{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:A4Q26ZOBDXYU3IIYUBMKB3LWCF","short_pith_number":"pith:A4Q26ZOB","schema_version":"1.0","canonical_sha256":"0721af65c11df14da118a058a0ed76117b5c752314fd69d06134dc2d4e43bf77","source":{"kind":"arxiv","id":"2309.09075","version":4},"attestation_state":"computed","paper":{"title":"Music Generation based on Generative Adversarial Networks with Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Ruoxue Wu, Xiaoxuan Liang, zhenghan Chen, Ziyi Jiang","submitted_at":"2023-09-16T18:48:40Z","abstract_excerpt":"Autoregressive models based on Transformers have become the prevailing approach for generating music compositions that exhibit comprehensive musical structure. These models are typically trained by minimizing the negative log-likelihood (NLL) of the observed sequence in an autoregressive manner. However, when generating long sequences, the quality of samples from these models tends to significantly deteriorate due to exposure bias. To address this issue, we leverage classifiers trained to differentiate between real and sampled sequences to identify these failures. This observation motivates ou"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.09075","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-16T18:48:40Z","cross_cats_sorted":[],"title_canon_sha256":"c9cde3805fc396fdcc2afbfcf83565c2ca0365e4cf2e22e66d6e74f83b6981b7","abstract_canon_sha256":"990d5bef14eb20a531d05ee619ada648f9489128eaa0d23aacb67e6f86d06e31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:22.893784Z","signature_b64":"AHetMKT440hUbT/PXDxtqs7aVZdaTGCSXL9CpbUFhoSevh6RAGWf/t/wf50o35sVddv0KUkB/jRhvLuWqQuXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0721af65c11df14da118a058a0ed76117b5c752314fd69d06134dc2d4e43bf77","last_reissued_at":"2026-07-05T06:59:22.893294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:22.893294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Music Generation based on Generative Adversarial Networks with Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Ruoxue Wu, Xiaoxuan Liang, zhenghan Chen, Ziyi Jiang","submitted_at":"2023-09-16T18:48:40Z","abstract_excerpt":"Autoregressive models based on Transformers have become the prevailing approach for generating music compositions that exhibit comprehensive musical structure. These models are typically trained by minimizing the negative log-likelihood (NLL) of the observed sequence in an autoregressive manner. However, when generating long sequences, the quality of samples from these models tends to significantly deteriorate due to exposure bias. To address this issue, we leverage classifiers trained to differentiate between real and sampled sequences to identify these failures. This observation motivates ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09075","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.09075/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.09075","created_at":"2026-07-05T06:59:22.893363+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09075v4","created_at":"2026-07-05T06:59:22.893363+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09075","created_at":"2026-07-05T06:59:22.893363+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4Q26ZOBDXYU","created_at":"2026-07-05T06:59:22.893363+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4Q26ZOBDXYU3IIY","created_at":"2026-07-05T06:59:22.893363+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4Q26ZOB","created_at":"2026-07-05T06:59:22.893363+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A4Q26ZOBDXYU3IIYUBMKB3LWCF","json":"https://pith.science/pith/A4Q26ZOBDXYU3IIYUBMKB3LWCF.json","graph_json":"https://pith.science/api/pith-number/A4Q26ZOBDXYU3IIYUBMKB3LWCF/graph.json","events_json":"https://pith.science/api/pith-number/A4Q26ZOBDXYU3IIYUBMKB3LWCF/events.json","paper":"https://pith.science/paper/A4Q26ZOB"},"agent_actions":{"view_html":"https://pith.science/pith/A4Q26ZOBDXYU3IIYUBMKB3LWCF","download_json":"https://pith.science/pith/A4Q26ZOBDXYU3IIYUBMKB3LWCF.json","view_paper":"https://pith.science/paper/A4Q26ZOB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09075&json=true","fetch_graph":"https://pith.science/api/pith-number/A4Q26ZOBDXYU3IIYUBMKB3LWCF/graph.json","fetch_events":"https://pith.science/api/pith-number/A4Q26ZOBDXYU3IIYUBMKB3LWCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4Q26ZOBDXYU3IIYUBMKB3LWCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4Q26ZOBDXYU3IIYUBMKB3LWCF/action/storage_attestation","attest_author":"https://pith.science/pith/A4Q26ZOBDXYU3IIYUBMKB3LWCF/action/author_attestation","sign_citation":"https://pith.science/pith/A4Q26ZOBDXYU3IIYUBMKB3LWCF/action/citation_signature","submit_replication":"https://pith.science/pith/A4Q26ZOBDXYU3IIYUBMKB3LWCF/action/replication_record"}},"created_at":"2026-07-05T06:59:22.893363+00:00","updated_at":"2026-07-05T06:59:22.893363+00:00"}