{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WP7U4XOYRHE6NEWWKFT3S5HXC4","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":"72506d2b0441cbb68734197db7368a073d08d71c80587f41b23b67b302ed9c96","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-25T15:54:29Z","title_canon_sha256":"ff55640b35188b75f937cb7cad2b63855f05234435d9b355bfe7f4ffaa73f18e"},"schema_version":"1.0","source":{"id":"2409.17044","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17044","created_at":"2026-07-05T11:14:49Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17044v3","created_at":"2026-07-05T11:14:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17044","created_at":"2026-07-05T11:14:49Z"},{"alias_kind":"pith_short_12","alias_value":"WP7U4XOYRHE6","created_at":"2026-07-05T11:14:49Z"},{"alias_kind":"pith_short_16","alias_value":"WP7U4XOYRHE6NEWW","created_at":"2026-07-05T11:14:49Z"},{"alias_kind":"pith_short_8","alias_value":"WP7U4XOY","created_at":"2026-07-05T11:14:49Z"}],"graph_snapshots":[{"event_id":"sha256:b5e405a6c0dc2c442940d03c609a0baaf4b8e518252858254f63a6894474643f","target":"graph","created_at":"2026-07-05T11:14:49Z","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/2409.17044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The remarkable performance achieved by Large Language Models (LLM) has driven research efforts to leverage them for a wide range of tasks and input modalities. In speech-to-text (S2T) tasks, the emerging solution consists of projecting the output of the encoder of a Speech Foundational Model (SFM) into the LLM embedding space through an adapter module. However, no work has yet investigated how much the downstream-task performance depends on each component (SFM, adapter, LLM) nor whether the best design of the adapter depends on the chosen SFM and LLM. To fill this gap, we evaluate the combinat","authors_text":"Francesco Cariaggi, Francesco Verdini, Luisa Bentivogli, Marco Gaido, Marek Kasztelnik, Paolo Merialdo, Pierfrancesco Melucci, Sara Papi, S\\'ebastien Brati\\`eres, Simone Scardapane, Stefano Perna, Szymon Mazurek","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-25T15:54:29Z","title":"How to Connect Speech Foundation Models and Large Language Models? What Matters and What Does Not"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17044","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":"sha256:39fe24341befbf2dc198ae371bd898ec3209a00d9340a89cfaf16824f16b7d38","target":"record","created_at":"2026-07-05T11:14:49Z","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":"72506d2b0441cbb68734197db7368a073d08d71c80587f41b23b67b302ed9c96","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-25T15:54:29Z","title_canon_sha256":"ff55640b35188b75f937cb7cad2b63855f05234435d9b355bfe7f4ffaa73f18e"},"schema_version":"1.0","source":{"id":"2409.17044","kind":"arxiv","version":3}},"canonical_sha256":"b3ff4e5dd889c9e692d65167b974f717186e1219bddc3dd763cc0930ccc0ebdf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3ff4e5dd889c9e692d65167b974f717186e1219bddc3dd763cc0930ccc0ebdf","first_computed_at":"2026-07-05T11:14:49.368525Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:49.368525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mnIvE1CgjNH9kHrHd9Dm8SqPYL4kSc8T96SQoJpnU3YlDvGlYkP0IQ8nOz/LD7NQxtt4gKStKKidjRExuP+EBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:49.368986Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.17044","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39fe24341befbf2dc198ae371bd898ec3209a00d9340a89cfaf16824f16b7d38","sha256:b5e405a6c0dc2c442940d03c609a0baaf4b8e518252858254f63a6894474643f"],"state_sha256":"8758ec1429fe10acbf160313e43d286494ae8a80e28c14dcb6bed1ee2fe6fb01"}