{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZV3F5CHPYQDVLLV4OBNHFXIAF3","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":"ec18ad1326f5cd5ac8f70ebb8fd912256c4275b19830f41b03c1e3d0cbb108f0","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T06:07:53Z","title_canon_sha256":"84152f33a6f82c6d0a27b4311edc94ba9f68e8113fc1972670e49aa3c1cb729f"},"schema_version":"1.0","source":{"id":"2411.01834","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01834","created_at":"2026-07-05T11:10:33Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01834v2","created_at":"2026-07-05T11:10:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01834","created_at":"2026-07-05T11:10:33Z"},{"alias_kind":"pith_short_12","alias_value":"ZV3F5CHPYQDV","created_at":"2026-07-05T11:10:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZV3F5CHPYQDVLLV4","created_at":"2026-07-05T11:10:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZV3F5CHP","created_at":"2026-07-05T11:10:33Z"}],"graph_snapshots":[{"event_id":"sha256:471db0a9c65377548c1506bdceefb44eee0d1d217c8e4e8431791cb111817b35","target":"graph","created_at":"2026-07-05T11:10:33Z","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/2411.01834/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While textless Spoken Language Models (SLMs) have shown potential in end-to-end speech-to-speech modeling, they still lag behind text-based Large Language Models (LLMs) in terms of semantic coherence and relevance. This work introduces the Align-SLM framework, which leverages preference optimization inspired by Reinforcement Learning with AI Feedback (RLAIF) to enhance the semantic understanding of SLMs. Our approach generates multiple speech continuations from a given prompt and uses semantic metrics to create preference data for Direct Preference Optimization (DPO). We evaluate the framework","authors_text":"Aditya Gourav, Ankur Gandhe, Guan-Ting Lin, Hung-yi Lee, Ivan Bulyko, Prashanth Gurunath Shivakumar, Yile Gu","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T06:07:53Z","title":"Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01834","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":"sha256:5b40fa56eecc1217f160c079caba3dad4ed6356cdaf603ad0ca5f5da70a5f372","target":"record","created_at":"2026-07-05T11:10:33Z","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":"ec18ad1326f5cd5ac8f70ebb8fd912256c4275b19830f41b03c1e3d0cbb108f0","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T06:07:53Z","title_canon_sha256":"84152f33a6f82c6d0a27b4311edc94ba9f68e8113fc1972670e49aa3c1cb729f"},"schema_version":"1.0","source":{"id":"2411.01834","kind":"arxiv","version":2}},"canonical_sha256":"cd765e88efc40755aebc705a72dd002ee362c27c578be6d90f8b731cb08ddcf8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd765e88efc40755aebc705a72dd002ee362c27c578be6d90f8b731cb08ddcf8","first_computed_at":"2026-07-05T11:10:33.042735Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:33.042735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o+bGfC9s2+N16fKQ+jwCbj/ebFeLyKNuHVgdJj/NCDasM9m/LaM1fhDbdwIhTaA7srkZqUeHfRhfOpgqSOwzCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:33.043232Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.01834","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b40fa56eecc1217f160c079caba3dad4ed6356cdaf603ad0ca5f5da70a5f372","sha256:471db0a9c65377548c1506bdceefb44eee0d1d217c8e4e8431791cb111817b35"],"state_sha256":"bf540034696e377260695925d88e1f7412651d4abb32c8ef0bb9a840f4e30323"}