{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:K5KQ4Q4EVXZB6UVRMJ22B7ZMIP","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":"bfc214f1c3f68a78cdac4cdb6a613fb298249feec4e545132a7687862b33fab7","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-15T21:32:20Z","title_canon_sha256":"9feaec24d607a2d4535f2f4473c1308c048bc27204ce16a9f289d819e72cbfdb"},"schema_version":"1.0","source":{"id":"2309.08773","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08773","created_at":"2026-07-05T06:51:13Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08773v1","created_at":"2026-07-05T06:51:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08773","created_at":"2026-07-05T06:51:13Z"},{"alias_kind":"pith_short_12","alias_value":"K5KQ4Q4EVXZB","created_at":"2026-07-05T06:51:13Z"},{"alias_kind":"pith_short_16","alias_value":"K5KQ4Q4EVXZB6UVR","created_at":"2026-07-05T06:51:13Z"},{"alias_kind":"pith_short_8","alias_value":"K5KQ4Q4E","created_at":"2026-07-05T06:51:13Z"}],"graph_snapshots":[{"event_id":"sha256:da88778a4f0cd95f32c6be6d1f26105ca9c7d6a38c543aa49eae42c609330486","target":"graph","created_at":"2026-07-05T06:51:13Z","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/2309.08773/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents an innovative approach to enhance control over audio generation by emphasizing the alignment between audio and text representations during model training. In the context of language model-based audio generation, the model leverages input from both textual and audio token representations to predict subsequent audio tokens. However, the current configuration lacks explicit regularization to ensure the alignment between the chosen text representation and the language model's predictions. Our proposal involves the incorporation of audio and text representation regularization, p","authors_text":"Ernie Chang, Forrest Iandola, Gael Le Lan, Varun Nagaraja, Vikas Chandra, Xinhao Mei, Yang Liu, Yangyang Shi, Zhaoheng Ni","cross_cats":["cs.AI","cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-15T21:32:20Z","title":"Enhance audio generation controllability through representation similarity regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08773","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:eb72ac18ad4dd949b7b605ebb03b84d647999e80afda44192bc48d53d9c0fad3","target":"record","created_at":"2026-07-05T06:51:13Z","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":"bfc214f1c3f68a78cdac4cdb6a613fb298249feec4e545132a7687862b33fab7","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-15T21:32:20Z","title_canon_sha256":"9feaec24d607a2d4535f2f4473c1308c048bc27204ce16a9f289d819e72cbfdb"},"schema_version":"1.0","source":{"id":"2309.08773","kind":"arxiv","version":1}},"canonical_sha256":"57550e4384adf21f52b16275a0ff2c43dd36059992079095a5e2164ef53d68e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57550e4384adf21f52b16275a0ff2c43dd36059992079095a5e2164ef53d68e8","first_computed_at":"2026-07-05T06:51:13.060957Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:51:13.060957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fJr6FrDNODPfPq6JpbtZr/pkz+hbZ5R4PcUMxXpTxSWBcT7+5vE1QDaz9RGXaMz0zxqcsZ1AZ8rbavtDSf3vAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:51:13.061364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.08773","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb72ac18ad4dd949b7b605ebb03b84d647999e80afda44192bc48d53d9c0fad3","sha256:da88778a4f0cd95f32c6be6d1f26105ca9c7d6a38c543aa49eae42c609330486"],"state_sha256":"8a4b8cbffaa145738be703c20a54f79352762ef14266b2df5f15e6f0edb9b505"}