorporating speech understanding capabilities into pretrained large-language models has become a vital research direction (SpeechLLM). The previous architectures can be categorized as: i) GPT-style, prepend speech prompts to the text prompts as a sequence of LLM inputs like a decoder-only model; ii) T5-style, introduce speech cross-attention to each layer of the pretrained LLMs. We propose BESTOW architecture to bring the BESt features from TwO Worlds into a single model that is highly efficient and has strong multitask capabilities. Moreover, there is no clear streaming solution for either ","authors_text":"Boris Ginsburg, He Huang, Jagadeesh Balam, Krishna C. Puvvada, Nithin Rao Koluguri, Oleksii Hrinchuk, Piotr \\.Zelasko, Zhehuai Chen","cross_cats":["cs.HC","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T14:40:03Z","title":"BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19954","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":"sha256:9028244c092e2a3592b3840d2ff5113448e93e594c1b722b9a1469c14c562ae5","target":"record","created_at":"2026-07-05T08:37:57Z","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":"728d3122e6b2f4cffc9ebd0a42540e2b0d7aa5a550d6ab02a3559151a1078243","cross_cats_sorted":["cs.HC","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T14:40:03Z","title_canon_sha256":"56dffc1cf4c93b11b3c74e4d05efc11122f27bc371c7260ef94ca14777266a46"},"schema_version":"1.0","source":{"id":"2406.19954","kind":"arxiv","version":1}},"canonical_sha256":"61446e2a0d1475411b6d33b8444fc16945a2db31635fce82bc67f03e6ea31703","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61446e2a0d1475411b6d33b8444fc16945a2db31635fce82bc67f03e6ea31703","first_computed_at":"2026-07-05T08:37:57.353913Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:57.353913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H5jYDHzFyPwX2aVub8DGcfnbthX0Dav3Deamt5E0MF4wLyt8oR1J2tLUX/dXOWNKxjtPM8L4xCn78LmTxSJPBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:57.354496Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.19954","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9028244c092e2a3592b3840d2ff5113448e93e594c1b722b9a1469c14c562ae5","sha256:498cd01450518a53e57b7f42ebe45fc9e9fece4f37d6c0672c6cb542c488c199"],"state_sha256":"125fe9e853d1ea36ff8d4fcb4bd6349271c1951b37a190a992800fe4eab9cd33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5hi2BYl+mQqy+X/CxN9+zPKJ5IKgRnPRa2PQxWF/Wn7ReOjTln0wPn2keVtGqSuUeFzwnyfHFi5lRtToPwxnBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:17:13.441828Z","bundle_sha256":"4f060ecd2c7e455756a4e23d35d0f7c459686f32cb5654c84fa91b70c0688733"}}