{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CE3LAB7U6LJCM7UTIR3W3HTS6Q","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":"2d91db9289923d29b68423ce804425698b1efd62b7c274cc796cf868e8c8bf00","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-30T02:27:45Z","title_canon_sha256":"765820ef3c420260879cfb0669c633779a5e5fff14c2eb8c5670d18958f005e3"},"schema_version":"1.0","source":{"id":"2310.00230","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00230","created_at":"2026-07-05T06:56:03Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00230v1","created_at":"2026-07-05T06:56:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00230","created_at":"2026-07-05T06:56:03Z"},{"alias_kind":"pith_short_12","alias_value":"CE3LAB7U6LJC","created_at":"2026-07-05T06:56:03Z"},{"alias_kind":"pith_short_16","alias_value":"CE3LAB7U6LJCM7UT","created_at":"2026-07-05T06:56:03Z"},{"alias_kind":"pith_short_8","alias_value":"CE3LAB7U","created_at":"2026-07-05T06:56:03Z"}],"graph_snapshots":[{"event_id":"sha256:8dfa782582d787986d47b0945b98b11ee09a2099a51953b68012b6e44e494a6c","target":"graph","created_at":"2026-07-05T06:56:03Z","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/2310.00230/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a joint Speech and Language Model (SLM), a multitask, multilingual, and dual-modal model that takes advantage of pretrained foundational speech and language models. SLM freezes the pretrained foundation models to maximally preserves their capabilities, and only trains a simple adapter with just 1\\% (156M) of the foundation models' parameters. This adaptation not only leads SLM to achieve strong performance on conventional tasks such as speech recognition (ASR) and speech translation (AST), but also introduces the novel capability of zero-shot instruction-following for more diverse t","authors_text":"Chung-Cheng Chiu, Dian Yu, Golan Pundak, Hagen Soltau, Izhak Shafran, Johan Schalkwyk, Lukas Zilka, Mingqiu Wang, Nanxin Chen, Nikhil Siddhartha, Paul Rubenstein, Wei Han, Yonghui Wu, Yongqiang Wang, Yuan Cao, Yu Zhang, Zelin Wu, Zhong Meng","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-30T02:27:45Z","title":"SLM: Bridge the thin gap between speech and text foundation models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00230","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:df89b4cf0caeb221d94ae0062e3077c501aac8c9445104d72cce981666f8187f","target":"record","created_at":"2026-07-05T06:56:03Z","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":"2d91db9289923d29b68423ce804425698b1efd62b7c274cc796cf868e8c8bf00","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-30T02:27:45Z","title_canon_sha256":"765820ef3c420260879cfb0669c633779a5e5fff14c2eb8c5670d18958f005e3"},"schema_version":"1.0","source":{"id":"2310.00230","kind":"arxiv","version":1}},"canonical_sha256":"1136b007f4f2d2267e9344776d9e72f4311b2f80e8ba1f7a1be7698593a3ee78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1136b007f4f2d2267e9344776d9e72f4311b2f80e8ba1f7a1be7698593a3ee78","first_computed_at":"2026-07-05T06:56:03.204548Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:56:03.204548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rHsgdY5g07VeLxUcj7/7Noq0Vb3HFR1EYk8px2G6X6/uhiMyoVhzYa+huH4uiJw5cRtIL/adfb+B9qqM0VHdCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:56:03.205032Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.00230","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df89b4cf0caeb221d94ae0062e3077c501aac8c9445104d72cce981666f8187f","sha256:8dfa782582d787986d47b0945b98b11ee09a2099a51953b68012b6e44e494a6c"],"state_sha256":"e510eb08179f92af980081783e4947324ee682e0f2e4426fc60d26ee7ef9055c"}