{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JA6RQZYS2L2ZJ3KDIPY4Q55RMQ","short_pith_number":"pith:JA6RQZYS","canonical_record":{"source":{"id":"2312.01133","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-12-02T13:14:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2207d8bf97679abd7b4da316e2b506f1eb7daaec0eaaa2173c2d748b4f15b3d5","abstract_canon_sha256":"20aa1a1a25c4a7525a53d8595c7d2df65e6bcf99391e2a424011d36f8286729c"},"schema_version":"1.0"},"canonical_sha256":"483d186712d2f594ed4343f1c877b1642f1ca7ef270948165f0a75d52421c395","source":{"kind":"arxiv","id":"2312.01133","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.01133","created_at":"2026-07-05T07:51:36Z"},{"alias_kind":"arxiv_version","alias_value":"2312.01133v2","created_at":"2026-07-05T07:51:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01133","created_at":"2026-07-05T07:51:36Z"},{"alias_kind":"pith_short_12","alias_value":"JA6RQZYS2L2Z","created_at":"2026-07-05T07:51:36Z"},{"alias_kind":"pith_short_16","alias_value":"JA6RQZYS2L2ZJ3KD","created_at":"2026-07-05T07:51:36Z"},{"alias_kind":"pith_short_8","alias_value":"JA6RQZYS","created_at":"2026-07-05T07:51:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JA6RQZYS2L2ZJ3KDIPY4Q55RMQ","target":"record","payload":{"canonical_record":{"source":{"id":"2312.01133","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-12-02T13:14:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2207d8bf97679abd7b4da316e2b506f1eb7daaec0eaaa2173c2d748b4f15b3d5","abstract_canon_sha256":"20aa1a1a25c4a7525a53d8595c7d2df65e6bcf99391e2a424011d36f8286729c"},"schema_version":"1.0"},"canonical_sha256":"483d186712d2f594ed4343f1c877b1642f1ca7ef270948165f0a75d52421c395","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:36.015012Z","signature_b64":"sufp9Jg760P+zXZTBYC/6Tp+eRmgVLYJWDaHqhMrXDT55pHMUjQV1TTXNqOWElkLcIstM0IpazBBOL9XGattBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"483d186712d2f594ed4343f1c877b1642f1ca7ef270948165f0a75d52421c395","last_reissued_at":"2026-07-05T07:51:36.014573Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:36.014573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.01133","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":"2026-07-05T07:51:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gioL2eQ6xP8TUvm+C0tOI/odpASeTZmQBcT0mH09Lf4mTEI0RJGZrr7Z+wzD3tJ40JfN3bEuwxMO3g+xjaieCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:07:14.766011Z"},"content_sha256":"c3ed62a2c93a4f5fa27593a69326c299f5ac11176d59a5b3ad62724cdb6b6586","schema_version":"1.0","event_id":"sha256:c3ed62a2c93a4f5fa27593a69326c299f5ac11176d59a5b3ad62724cdb6b6586"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JA6RQZYS2L2ZJ3KDIPY4Q55RMQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"$t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"HyunJong Lee, Jaehyuk Kwon, Joong-Ho Won, Juno Kim, Mincheol Cho","submitted_at":"2023-12-02T13:14:28Z","abstract_excerpt":"The variational autoencoder (VAE) typically employs a standard normal prior as a regularizer for the probabilistic latent encoder. However, the Gaussian tail often decays too quickly to effectively accommodate the encoded points, failing to preserve crucial structures hidden in the data. In this paper, we explore the use of heavy-tailed models to combat over-regularization. Drawing upon insights from information geometry, we propose $t^3$VAE, a modified VAE framework that incorporates Student's t-distributions for the prior, encoder, and decoder. This results in a joint model distribution of a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01133","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/2312.01133/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":"2026-07-05T07:51:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KHEMm3ZC5PS1zQAScn7pwLpeZGkalDI1V4kMaubOSnQQ2U4t6THPm4HjgdL7s/WEXibDNbesJC06sslhd5p/BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:07:14.766508Z"},"content_sha256":"5171c9bc389e72ec5d255aa9aec86ba68a19d4ce76c67fda24f3a896f4be5637","schema_version":"1.0","event_id":"sha256:5171c9bc389e72ec5d255aa9aec86ba68a19d4ce76c67fda24f3a896f4be5637"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JA6RQZYS2L2ZJ3KDIPY4Q55RMQ/bundle.json","state_url":"https://