{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ATQPWCAGD4IZGH7DLB6FU2M4J4","short_pith_number":"pith:ATQPWCAG","canonical_record":{"source":{"id":"2305.18474","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-29T10:41:28Z","cross_cats_sorted":["cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"4a74e950d900b5722a344bbdc9eba5049a87ae96ffa0afaf8bff48ff3df9cbcd","abstract_canon_sha256":"ac8c61e3fe50a9743653eb658c7d1feecbcd426c6269588e7b97647e2f94f396"},"schema_version":"1.0"},"canonical_sha256":"04e0fb08061f11931fe3587c5a699c4f3b371a17a0f1c66016788c19020d96ab","source":{"kind":"arxiv","id":"2305.18474","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18474","created_at":"2026-07-05T06:15:01Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18474v1","created_at":"2026-07-05T06:15:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18474","created_at":"2026-07-05T06:15:01Z"},{"alias_kind":"pith_short_12","alias_value":"ATQPWCAGD4IZ","created_at":"2026-07-05T06:15:01Z"},{"alias_kind":"pith_short_16","alias_value":"ATQPWCAGD4IZGH7D","created_at":"2026-07-05T06:15:01Z"},{"alias_kind":"pith_short_8","alias_value":"ATQPWCAG","created_at":"2026-07-05T06:15:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ATQPWCAGD4IZGH7DLB6FU2M4J4","target":"record","payload":{"canonical_record":{"source":{"id":"2305.18474","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-29T10:41:28Z","cross_cats_sorted":["cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"4a74e950d900b5722a344bbdc9eba5049a87ae96ffa0afaf8bff48ff3df9cbcd","abstract_canon_sha256":"ac8c61e3fe50a9743653eb658c7d1feecbcd426c6269588e7b97647e2f94f396"},"schema_version":"1.0"},"canonical_sha256":"04e0fb08061f11931fe3587c5a699c4f3b371a17a0f1c66016788c19020d96ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:01.259014Z","signature_b64":"19idt0Si4q1RxBkoev3Ai6shXSXIMIyB617o7+vAO4KM5kQlBHk2BPjnzLEsMx2VAxa5RT+7+LCF0p8WqxeoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04e0fb08061f11931fe3587c5a699c4f3b371a17a0f1c66016788c19020d96ab","last_reissued_at":"2026-07-05T06:15:01.258554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:01.258554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.18474","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":"2026-07-05T06:15:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZgkJuH4kQWY+ZCIw8y7mGc7+yT5BeoVRlkyy6/jK5bOa5wp7lfDRM0R+6MDGsL9rHsmOFbFyDsd/IaUo4470Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T18:36:09.986082Z"},"content_sha256":"a982ce0009f175225977a19d10e49dbe39899a0f41846081ebd8320f5ec0e08d","schema_version":"1.0","event_id":"sha256:a982ce0009f175225977a19d10e49dbe39899a0f41846081ebd8320f5ec0e08d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ATQPWCAGD4IZGH7DLB6FU2M4J4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chen Zhang, Dongchao Yang, Jiawei Huang, Jinglin Liu, Rongjie Huang, Xiang Yin, Yi Ren, Zejun Ma, Zhenhui Ye, Zhou Zhao","submitted_at":"2023-05-29T10:41:28Z","abstract_excerpt":"Large diffusion models have been successful in text-to-audio (T2A) synthesis tasks, but they often suffer from common issues such as semantic misalignment and poor temporal consistency due to limited natural language understanding and data scarcity. Additionally, 2D spatial structures widely used in T2A works lead to unsatisfactory audio quality when generating variable-length audio samples since they do not adequately prioritize temporal information. To address these challenges, we propose Make-an-Audio 2, a latent diffusion-based T2A method that builds on the success of Make-an-Audio. Our ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18474","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/2305.18474/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":"2026-07-05T06:15:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9yh9bFC4AXRcLWkVwmixf6SGPo2HSf6sI+kKXJScTF0fp37xlJeVAytbSkxK2JR8bwRQv1YpVcTXEj653yjWBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T18:36:09.986378Z"},"content_sha256":"663c92f1f59bdc096d5559e05cc45a30e92f677345b39f8c06b03184741f2c9e","schema_version":"1.0","event_id":"sha256:663c92f1f59bdc096d5559e05cc45a30e92f677345b39f8c06b03184741f2c9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ATQPWCAGD4IZGH7DLB6FU2M4J4/bundle.json","state_url":"https://pith.science/pith/ATQPWCAGD4IZGH7DLB6FU2M4J4