{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LOE4K5MHL5GULE2HYTBD6DK756","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":"40eaeae610b359e87a7d1287a8e54aedd010ac5df691d2d9e32c32dba73c2e5b","cross_cats_sorted":["cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T09:33:31Z","title_canon_sha256":"3af38ba87a976693b583f211bd96bac11e89a832560fa5f9a06badd2f0982e3a"},"schema_version":"1.0","source":{"id":"2412.15712","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15712","created_at":"2026-07-05T11:12:23Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15712v2","created_at":"2026-07-05T11:12:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15712","created_at":"2026-07-05T11:12:23Z"},{"alias_kind":"pith_short_12","alias_value":"LOE4K5MHL5GU","created_at":"2026-07-05T11:12:23Z"},{"alias_kind":"pith_short_16","alias_value":"LOE4K5MHL5GULE2H","created_at":"2026-07-05T11:12:23Z"},{"alias_kind":"pith_short_8","alias_value":"LOE4K5MH","created_at":"2026-07-05T11:12:23Z"}],"graph_snapshots":[{"event_id":"sha256:5ea7a6c53f2acc65389b7bfee05fc2f8b31a9e4246b6e97dbb71b45ff38d426e","target":"graph","created_at":"2026-07-05T11:12:23Z","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/2412.15712/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) excel in natural language processing but adapting these LLMs to speech processing tasks efficiently is not straightforward. Direct task-specific fine-tuning is limited by overfitting risks, data requirements, and computational costs. To address these challenges, we propose a scalable, two-stage training approach: (1) A task-independent speech pretraining stage using contrastive learning to align text and speech representations over all layers, followed by (2) a task-specific fine-tuning stage requiring minimal data. This approach outperforms traditional ASR pretrai","authors_text":"Jan Niehues, Maike Z\\\"ufle","cross_cats":["cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T09:33:31Z","title":"Contrastive Learning for Task-Independent SpeechLLM-Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15712","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":"sha256:9d99b7f5f26a27caa7b5e9010f3dcc9f9f4ce2d715177f92672ec0259d367e36","target":"record","created_at":"2026-07-05T11:12:23Z","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":"40eaeae610b359e87a7d1287a8e54aedd010ac5df691d2d9e32c32dba73c2e5b","cross_cats_sorted":["cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T09:33:31Z","title_canon_sha256":"3af38ba87a976693b583f211bd96bac11e89a832560fa5f9a06badd2f0982e3a"},"schema_version":"1.0","source":{"id":"2412.15712","kind":"arxiv","version":2}},"canonical_sha256":"5b89c575875f4d459347c4c23f0d5fefb6124a98a24c9c680485467e660e8574","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b89c575875f4d459347c4c23f0d5fefb6124a98a24c9c680485467e660e8574","first_computed_at":"2026-07-05T11:12:23.697582Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:23.697582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pDvjt5NFuRGF7eSIl2dkzQb4nepHUDpTJBIuL1NJ42K7spcV2xRmszFGnhL+ZXjuuMQG42qPJEeg3R/R7PWuBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:23.698082Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15712","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d99b7f5f26a27caa7b5e9010f3dcc9f9f4ce2d715177f92672ec0259d367e36","sha256:5ea7a6c53f2acc65389b7bfee05fc2f8b31a9e4246b6e97dbb71b45ff38d426e"],"state_sha256":"6f75d0af3518bc5f25707c2094f7b10679e45051ce889f48e254d8e83fb19a38"}