{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CAHL2442GFNJ5HYILJNXIPAYUU","short_pith_number":"pith:CAHL2442","canonical_record":{"source":{"id":"2303.09404","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-03-07T13:35:45Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"d525e1f65b994b7d5f121ea297858eeec7a947ec528951653fbc2004dce5c3f0","abstract_canon_sha256":"026df57166ecb1253de7d150616c051c349ee9ff02f3a8e13491e67a8d2aee53"},"schema_version":"1.0"},"canonical_sha256":"100ebd739a315a9e9f085a5b743c18a53b32796dae8ed9692770b63dee6ddb88","source":{"kind":"arxiv","id":"2303.09404","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.09404","created_at":"2026-07-05T06:08:54Z"},{"alias_kind":"arxiv_version","alias_value":"2303.09404v2","created_at":"2026-07-05T06:08:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09404","created_at":"2026-07-05T06:08:54Z"},{"alias_kind":"pith_short_12","alias_value":"CAHL2442GFNJ","created_at":"2026-07-05T06:08:54Z"},{"alias_kind":"pith_short_16","alias_value":"CAHL2442GFNJ5HYI","created_at":"2026-07-05T06:08:54Z"},{"alias_kind":"pith_short_8","alias_value":"CAHL2442","created_at":"2026-07-05T06:08:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CAHL2442GFNJ5HYILJNXIPAYUU","target":"record","payload":{"canonical_record":{"source":{"id":"2303.09404","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-03-07T13:35:45Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"d525e1f65b994b7d5f121ea297858eeec7a947ec528951653fbc2004dce5c3f0","abstract_canon_sha256":"026df57166ecb1253de7d150616c051c349ee9ff02f3a8e13491e67a8d2aee53"},"schema_version":"1.0"},"canonical_sha256":"100ebd739a315a9e9f085a5b743c18a53b32796dae8ed9692770b63dee6ddb88","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:54.639749Z","signature_b64":"+IkJGftdh5hO45T05ek7BY0vX+KW5XQA4WcxYbXbDCvzS4iJSfn0RJLck7sDiGvl6LcWXCPTgKdVT7OmLS/eDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"100ebd739a315a9e9f085a5b743c18a53b32796dae8ed9692770b63dee6ddb88","last_reissued_at":"2026-07-05T06:08:54.639336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:54.639336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.09404","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":"2026-07-05T06:08:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J9imX9RP0qTrieGVeylEswYSsqgP7Z++nC7yplNY3fxCIHKa2vRGqPRw8z5s8DAF4jHsCp5oOz3KFOE/e2GiDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:36:55.069811Z"},"content_sha256":"d27240f3881e1c1a71090e08d93a7efb28d11e93e41e9f25d18fa118be710a8e","schema_version":"1.0","event_id":"sha256:d27240f3881e1c1a71090e08d93a7efb28d11e93e41e9f25d18fa118be710a8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CAHL2442GFNJ5HYILJNXIPAYUU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speech Modeling with a Hierarchical Transformer Dynamical VAE","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Laurent Girin, Simon Leglaive, Xavier Alameda-Pineda, Xiaoyu Bie, Xiaoyu Lin","submitted_at":"2023-03-07T13:35:45Z","abstract_excerpt":"The dynamical variational autoencoders (DVAEs) are a family of latent-variable deep generative models that extends the VAE to model a sequence of observed data and a corresponding sequence of latent vectors. In almost all the DVAEs of the literature, the temporal dependencies within each sequence and across the two sequences are modeled with recurrent neural networks. In this paper, we propose to model speech signals with the Hierarchical Transformer DVAE (HiT-DVAE), which is a DVAE with two levels of latent variable (sequence-wise and frame-wise) and in which the temporal dependencies are imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09404","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/2303.09404/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":"2026-07-05T06:08:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D6unVr4wmMOu7PVnQnWiXeuIOIhnj52T4vDk227nAVjFuENprJIGzd4fGh6Y80Q5ESGwKamQn58orBe8+/niBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:36:55.070200Z"},"content_sha256":"036db470cc0353d87ba498466b46a97c29221986c292a13e8b2455d8cba9e001","schema_version":"1.0","event_id":"sha256:036db470cc0353d87ba498466b46a97c29221986c292a13e8b2455d8cba9e001"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CAHL2442GFNJ5HYILJNXIPAYUU/bundle.json","state_url":"https://pith.science/pith/CAHL2442GFNJ5HYILJNXIPAYUU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CAHL2442GFNJ5HYILJNXIPAYUU/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":"2026-07-07T14:36:55Z","links":{"resolver":"https://pith.science/pith/CAHL2442GFNJ5HYILJNXIPAYUU","bundle":"https://pith.science/pith/CAHL2442GFNJ5HYILJNXIPAYUU/bundle.json","state":"https://pith.science/pith/CAHL2442GFNJ5HYILJNXIPAYUU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CAHL2442GFNJ5HYILJNXIPAYUU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CAHL2442GFNJ5HYILJNXIPAYUU","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":"026df57166ecb1253de7d150616c051c349ee9ff02f3a8e13491e67a8d2aee53","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-03-07T13:35:45Z","title_canon_sha256":"d525e1f65b994b7d5f121ea297858eeec7a947ec528951653fbc2004dce5c3f0"},"schema_version":"1.0","source":{"id":"2303.09404","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.09404","created_at":"2026-07-05T06:08:54Z"},{"alias_kind":"arxiv_version","alias_value":"2303.09404v2","created_at":"2026-07-05T06:08:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09404","created_at":"2026-07-05T06:08:54Z"},{"alias_kind":"pith_short_12","alias_value":"CAHL2442GFNJ","created_at":"2026-07-05T06:08:54Z"},{"alias_kind":"pith_short_16","alias_value":"CAHL2442GFNJ5HYI","created_at":"2026-07-05T06:08:54Z"},{"alias_kind":"pith_short_8","alias_value":"CAHL2442","created_at":"2026-07-05T06:08:54Z"}],"graph_snapshots":[{"event_id":"sha256:036db470cc0353d87ba498466b46a97c29221986c292a13e8b2455d8cba9e001","target":"graph","created_at":"2026-07-05T06:08:54Z","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/2303.09404/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The dynamical variational autoencoders (DVAEs) are a family of latent-variable deep generative models that extends the VAE to model a sequence of observed data and a corresponding sequence of latent vectors. In almost all the DVAEs of the literature, the temporal dependencies within each sequence and across the two sequences are modeled with recurrent neural networks. In this paper, we propose to model speech signals with the Hierarchical Transformer DVAE (HiT-DVAE), which is a DVAE with two levels of latent variable (sequence-wise and frame-wise) and in which the temporal dependencies are imp","authors_text":"Laurent Girin, Simon Leglaive, Xavier Alameda-Pineda, Xiaoyu Bie, Xiaoyu Lin","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-03-07T13:35:45Z","title":"Speech Modeling with a Hierarchical Transformer Dynamical VAE"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09404","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:d27240f3881e1c1a71090e08d93a7efb28d11e93e41e9f25d18fa118be710a8e","target":"record","created_at":"2026-07-05T06:08:54Z","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":"026df57166ecb1253de7d150616c051c349ee9ff02f3a8e13491e67a8d2aee53","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-03-07T13:35:45Z","title_canon_sha256":"d525e1f65b994b7d5f121ea297858eeec7a947ec528951653fbc2004dce5c3f0"},"schema_version":"1.0","source":{"id":"2303.09404","kind":"arxiv","version":2}},"canonical_sha256":"100ebd739a315a9e9f085a5b743c18a53b32796dae8ed9692770b63dee6ddb88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"100ebd739a315a9e9f085a5b743c18a53b32796dae8ed9692770b63dee6ddb88","first_computed_at":"2026-07-05T06:08:54.639336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:08:54.639336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+IkJGftdh5hO45T05ek7BY0vX+KW5XQA4WcxYbXbDCvzS4iJSfn0RJLck7sDiGvl6LcWXCPTgKdVT7OmLS/eDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:08:54.639749Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.09404","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d27240f3881e1c1a71090e08d93a7efb28d11e93e41e9f25d18fa118be710a8e","sha256:036db470cc0353d87ba498466b46a97c29221986c292a13e8b2455d8cba9e001"],"state_sha256":"df40c6daf0372ec681f486dd2193839f149ae060a529229014ffa407f5f44d26"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"87QIkdVe45jELbUMb2iw4nDGiM8jc959emmw3O8RvCGtULe2VHj5DGOogszhKJ+VttAZxvw2fKHOy6KrjGiCCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:36:55.072085Z","bundle_sha256":"4037e679d59e1d98dfa527e908d730403cfeb438f4847c92ba3623f5015e21b2"}}