{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:YK7J6YGNWAR22TOHVD6MRRQY6C","short_pith_number":"pith:YK7J6YGN","canonical_record":{"source":{"id":"1904.10446","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-23T17:53:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cedcbf40248d42512ccc8325f005f0dac98f37f4cd97c0c30e707b9bf45df455","abstract_canon_sha256":"4fabf532218917011f7c0230b33cba29e1f69d7db3690812aa928e3929ebf7b7"},"schema_version":"1.0"},"canonical_sha256":"c2be9f60cdb023ad4dc7a8fcc8c618f0ab46d220eab45e0b7f87af70b978a65b","source":{"kind":"arxiv","id":"1904.10446","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.10446","created_at":"2026-05-17T23:47:54Z"},{"alias_kind":"arxiv_version","alias_value":"1904.10446v1","created_at":"2026-05-17T23:47:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.10446","created_at":"2026-05-17T23:47:54Z"},{"alias_kind":"pith_short_12","alias_value":"YK7J6YGNWAR2","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YK7J6YGNWAR22TOH","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YK7J6YGN","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:YK7J6YGNWAR22TOHVD6MRRQY6C","target":"record","payload":{"canonical_record":{"source":{"id":"1904.10446","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-23T17:53:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cedcbf40248d42512ccc8325f005f0dac98f37f4cd97c0c30e707b9bf45df455","abstract_canon_sha256":"4fabf532218917011f7c0230b33cba29e1f69d7db3690812aa928e3929ebf7b7"},"schema_version":"1.0"},"canonical_sha256":"c2be9f60cdb023ad4dc7a8fcc8c618f0ab46d220eab45e0b7f87af70b978a65b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:54.143198Z","signature_b64":"f3+U6mYlU+mj+dFbpVGvHMSGguPwQx+Lo/3YHnAhtpNzhxQqpWPM294HeC23MExX+ED4FarjYqvzSIUUobToCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2be9f60cdb023ad4dc7a8fcc8c618f0ab46d220eab45e0b7f87af70b978a65b","last_reissued_at":"2026-05-17T23:47:54.142702Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:54.142702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.10446","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":"2026-05-17T23:47:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+yhZW2rUl42VG5uFHpd3ii8Wcqj80EPDYevO3iMJccQWEqL1lYgitfHfPeFQg54AZchKTBt9Viq9Yn14J3ZMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:55:18.106126Z"},"content_sha256":"3cafcd4c7d44c4312cb6e39a026e03d98060bc59f28e9830379b195e92ddd8af","schema_version":"1.0","event_id":"sha256:3cafcd4c7d44c4312cb6e39a026e03d98060bc59f28e9830379b195e92ddd8af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:YK7J6YGNWAR22TOHVD6MRRQY6C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generated Loss, Augmented Training, and Multiscale VAE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gautam Hathi, Jason Chou","submitted_at":"2019-04-23T17:53:59Z","abstract_excerpt":"The variational autoencoder (VAE) framework remains a popular option for training unsupervised generative models, especially for discrete data where generative adversarial networks (GANs) require workaround to create gradient for the generator. In our work modeling US postal addresses, we show that our discrete VAE with tree recursive architecture demonstrates limited capability of capturing field correlations within structured data, even after overcoming the challenge of posterior collapse with scheduled sampling and tuning of the KL-divergence weight $\\beta$. Worse, VAE seems to have difficu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.10446","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":""},"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":"2026-05-17T23:47:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"751ejMlTNrnPb/SxLjnUxFgXf24YzaJh3A3g6lChmqPsjBxpepiDN/+FGOxftpVPAE8XHFOiNgqatqfGAal9Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:55:18.106629Z"},"content_sha256":"af04a6de03f81a45da4bf9f6e09e873288560a608233610afd8348d293c2bae9","schema_version":"1.0","event_id":"sha256:af04a6de03f81a45da4bf9f6e09e873288560a608233610afd8348d293c2bae9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YK7J6YGNWAR22TOHVD6MRRQY6C/bundle.json","state_url":"https