{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KT3GMEDBRN37ODFPSQA4PAG2RY","short_pith_number":"pith:KT3GMEDB","canonical_record":{"source":{"id":"2412.08577","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T17:51:44Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"2a5465a6ed7d9d4ba9b2dd6592a39a4f90b23390d16f63a95fb7c9e0f2d78c5e","abstract_canon_sha256":"43ca7c7400e1ffd39e5c5dd7f0b234f74459eea68e8365110e5e841e935c92d0"},"schema_version":"1.0"},"canonical_sha256":"54f66610618b77f70caf9401c780da8e198202786b10ec68e0cd6fa6a404567d","source":{"kind":"arxiv","id":"2412.08577","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08577","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08577v1","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08577","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"pith_short_12","alias_value":"KT3GMEDBRN37","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"pith_short_16","alias_value":"KT3GMEDBRN37ODFP","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"pith_short_8","alias_value":"KT3GMEDB","created_at":"2026-07-05T09:47:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KT3GMEDBRN37ODFPSQA4PAG2RY","target":"record","payload":{"canonical_record":{"source":{"id":"2412.08577","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T17:51:44Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"2a5465a6ed7d9d4ba9b2dd6592a39a4f90b23390d16f63a95fb7c9e0f2d78c5e","abstract_canon_sha256":"43ca7c7400e1ffd39e5c5dd7f0b234f74459eea68e8365110e5e841e935c92d0"},"schema_version":"1.0"},"canonical_sha256":"54f66610618b77f70caf9401c780da8e198202786b10ec68e0cd6fa6a404567d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:52.134230Z","signature_b64":"KiDNPuD3v0OU02OCS5EvXQ5vMnIponQjVqP2SjRHhGezBuByHxnk9y51z+1Bn/UYGCb+nfk0K9WIG9hf67BbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54f66610618b77f70caf9401c780da8e198202786b10ec68e0cd6fa6a404567d","last_reissued_at":"2026-07-05T09:47:52.133773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:52.133773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.08577","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:47:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vqgZ1+DFWgSLV+noCS8uz7bucjTbxsaQl9Xiu+q2aCkUJUY83k27yQ5TZQCxX+e++uDeNesrZUNjTr7PjpvNAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:27:28.068096Z"},"content_sha256":"031296c15ce49d4e99718312df1e97d4a02113464175ac5b499ea5c91f5d7fc9","schema_version":"1.0","event_id":"sha256:031296c15ce49d4e99718312df1e97d4a02113464175ac5b499ea5c91f5d7fc9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KT3GMEDBRN37ODFPSQA4PAG2RY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mel-Refine: A Plug-and-Play Approach to Refine Mel-Spectrogram in Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenxing Li, Chunyu Qiang, Hongming Guo, Ruibo Fu, Shuai Liu, Shuchen Shi, Tao Wang, Xuefei Liu, Ya Li, Yizhong Geng, Yukun Liu, Zhengqi Wen","submitted_at":"2024-12-11T17:51:44Z","abstract_excerpt":"Text-to-audio (TTA) model is capable of generating diverse audio from textual prompts. However, most mainstream TTA models, which predominantly rely on Mel-spectrograms, still face challenges in producing audio with rich content. The intricate details and texture required in Mel-spectrograms for such audio often surpass the models' capacity, leading to outputs that are blurred or lack coherence. In this paper, we begin by investigating the critical role of U-Net in Mel-spectrogram generation. Our analysis shows that in U-Net structure, high-frequency components in skip-connections and the back"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08577","kind":"arxiv","version":1},"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/2412.08577/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:47:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wiiDqIzwWYKyegYfj9Y77yX/a5QUKeu3D98swyVWp5dsOOJemW4RebWiE7H6h8Q/SdseYquvRem5+Qqw3gvdDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:27:28.069047Z"},"content_sha256":"49fc7d78072d8c102ce6cfd4580811fd9f70ac6e511359ca9325b0b564db4fa5","schema_version":"1.0","event_id":"sha256:49fc7d78072d8c102ce6cfd4580811fd9f70ac6e511359ca9325b0b564db4fa5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KT3GMEDBRN37ODFPSQA4PAG2RY/bundle.json","state_url":"https://pith.science/pith/KT3GMEDBRN37ODFPSQA4PAG2RY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KT3GMEDBRN37ODFPSQA4PAG2RY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T19:27:28Z","links":{"resolver":"https://pith.science/pith/KT3GMEDBRN37ODFPSQA4PAG2RY","bundle":"https://pith.science/pith/KT3GMEDBRN37ODFPSQA4PAG2RY/bundle.json","state":"https://pith.science/pith/KT3GMEDBRN37ODFPSQA4PAG2RY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KT3GMEDBRN37ODFPSQA4PAG2RY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KT3GMEDBRN37ODFPSQA4PAG2RY","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":"43ca7c7400e1ffd39e5c5dd7f0b234f74459eea68e8365110e5e841e935c92d0","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T17:51:44Z","title_canon_sha256":"2a5465a6ed7d9d4ba9b2dd6592a39a4f90b23390d16f63a95fb7c9e0f2d78c5e"},"schema_version":"1.0","source":{"id":"2412.08577","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08577","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08577v1","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08577","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"pith_short_12","alias_value":"KT3GMEDBRN37","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"pith_short_16","alias_value":"KT3GMEDBRN37ODFP","created_at":"2026-07-05T09:47:52Z"},{"alias_kind":"pith_short_8","alias_value":"KT3GMEDB","created_at":"2026-07-05T09:47:52Z"}],"graph_snapshots":[{"event_id":"sha256:49fc7d78072d8c102ce6cfd4580811fd9f70ac6e511359ca9325b0b564db4fa5","target":"graph","created_at":"2026-07-05T09:47:52Z","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/2412.08577/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-audio (TTA) model is capable of generating diverse audio from textual prompts. However, most mainstream TTA models, which predominantly rely on Mel-spectrograms, still face challenges in producing audio with rich content. The intricate details and texture required in Mel-spectrograms for such audio often surpass the models' capacity, leading to outputs that are blurred or lack coherence. In this paper, we begin by investigating the critical role of U-Net in Mel-spectrogram generation. Our analysis shows that in U-Net structure, high-frequency components in skip-connections and the back","authors_text":"Chenxing Li, Chunyu Qiang, Hongming Guo, Ruibo Fu, Shuai Liu, Shuchen Shi, Tao Wang, Xuefei Liu, Ya Li, Yizhong Geng, Yukun Liu, Zhengqi Wen","cross_cats":["cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T17:51:44Z","title":"Mel-Refine: A Plug-and-Play Approach to Refine Mel-Spectrogram in Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08577","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":"sha256:031296c15ce49d4e99718312df1e97d4a02113464175ac5b499ea5c91f5d7fc9","target":"record","created_at":"2026-07-05T09:47:52Z","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":"43ca7c7400e1ffd39e5c5dd7f0b234f74459eea68e8365110e5e841e935c92d0","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T17:51:44Z","title_canon_sha256":"2a5465a6ed7d9d4ba9b2dd6592a39a4f90b23390d16f63a95fb7c9e0f2d78c5e"},"schema_version":"1.0","source":{"id":"2412.08577","kind":"arxiv","version":1}},"canonical_sha256":"54f66610618b77f70caf9401c780da8e198202786b10ec68e0cd6fa6a404567d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54f66610618b77f70caf9401c780da8e198202786b10ec68e0cd6fa6a404567d","first_computed_at":"2026-07-05T09:47:52.133773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:52.133773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KiDNPuD3v0OU02OCS5EvXQ5vMnIponQjVqP2SjRHhGezBuByHxnk9y51z+1Bn/UYGCb+nfk0K9WIG9hf67BbDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:52.134230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08577","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:031296c15ce49d4e99718312df1e97d4a02113464175ac5b499ea5c91f5d7fc9","sha256:49fc7d78072d8c102ce6cfd4580811fd9f70ac6e511359ca9325b0b564db4fa5"],"state_sha256":"021c1331cc874d7e130974ae6da5593f56b400e47b8d7c73877517cf2deaf1fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nJ/+Ly9ZFPlv4vzdpZ9bYJ8WYf/8wGhrg4Lz8bZPSNeZq0EHJb2Vk8VVXclqTwhu0sjBfFpr+4IW6R1v4Yx7DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:27:28.075681Z","bundle_sha256":"8484fae3f598e253a2ccc6d108f9155f882c831627c95413c6fe1e2c76d2b919"}}