pith.science/pith/JA6RQZYS2L2ZJ3KDIPY4Q55RMQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JA6RQZYS2L2ZJ3KDIPY4Q55RMQ/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":"2026-07-31T14:07:14Z","links":{"resolver":"https://pith.science/pith/JA6RQZYS2L2ZJ3KDIPY4Q55RMQ","bundle":"https://pith.science/pith/JA6RQZYS2L2ZJ3KDIPY4Q55RMQ/bundle.json","state":"https://pith.science/pith/JA6RQZYS2L2ZJ3KDIPY4Q55RMQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JA6RQZYS2L2ZJ3KDIPY4Q55RMQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JA6RQZYS2L2ZJ3KDIPY4Q55RMQ","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":"20aa1a1a25c4a7525a53d8595c7d2df65e6bcf99391e2a424011d36f8286729c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-12-02T13:14:28Z","title_canon_sha256":"2207d8bf97679abd7b4da316e2b506f1eb7daaec0eaaa2173c2d748b4f15b3d5"},"schema_version":"1.0","source":{"id":"2312.01133","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.01133","created_at":"2026-07-05T07:51:36Z"},{"alias_kind":"arxiv_version","alias_value":"2312.01133v2","created_at":"2026-07-05T07:51:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01133","created_at":"2026-07-05T07:51:36Z"},{"alias_kind":"pith_short_12","alias_value":"JA6RQZYS2L2Z","created_at":"2026-07-05T07:51:36Z"},{"alias_kind":"pith_short_16","alias_value":"JA6RQZYS2L2ZJ3KD","created_at":"2026-07-05T07:51:36Z"},{"alias_kind":"pith_short_8","alias_value":"JA6RQZYS","created_at":"2026-07-05T07:51:36Z"}],"graph_snapshots":[{"event_id":"sha256:5171c9bc389e72ec5d255aa9aec86ba68a19d4ce76c67fda24f3a896f4be5637","target":"graph","created_at":"2026-07-05T07:51:36Z","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/2312.01133/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The variational autoencoder (VAE) typically employs a standard normal prior as a regularizer for the probabilistic latent encoder. However, the Gaussian tail often decays too quickly to effectively accommodate the encoded points, failing to preserve crucial structures hidden in the data. In this paper, we explore the use of heavy-tailed models to combat over-regularization. Drawing upon insights from information geometry, we propose $t^3$VAE, a modified VAE framework that incorporates Student's t-distributions for the prior, encoder, and decoder. This results in a joint model distribution of a","authors_text":"HyunJong Lee, Jaehyuk Kwon, Joong-Ho Won, Juno Kim, Mincheol Cho","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-12-02T13:14:28Z","title":"$t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01133","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:c3ed62a2c93a4f5fa27593a69326c299f5ac11176d59a5b3ad62724cdb6b6586","target":"record","created_at":"2026-07-05T07:51:36Z","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":"20aa1a1a25c4a7525a53d8595c7d2df65e6bcf99391e2a424011d36f8286729c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-12-02T13:14:28Z","title_canon_sha256":"2207d8bf97679abd7b4da316e2b506f1eb7daaec0eaaa2173c2d748b4f15b3d5"},"schema_version":"1.0","source":{"id":"2312.01133","kind":"arxiv","version":2}},"canonical_sha256":"483d186712d2f594ed4343f1c877b1642f1ca7ef270948165f0a75d52421c395","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"483d186712d2f594ed4343f1c877b1642f1ca7ef270948165f0a75d52421c395","first_computed_at":"2026-07-05T07:51:36.014573Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:36.014573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sufp9Jg760P+zXZTBYC/6Tp+eRmgVLYJWDaHqhMrXDT55pHMUjQV1TTXNqOWElkLcIstM0IpazBBOL9XGattBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:36.015012Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.01133","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3ed62a2c93a4f5fa27593a69326c299f5ac11176d59a5b3ad62724cdb6b6586","sha256:5171c9bc389e72ec5d255aa9aec86ba68a19d4ce76c67fda24f3a896f4be5637"],"state_sha256":"38a59a3d2a943a4f048ae6b1b1b268dd1e985944bb6cff52b4a6ee93f084570a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wc09UxfgspOQOvgDW6UFZd/91yK3ltruW9P5LYF85VIiSyYA0Ot5hTirufTqHQm516OgkBpyLKQkBcUL8tp4Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T14:07:14.771575Z","bundle_sha256":"b4aec160a2d512dd7b0aefc6f9a2352e5c6af7070a119fd2dca9efbd7c4acffe"}}