://pith.science/pith/YK7J6YGNWAR22TOHVD6MRRQY6C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YK7J6YGNWAR22TOHVD6MRRQY6C/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":"2026-08-21T17:55:18Z","links":{"resolver":"https://pith.science/pith/YK7J6YGNWAR22TOHVD6MRRQY6C","bundle":"https://pith.science/pith/YK7J6YGNWAR22TOHVD6MRRQY6C/bundle.json","state":"https://pith.science/pith/YK7J6YGNWAR22TOHVD6MRRQY6C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YK7J6YGNWAR22TOHVD6MRRQY6C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YK7J6YGNWAR22TOHVD6MRRQY6C","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":"4fabf532218917011f7c0230b33cba29e1f69d7db3690812aa928e3929ebf7b7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-23T17:53:59Z","title_canon_sha256":"cedcbf40248d42512ccc8325f005f0dac98f37f4cd97c0c30e707b9bf45df455"},"schema_version":"1.0","source":{"id":"1904.10446","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.10446","created_at":"2026-05-17T23:47:54Z"},{"alias_kind":"arxiv_version","alias_value":"1904.10446v1","created_at":"2026-05-17T23:47:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.10446","created_at":"2026-05-17T23:47:54Z"},{"alias_kind":"pith_short_12","alias_value":"YK7J6YGNWAR2","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YK7J6YGNWAR22TOH","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YK7J6YGN","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:af04a6de03f81a45da4bf9f6e09e873288560a608233610afd8348d293c2bae9","target":"graph","created_at":"2026-05-17T23:47:54Z","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"},"paper":{"abstract_excerpt":"The variational autoencoder (VAE) framework remains a popular option for training unsupervised generative models, especially for discrete data where generative adversarial networks (GANs) require workaround to create gradient for the generator. In our work modeling US postal addresses, we show that our discrete VAE with tree recursive architecture demonstrates limited capability of capturing field correlations within structured data, even after overcoming the challenge of posterior collapse with scheduled sampling and tuning of the KL-divergence weight $\\beta$. Worse, VAE seems to have difficu","authors_text":"Gautam Hathi, Jason Chou","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-23T17:53:59Z","title":"Generated Loss, Augmented Training, and Multiscale VAE"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.10446","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":"sha256:3cafcd4c7d44c4312cb6e39a026e03d98060bc59f28e9830379b195e92ddd8af","target":"record","created_at":"2026-05-17T23:47:54Z","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":"4fabf532218917011f7c0230b33cba29e1f69d7db3690812aa928e3929ebf7b7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-23T17:53:59Z","title_canon_sha256":"cedcbf40248d42512ccc8325f005f0dac98f37f4cd97c0c30e707b9bf45df455"},"schema_version":"1.0","source":{"id":"1904.10446","kind":"arxiv","version":1}},"canonical_sha256":"c2be9f60cdb023ad4dc7a8fcc8c618f0ab46d220eab45e0b7f87af70b978a65b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2be9f60cdb023ad4dc7a8fcc8c618f0ab46d220eab45e0b7f87af70b978a65b","first_computed_at":"2026-05-17T23:47:54.142702Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:54.142702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f3+U6mYlU+mj+dFbpVGvHMSGguPwQx+Lo/3YHnAhtpNzhxQqpWPM294HeC23MExX+ED4FarjYqvzSIUUobToCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:54.143198Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.10446","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cafcd4c7d44c4312cb6e39a026e03d98060bc59f28e9830379b195e92ddd8af","sha256:af04a6de03f81a45da4bf9f6e09e873288560a608233610afd8348d293c2bae9"],"state_sha256":"f620accdf4bbd83e7e606f62412250d0b04c279ed82140a9b1f44a7c22ddb619"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WEHNqwkjF5EsLcE1E7kRZ6hZ6+rEUjGSwbXuCykInSZlF4sPeDCmOQcUfcQtuxxWou3lJpqWV2v40IyrfXUDDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T17:55:18.111253Z","bundle_sha256":"7547559bac55cb24193896bba5162e2d3fca4c7181a69728e6550a3905a6a0b8"}}