{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:24NP4JIY7XNDNC5VM7G73KFC3D","short_pith_number":"pith:24NP4JIY","canonical_record":{"source":{"id":"2504.13214","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-16T13:51:41Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"00a415d751658bb9259f9e883fe9b00ca1a90976c8a251653062b3998fc31738","abstract_canon_sha256":"98f049cb8006e38eb04a8e9fc0c18471a4d63f845f7078376deb5bf816244cde"},"schema_version":"1.0"},"canonical_sha256":"d71afe2518fdda368bb567cdfda8a2d8c5804e9cf851e12026e1360ad50cd8a7","source":{"kind":"arxiv","id":"2504.13214","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13214","created_at":"2026-07-05T10:50:50Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13214v1","created_at":"2026-07-05T10:50:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13214","created_at":"2026-07-05T10:50:50Z"},{"alias_kind":"pith_short_12","alias_value":"24NP4JIY7XND","created_at":"2026-07-05T10:50:50Z"},{"alias_kind":"pith_short_16","alias_value":"24NP4JIY7XNDNC5V","created_at":"2026-07-05T10:50:50Z"},{"alias_kind":"pith_short_8","alias_value":"24NP4JIY","created_at":"2026-07-05T10:50:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:24NP4JIY7XNDNC5VM7G73KFC3D","target":"record","payload":{"canonical_record":{"source":{"id":"2504.13214","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-16T13:51:41Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"00a415d751658bb9259f9e883fe9b00ca1a90976c8a251653062b3998fc31738","abstract_canon_sha256":"98f049cb8006e38eb04a8e9fc0c18471a4d63f845f7078376deb5bf816244cde"},"schema_version":"1.0"},"canonical_sha256":"d71afe2518fdda368bb567cdfda8a2d8c5804e9cf851e12026e1360ad50cd8a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:50.587907Z","signature_b64":"y36z3zE+35vMM/2CkIwDRspn+c9fjI2Kn20O6JDteZILJfq40QoLac543ft9FC1p65VD0cvG20ouX9nm+pyKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d71afe2518fdda368bb567cdfda8a2d8c5804e9cf851e12026e1360ad50cd8a7","last_reissued_at":"2026-07-05T10:50:50.587347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:50.587347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.13214","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":"2026-07-05T10:50:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zOAe5fku9Vqlomg7SswYmJ2c9Tzf/dq8DCkDKNA5CRotWrH2vGcDykh1ci+1SZmT6BJ/9REiNIYETpveW99KBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:11:42.939697Z"},"content_sha256":"957d40eff8898a10a093785a90334f31000f4e32999c12ed9622d344fee9ff47","schema_version":"1.0","event_id":"sha256:957d40eff8898a10a093785a90334f31000f4e32999c12ed9622d344fee9ff47"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:24NP4JIY7XNDNC5VM7G73KFC3D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Wavelet-based Variational Autoencoders for High-Resolution Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Andrew Kiruluta","submitted_at":"2025-04-16T13:51:41Z","abstract_excerpt":"Variational Autoencoders (VAEs) are powerful generative models capable of learning compact latent representations. However, conventional VAEs often generate relatively blurry images due to their assumption of an isotropic Gaussian latent space and constraints in capturing high-frequency details. In this paper, we explore a novel wavelet-based approach (Wavelet-VAE) in which the latent space is constructed using multi-scale Haar wavelet coefficients. We propose a comprehensive method to encode the image features into multi-scale detail and approximation coefficients and introduce a learnable no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13214","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.13214/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":"2026-07-05T10:50:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ErVyi7r7+oHTtc1i3cm5TAmx+D7NcCR6o4JDl7ltTH86Zmo0hp4OOuxO55EKjeD/rElPLcjp7ptEaRIKz2d4Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:11:42.940225Z"},"content_sha256":"0b3b9e86081c31498471955488cc1708b13dfb37974a15ca67700a335f40e4fa","schema_version":"1.0","event_id":"sha256:0b3b9e86081c31498471955488cc1708b13dfb37974a15ca67700a335f40e4fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/24NP4JIY7XNDNC5VM7G73KFC3D/bundle.json","state_url":"https://pith.science/pith/24NP4JIY7XNDNC5VM7G73KFC