{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OKKU6UWSVDOGZE2HAAP3IGX32C","short_pith_number":"pith:OKKU6UWS","schema_version":"1.0","canonical_sha256":"72954f52d2a8dc6c9347001fb41afbd0858670084cc849d78b9506df39f0f8fe","source":{"kind":"arxiv","id":"2203.05074","version":2},"attestation_state":"computed","paper":{"title":"The Transitive Information Theory and its Application to Deep Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Merja Hein\\\"aniemi, Najwa Laabid, Trung Ngo, Ville Hautam\\\"aki","submitted_at":"2022-03-09T22:35:02Z","abstract_excerpt":"Paradoxically, a Variational Autoencoder (VAE) could be pushed in two opposite directions, utilizing powerful decoder model for generating realistic images but collapsing the learned representation, or increasing regularization coefficient for disentangling representation but ultimately generating blurry examples. Existing methods narrow the issues to the rate-distortion trade-off between compression and reconstruction. We argue that a good reconstruction model does learn high capacity latents that encode more details, however, its use is hindered by two major issues: the prior is random noise"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2203.05074","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-09T22:35:02Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"5629121facffa43b861eb654275e814b1d24fa30f9b00b3fe6dc65a3e489c3ff","abstract_canon_sha256":"50d285581e92047dfa9905558067a78a05c7a79e60e720efedacfd6fa3e17c61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:18.654347Z","signature_b64":"4BgKClWsuOJHeoJsgDA+Xst/Ahu3oTZLT7nB6cZYNzKDhTcnEOx8MGDPai4E/up3Iq0OTMxg/6BkLbYWuNsEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72954f52d2a8dc6c9347001fb41afbd0858670084cc849d78b9506df39f0f8fe","last_reissued_at":"2026-07-05T04:09:18.653844Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:18.653844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Transitive Information Theory and its Application to Deep Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Merja Hein\\\"aniemi, Najwa Laabid, Trung Ngo, Ville Hautam\\\"aki","submitted_at":"2022-03-09T22:35:02Z","abstract_excerpt":"Paradoxically, a Variational Autoencoder (VAE) could be pushed in two opposite directions, utilizing powerful decoder model for generating realistic images but collapsing the learned representation, or increasing regularization coefficient for disentangling representation but ultimately generating blurry examples. Existing methods narrow the issues to the rate-distortion trade-off between compression and reconstruction. We argue that a good reconstruction model does learn high capacity latents that encode more details, however, its use is hindered by two major issues: the prior is random noise"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.05074","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/2203.05074/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2203.05074","created_at":"2026-07-05T04:09:18.653903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.05074v2","created_at":"2026-07-05T04:09:18.653903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.05074","created_at":"2026-07-05T04:09:18.653903+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKKU6UWSVDOG","created_at":"2026-07-05T04:09:18.653903+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKKU6UWSVDOGZE2H","created_at":"2026-07-05T04:09:18.653903+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKKU6UWS","created_at":"2026-07-05T04:09:18.653903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OKKU6UWSVDOGZE2HAAP3IGX32C","json":"https://pith.science/pith/OKKU6UWSVDOGZE2HAAP3IGX32C.json","graph_json":"https://pith.science/api/pith-number/OKKU6UWSVDOGZE2HAAP3IGX32C/graph.json","events_json":"https://pith.science/api/pith-number/OKKU6UWSVDOGZE2HAAP3IGX32C/events.json","paper":"https://pith.science/paper/OKKU6UWS"},"agent_actions":{"view_html":"https://pith.science/pith/OKKU6UWSVDOGZE2HAAP3IGX32C","download_json":"https://pith.science/pith/OKKU6UWSVDOGZE2HAAP3IGX32C.json","view_paper":"https://pith.science/paper/OKKU6UWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.05074&json=true","fetch_graph":"https://pith.science/api/pith-number/OKKU6UWSVDOGZE2HAAP3IGX32C/graph.json","fetch_events":"https://pith.science/api/pith-number/OKKU6UWSVDOGZE2HAAP3IGX32C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKKU6UWSVDOGZE2HAAP3IGX32C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKKU6UWSVDOGZE2HAAP3IGX32C/action/storage_attestation","attest_author":"https://pith.science/pith/OKKU6UWSVDOGZE2HAAP3IGX32C/action/author_attestation","sign_citation":"https://pith.science/pith/OKKU6UWSVDOGZE2HAAP3IGX32C/action/citation_signature","submit_replication":"https://pith.science/pith/OKKU6UWSVDOGZE2HAAP3IGX32C/action/replication_record"}},"created_at":"2026-07-05T04:09:18.653903+00:00","updated_at":"2026-07-05T04:09:18.653903+00:00"}