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ATQPWCAGD4IZGH7DLB6FU2M4J4/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":"2026-07-31T18:36:09Z","links":{"resolver":"https://pith.science/pith/ATQPWCAGD4IZGH7DLB6FU2M4J4","bundle":"https://pith.science/pith/ATQPWCAGD4IZGH7DLB6FU2M4J4/bundle.json","state":"https://pith.science/pith/ATQPWCAGD4IZGH7DLB6FU2M4J4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ATQPWCAGD4IZGH7DLB6FU2M4J4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ATQPWCAGD4IZGH7DLB6FU2M4J4","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":"ac8c61e3fe50a9743653eb658c7d1feecbcd426c6269588e7b97647e2f94f396","cross_cats_sorted":["cs.LG","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-29T10:41:28Z","title_canon_sha256":"4a74e950d900b5722a344bbdc9eba5049a87ae96ffa0afaf8bff48ff3df9cbcd"},"schema_version":"1.0","source":{"id":"2305.18474","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18474","created_at":"2026-07-05T06:15:01Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18474v1","created_at":"2026-07-05T06:15:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18474","created_at":"2026-07-05T06:15:01Z"},{"alias_kind":"pith_short_12","alias_value":"ATQPWCAGD4IZ","created_at":"2026-07-05T06:15:01Z"},{"alias_kind":"pith_short_16","alias_value":"ATQPWCAGD4IZGH7D","created_at":"2026-07-05T06:15:01Z"},{"alias_kind":"pith_short_8","alias_value":"ATQPWCAG","created_at":"2026-07-05T06:15:01Z"}],"graph_snapshots":[{"event_id":"sha256:663c92f1f59bdc096d5559e05cc45a30e92f677345b39f8c06b03184741f2c9e","target":"graph","created_at":"2026-07-05T06:15:01Z","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/2305.18474/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large diffusion models have been successful in text-to-audio (T2A) synthesis tasks, but they often suffer from common issues such as semantic misalignment and poor temporal consistency due to limited natural language understanding and data scarcity. Additionally, 2D spatial structures widely used in T2A works lead to unsatisfactory audio quality when generating variable-length audio samples since they do not adequately prioritize temporal information. To address these challenges, we propose Make-an-Audio 2, a latent diffusion-based T2A method that builds on the success of Make-an-Audio. Our ap","authors_text":"Chen Zhang, Dongchao Yang, Jiawei Huang, Jinglin Liu, Rongjie Huang, Xiang Yin, Yi Ren, Zejun Ma, Zhenhui Ye, Zhou Zhao","cross_cats":["cs.LG","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-29T10:41:28Z","title":"Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18474","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:a982ce0009f175225977a19d10e49dbe39899a0f41846081ebd8320f5ec0e08d","target":"record","created_at":"2026-07-05T06:15:01Z","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":"ac8c61e3fe50a9743653eb658c7d1feecbcd426c6269588e7b97647e2f94f396","cross_cats_sorted":["cs.LG","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-29T10:41:28Z","title_canon_sha256":"4a74e950d900b5722a344bbdc9eba5049a87ae96ffa0afaf8bff48ff3df9cbcd"},"schema_version":"1.0","source":{"id":"2305.18474","kind":"arxiv","version":1}},"canonical_sha256":"04e0fb08061f11931fe3587c5a699c4f3b371a17a0f1c66016788c19020d96ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04e0fb08061f11931fe3587c5a699c4f3b371a17a0f1c66016788c19020d96ab","first_computed_at":"2026-07-05T06:15:01.258554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:15:01.258554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"19idt0Si4q1RxBkoev3Ai6shXSXIMIyB617o7+vAO4KM5kQlBHk2BPjnzLEsMx2VAxa5RT+7+LCF0p8WqxeoAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:15:01.259014Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.18474","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a982ce0009f175225977a19d10e49dbe39899a0f41846081ebd8320f5ec0e08d","sha256:663c92f1f59bdc096d5559e05cc45a30e92f677345b39f8c06b03184741f2c9e"],"state_sha256":"25416e8e20d29299bbc2e9a26e4c9c94cab930d78717a6c05a10da0d8b84bc9d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8dEctMeY+Zuvvf6Et0hFCFdiofigtt+lINHUXwhO9Yq9HKexOAZkJ3H5FTKhRddtJrQJQdHFDpNmptq7Xm3ZCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T18:36:09.989626Z","bundle_sha256":"043951a6940a5f091b5f15433ae3aef278570af7f9c9ee29763c2c0c8461c9d7"}}