3D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/24NP4JIY7XNDNC5VM7G73KFC3D/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":"2026-08-18T19:11:42Z","links":{"resolver":"https://pith.science/pith/24NP4JIY7XNDNC5VM7G73KFC3D","bundle":"https://pith.science/pith/24NP4JIY7XNDNC5VM7G73KFC3D/bundle.json","state":"https://pith.science/pith/24NP4JIY7XNDNC5VM7G73KFC3D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/24NP4JIY7XNDNC5VM7G73KFC3D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:24NP4JIY7XNDNC5VM7G73KFC3D","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":"98f049cb8006e38eb04a8e9fc0c18471a4d63f845f7078376deb5bf816244cde","cross_cats_sorted":["eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-16T13:51:41Z","title_canon_sha256":"00a415d751658bb9259f9e883fe9b00ca1a90976c8a251653062b3998fc31738"},"schema_version":"1.0","source":{"id":"2504.13214","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13214","created_at":"2026-07-05T10:50:50Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13214v1","created_at":"2026-07-05T10:50:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13214","created_at":"2026-07-05T10:50:50Z"},{"alias_kind":"pith_short_12","alias_value":"24NP4JIY7XND","created_at":"2026-07-05T10:50:50Z"},{"alias_kind":"pith_short_16","alias_value":"24NP4JIY7XNDNC5V","created_at":"2026-07-05T10:50:50Z"},{"alias_kind":"pith_short_8","alias_value":"24NP4JIY","created_at":"2026-07-05T10:50:50Z"}],"graph_snapshots":[{"event_id":"sha256:0b3b9e86081c31498471955488cc1708b13dfb37974a15ca67700a335f40e4fa","target":"graph","created_at":"2026-07-05T10:50:50Z","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/2504.13214/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Variational Autoencoders (VAEs) are powerful generative models capable of learning compact latent representations. However, conventional VAEs often generate relatively blurry images due to their assumption of an isotropic Gaussian latent space and constraints in capturing high-frequency details. In this paper, we explore a novel wavelet-based approach (Wavelet-VAE) in which the latent space is constructed using multi-scale Haar wavelet coefficients. We propose a comprehensive method to encode the image features into multi-scale detail and approximation coefficients and introduce a learnable no","authors_text":"Andrew Kiruluta","cross_cats":["eess.IV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-16T13:51:41Z","title":"Wavelet-based Variational Autoencoders for High-Resolution Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13214","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":"sha256:957d40eff8898a10a093785a90334f31000f4e32999c12ed9622d344fee9ff47","target":"record","created_at":"2026-07-05T10:50:50Z","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":"98f049cb8006e38eb04a8e9fc0c18471a4d63f845f7078376deb5bf816244cde","cross_cats_sorted":["eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-16T13:51:41Z","title_canon_sha256":"00a415d751658bb9259f9e883fe9b00ca1a90976c8a251653062b3998fc31738"},"schema_version":"1.0","source":{"id":"2504.13214","kind":"arxiv","version":1}},"canonical_sha256":"d71afe2518fdda368bb567cdfda8a2d8c5804e9cf851e12026e1360ad50cd8a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d71afe2518fdda368bb567cdfda8a2d8c5804e9cf851e12026e1360ad50cd8a7","first_computed_at":"2026-07-05T10:50:50.587347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:50.587347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y36z3zE+35vMM/2CkIwDRspn+c9fjI2Kn20O6JDteZILJfq40QoLac543ft9FC1p65VD0cvG20ouX9nm+pyKBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:50.587907Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.13214","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:957d40eff8898a10a093785a90334f31000f4e32999c12ed9622d344fee9ff47","sha256:0b3b9e86081c31498471955488cc1708b13dfb37974a15ca67700a335f40e4fa"],"state_sha256":"eb7b00365cfbbf41a363df0c6eb2c15f47a6a422df42c817d498166126f9c328"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qB1AuxnDQerfEAn1k+wUZ5FBDGLTpm9JyUIAlMMvEsiB/hLPX7Gyo2so+9WmWpHa7darAlmIDOrb7NnButNYCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T19:11:42.945092Z","bundle_sha256":"235a67b16a7c79ca429b464b871bf133c4ba721e4c7b0d810c8c71cfdc427492"}}