{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7B7THCVNKLPXY7AAMFM5AAJ6TL","short_pith_number":"pith:7B7THCVN","canonical_record":{"source":{"id":"2304.03323","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-04-06T18:37:26Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"91a90bf061abd5bc0b60f4dd0d8c23763d808f1b0c1c86fa8145a4d78ff5769a","abstract_canon_sha256":"6c48258cc5fce5611382c850ca72707bef585df70952c884a66abdd2ef858b82"},"schema_version":"1.0"},"canonical_sha256":"f87f338aad52df7c7c006159d0013e9ad588a6f19c482868b14af7ffdace8f3f","source":{"kind":"arxiv","id":"2304.03323","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03323","created_at":"2026-07-05T06:35:50Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03323v2","created_at":"2026-07-05T06:35:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03323","created_at":"2026-07-05T06:35:50Z"},{"alias_kind":"pith_short_12","alias_value":"7B7THCVNKLPX","created_at":"2026-07-05T06:35:50Z"},{"alias_kind":"pith_short_16","alias_value":"7B7THCVNKLPXY7AA","created_at":"2026-07-05T06:35:50Z"},{"alias_kind":"pith_short_8","alias_value":"7B7THCVN","created_at":"2026-07-05T06:35:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7B7THCVNKLPXY7AAMFM5AAJ6TL","target":"record","payload":{"canonical_record":{"source":{"id":"2304.03323","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-04-06T18:37:26Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"91a90bf061abd5bc0b60f4dd0d8c23763d808f1b0c1c86fa8145a4d78ff5769a","abstract_canon_sha256":"6c48258cc5fce5611382c850ca72707bef585df70952c884a66abdd2ef858b82"},"schema_version":"1.0"},"canonical_sha256":"f87f338aad52df7c7c006159d0013e9ad588a6f19c482868b14af7ffdace8f3f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:50.217865Z","signature_b64":"6VOSi4KRAB/rustJwyCEhRhNWwCHpYT1hKTOdjPtp93UuKBFWLXkEk3ZkdN8zLNkVetfPSkFddPzFUIZRUozBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f87f338aad52df7c7c006159d0013e9ad588a6f19c482868b14af7ffdace8f3f","last_reissued_at":"2026-07-05T06:35:50.217381Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:50.217381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.03323","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:35:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gJumEWh0PYgT2DwVhEQluP7yAds/4zY/CTAAGDuqNFWqyeTkbfOJN4RuQbhiAcGM/xhAszMqz/Cto+DoI5xkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:54:41.814503Z"},"content_sha256":"33b4653e81083892f968f76632920863cc0e5e79da06918eceaf1adbf774e168","schema_version":"1.0","event_id":"sha256:33b4653e81083892f968f76632920863cc0e5e79da06918eceaf1adbf774e168"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7B7THCVNKLPXY7AAMFM5AAJ6TL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DSVAE: Interpretable Disentangled Representation for Synthetic Speech Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Amit Kumar Singh Yadav, Edward J. Delp, Kratika Bhagtani, Paolo Bestagini, Stefano Tubaro, Ziyue Xiang","submitted_at":"2023-04-06T18:37:26Z","abstract_excerpt":"Tools to generate high quality synthetic speech signal that is perceptually indistinguishable from speech recorded from human speakers are easily available. Several approaches have been proposed for detecting synthetic speech. Many of these approaches use deep learning methods as a black box without providing reasoning for the decisions they make. This limits the interpretability of these approaches. In this paper, we propose Disentangled Spectrogram Variational Auto Encoder (DSVAE) which is a two staged trained variational autoencoder that processes spectrograms of speech using disentangled r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03323","kind":"arxiv","version":2},"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/2304.03323/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":"2026-07-05T06:35:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qrVcrnYSbdi8V2U4AAjSRX2K7uIBS3xEk6aN1nusSP10SQwi5vP/GS7XW4pjWSafH0FdVGfloK6+h4LTnPPBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:54:41.814881Z"},"content_sha256":"497c4e93f99bb91b9606121173b31c7435609accbaff816c81509ba8198cec05","schema_version":"1.0","event_id":"sha256:497c4e93f99bb91b9606121173b31c7435609accbaff816c81509ba8198cec05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7B7THCVNKLPXY7AAMFM5AAJ6TL/bundle.json","state_url":"https://pith.science/pith/7B7THCVNKLPXY7AAMFM5AAJ6TL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7B7THCVNKLPXY7AAMFM5AAJ6TL/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":"2026-07-08T23:54:41Z","links":{"resolver":"https://pith.science/pith/7B7THCVNKLPXY7AAMFM5AAJ6TL","bundle":"https://pith.science/pith/7B7THCVNKLPXY7AAMFM5AAJ6TL/bundle.json","state":"https://pith.science/pith/7B7THCVNKLPXY7AAMFM5AAJ6TL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7B7THCVNKLPXY7AAMFM5AAJ6TL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7B7THCVNKLPXY7AAMFM5AAJ6TL","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":"6c48258cc5fce5611382c850ca72707bef585df70952c884a66abdd2ef858b82","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-04-06T18:37:26Z","title_canon_sha256":"91a90bf061abd5bc0b60f4dd0d8c23763d808f1b0c1c86fa8145a4d78ff5769a"},"schema_version":"1.0","source":{"id":"2304.03323","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03323","created_at":"2026-07-05T06:35:50Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03323v2","created_at":"2026-07-05T06:35:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03323","created_at":"2026-07-05T06:35:50Z"},{"alias_kind":"pith_short_12","alias_value":"7B7THCVNKLPX","created_at":"2026-07-05T06:35:50Z"},{"alias_kind":"pith_short_16","alias_value":"7B7THCVNKLPXY7AA","created_at":"2026-07-05T06:35:50Z"},{"alias_kind":"pith_short_8","alias_value":"7B7THCVN","created_at":"2026-07-05T06:35:50Z"}],"graph_snapshots":[{"event_id":"sha256:497c4e93f99bb91b9606121173b31c7435609accbaff816c81509ba8198cec05","target":"graph","created_at":"2026-07-05T06:35:50Z","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/2304.03323/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tools to generate high quality synthetic speech signal that is perceptually indistinguishable from speech recorded from human speakers are easily available. Several approaches have been proposed for detecting synthetic speech. Many of these approaches use deep learning methods as a black box without providing reasoning for the decisions they make. This limits the interpretability of these approaches. In this paper, we propose Disentangled Spectrogram Variational Auto Encoder (DSVAE) which is a two staged trained variational autoencoder that processes spectrograms of speech using disentangled r","authors_text":"Amit Kumar Singh Yadav, Edward J. Delp, Kratika Bhagtani, Paolo Bestagini, Stefano Tubaro, Ziyue Xiang","cross_cats":["cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-04-06T18:37:26Z","title":"DSVAE: Interpretable Disentangled Representation for Synthetic Speech Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03323","kind":"arxiv","version":2},"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":"sha256:33b4653e81083892f968f76632920863cc0e5e79da06918eceaf1adbf774e168","target":"record","created_at":"2026-07-05T06:35:50Z","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":"6c48258cc5fce5611382c850ca72707bef585df70952c884a66abdd2ef858b82","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-04-06T18:37:26Z","title_canon_sha256":"91a90bf061abd5bc0b60f4dd0d8c23763d808f1b0c1c86fa8145a4d78ff5769a"},"schema_version":"1.0","source":{"id":"2304.03323","kind":"arxiv","version":2}},"canonical_sha256":"f87f338aad52df7c7c006159d0013e9ad588a6f19c482868b14af7ffdace8f3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f87f338aad52df7c7c006159d0013e9ad588a6f19c482868b14af7ffdace8f3f","first_computed_at":"2026-07-05T06:35:50.217381Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:35:50.217381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6VOSi4KRAB/rustJwyCEhRhNWwCHpYT1hKTOdjPtp93UuKBFWLXkEk3ZkdN8zLNkVetfPSkFddPzFUIZRUozBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:35:50.217865Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.03323","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33b4653e81083892f968f76632920863cc0e5e79da06918eceaf1adbf774e168","sha256:497c4e93f99bb91b9606121173b31c7435609accbaff816c81509ba8198cec05"],"state_sha256":"53144883b003c315f32026c603bbeabfec87ceb1e7f75e3023fc02a3359d54de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zOuDZugJYADuiq7cfYAImiKMit2G0Rkm4/3uzPa2+nTtWolmP442fj8Di00Yo4Z8fYxKxMhYOo2eA4sAQn5nDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T23:54:41.816879Z","bundle_sha256":"feb363a0cffc8d9499d0a664d8506f0dfa591144092de943458e3be0be26d312"}}