{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VHQX325OHGGDXGDQXUZVTD6FLI","short_pith_number":"pith:VHQX325O","canonical_record":{"source":{"id":"2411.14642","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T00:21:39Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"52f0151fd926fb61834e6fc60d41e521f9f220025010e41a3a4260c7735a9b1e","abstract_canon_sha256":"4de8a515f6cee7ba6912227cc175d8aef1a8e1346d8e5838557b1a3ccd0f6801"},"schema_version":"1.0"},"canonical_sha256":"a9e17debae398c3b9870bd33598fc55a3340bc80167bc5098073c9bcb2a351b7","source":{"kind":"arxiv","id":"2411.14642","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14642","created_at":"2026-07-05T09:38:54Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14642v1","created_at":"2026-07-05T09:38:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14642","created_at":"2026-07-05T09:38:54Z"},{"alias_kind":"pith_short_12","alias_value":"VHQX325OHGGD","created_at":"2026-07-05T09:38:54Z"},{"alias_kind":"pith_short_16","alias_value":"VHQX325OHGGDXGDQ","created_at":"2026-07-05T09:38:54Z"},{"alias_kind":"pith_short_8","alias_value":"VHQX325O","created_at":"2026-07-05T09:38:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VHQX325OHGGDXGDQXUZVTD6FLI","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14642","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T00:21:39Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"52f0151fd926fb61834e6fc60d41e521f9f220025010e41a3a4260c7735a9b1e","abstract_canon_sha256":"4de8a515f6cee7ba6912227cc175d8aef1a8e1346d8e5838557b1a3ccd0f6801"},"schema_version":"1.0"},"canonical_sha256":"a9e17debae398c3b9870bd33598fc55a3340bc80167bc5098073c9bcb2a351b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:54.705714Z","signature_b64":"GeQCScPqBpgzYPeyYAxMu+9WEdgV0FeigrCD3SdZjt9qwtL9+heYjseFM7A+fwLViJKwoTqtitTQ+YommaItCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9e17debae398c3b9870bd33598fc55a3340bc80167bc5098073c9bcb2a351b7","last_reissued_at":"2026-07-05T09:38:54.705229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:54.705229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14642","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":"2026-07-05T09:38:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hBybsceKnqdOYE82+Cp5tIDNFFeTZuJP/u+kedCugwQHwgH/fVKfr0CNySUsciDeozWGh61m4LXoguTsO6hIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T00:37:15.923082Z"},"content_sha256":"0f848d363bbde7d6530ad3962c89612aa9675a758cc0fbaec9e2f437d4121a29","schema_version":"1.0","event_id":"sha256:0f848d363bbde7d6530ad3962c89612aa9675a758cc0fbaec9e2f437d4121a29"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VHQX325OHGGDXGDQXUZVTD6FLI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VQalAttent: a Transparent Speech Generation Pipeline based on Transformer-learned VQ-VAE Latent Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.LG","authors_text":"Armani Rodriguez, Silvija Kokalj-Filipovic","submitted_at":"2024-11-22T00:21:39Z","abstract_excerpt":"Generating high-quality speech efficiently remains a key challenge for generative models in speech synthesis. This paper introduces VQalAttent, a lightweight model designed to generate fake speech with tunable performance and interpretability. Leveraging the AudioMNIST dataset, consisting of human utterances of decimal digits (0-9), our method employs a two-step architecture: first, a scalable vector quantized autoencoder (VQ-VAE) that compresses audio spectrograms into discrete latent representations, and second, a decoder-only transformer that learns the probability model of these latents. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14642","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/2411.14642/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":"2026-07-05T09:38:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rFqnVoDSBr7kFZM/yJa3ct5Ew2n6UznG5/KQoNPXlU1CwlKyknPQtbXivPgMpBL/JtikFFOqQOEISGnDJDbeDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T00:37:15.923606Z"},"content_sha256":"72e19a86896c1882f8a4b4f1e3968c4a84dd9a4786610d1250987d6cbce5a23a","schema_version":"1.0","event_id":"sha256:72e19a86896c1882f8a4b4f1e3968c4a84dd9a4786610d1250987d6cbce5a23a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VHQX325OHGGDXGDQXUZVTD6FLI/bundle.json","state_url":"https://pith.science/pith/VHQX325OHGGDXGDQXUZVTD6FLI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VHQX325OHGGDXGDQXUZVTD6FLI/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":"2026-08-23T00:37:15Z","links":{"resolver":"https://pith.science/pith/VHQX325OHGGDXGDQXUZVTD6FLI","bundle":"https://pith.science/pith/VHQX325OHGGDXGDQXUZVTD6FLI/bundle.json","state":"https://pith.science/pith/VHQX325OHGGDXGDQXUZVTD6FLI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VHQX325OHGGDXGDQXUZVTD6FLI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VHQX325OHGGDXGDQXUZVTD6FLI","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":"4de8a515f6cee7ba6912227cc175d8aef1a8e1346d8e5838557b1a3ccd0f6801","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T00:21:39Z","title_canon_sha256":"52f0151fd926fb61834e6fc60d41e521f9f220025010e41a3a4260c7735a9b1e"},"schema_version":"1.0","source":{"id":"2411.14642","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14642","created_at":"2026-07-05T09:38:54Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14642v1","created_at":"2026-07-05T09:38:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14642","created_at":"2026-07-05T09:38:54Z"},{"alias_kind":"pith_short_12","alias_value":"VHQX325OHGGD","created_at":"2026-07-05T09:38:54Z"},{"alias_kind":"pith_short_16","alias_value":"VHQX325OHGGDXGDQ","created_at":"2026-07-05T09:38:54Z"},{"alias_kind":"pith_short_8","alias_value":"VHQX325O","created_at":"2026-07-05T09:38:54Z"}],"graph_snapshots":[{"event_id":"sha256:72e19a86896c1882f8a4b4f1e3968c4a84dd9a4786610d1250987d6cbce5a23a","target":"graph","created_at":"2026-07-05T09:38:54Z","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/2411.14642/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating high-quality speech efficiently remains a key challenge for generative models in speech synthesis. This paper introduces VQalAttent, a lightweight model designed to generate fake speech with tunable performance and interpretability. Leveraging the AudioMNIST dataset, consisting of human utterances of decimal digits (0-9), our method employs a two-step architecture: first, a scalable vector quantized autoencoder (VQ-VAE) that compresses audio spectrograms into discrete latent representations, and second, a decoder-only transformer that learns the probability model of these latents. T","authors_text":"Armani Rodriguez, Silvija Kokalj-Filipovic","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T00:21:39Z","title":"VQalAttent: a Transparent Speech Generation Pipeline based on Transformer-learned VQ-VAE Latent Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14642","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":"sha256:0f848d363bbde7d6530ad3962c89612aa9675a758cc0fbaec9e2f437d4121a29","target":"record","created_at":"2026-07-05T09:38:54Z","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":"4de8a515f6cee7ba6912227cc175d8aef1a8e1346d8e5838557b1a3ccd0f6801","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T00:21:39Z","title_canon_sha256":"52f0151fd926fb61834e6fc60d41e521f9f220025010e41a3a4260c7735a9b1e"},"schema_version":"1.0","source":{"id":"2411.14642","kind":"arxiv","version":1}},"canonical_sha256":"a9e17debae398c3b9870bd33598fc55a3340bc80167bc5098073c9bcb2a351b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9e17debae398c3b9870bd33598fc55a3340bc80167bc5098073c9bcb2a351b7","first_computed_at":"2026-07-05T09:38:54.705229Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:54.705229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GeQCScPqBpgzYPeyYAxMu+9WEdgV0FeigrCD3SdZjt9qwtL9+heYjseFM7A+fwLViJKwoTqtitTQ+YommaItCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:54.705714Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14642","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f848d363bbde7d6530ad3962c89612aa9675a758cc0fbaec9e2f437d4121a29","sha256:72e19a86896c1882f8a4b4f1e3968c4a84dd9a4786610d1250987d6cbce5a23a"],"state_sha256":"a6fd51286a5e2515ee5f0abe08c77226f06d37601f3949e9bd724a5647a7b3f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5by4+GQiEa+CnzchpnDX3cYCuJ5ppC/Z2RQUMp0CAIHbeu0+kl8nZ9Bae3Nck4ks7FnUAI3da+kCfKJGFAcYBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T00:37:15.929211Z","bundle_sha256":"05ec4ea3d5e0b5004075cdb11a6a181e2d24353435aee79475cdf4731a3fe006"}}