{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WWOBF6FIZQYRNMPROX6ZJRJRTW","short_pith_number":"pith:WWOBF6FI","schema_version":"1.0","canonical_sha256":"b59c12f8a8cc3116b1f175fd94c5319da1a7688dd8386ffbe7dc962b194ba031","source":{"kind":"arxiv","id":"2502.14831","version":3},"attestation_state":"computed","paper":{"title":"Improving the Diffusability of Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Benran Hu, Ivan Skorokhodov, Rameen Abdal, Sergey Tulyakov, Sharath Girish, Willi Menapace, Yanyu Li","submitted_at":"2025-02-20T18:45:44Z","abstract_excerpt":"Latent diffusion models have emerged as the leading approach for generating high-quality images and videos, utilizing compressed latent representations to reduce the computational burden of the diffusion process. While recent advancements have primarily focused on scaling diffusion backbones and improving autoencoder reconstruction quality, the interaction between these components has received comparatively less attention. In this work, we perform a spectral analysis of modern autoencoders and identify inordinate high-frequency components in their latent spaces, which are especially pronounced"},"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":"2502.14831","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-20T18:45:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8d34e60687b1290240462fd6ab56698a865ee85174a1852c8e4147e55ee2ac9d","abstract_canon_sha256":"733f5918246f311b046cf90c66d407cedb4ff50d3f53cc39e65f7186a702e5d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:41.754532Z","signature_b64":"Y9N9FLXHPDPPRFrl+Hd3nfg0JOZTepMJJ5rUCPL3YoirRbo6IyBAdMI5gFompEwJRr8+mWXOKHXpmG6AWVMLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b59c12f8a8cc3116b1f175fd94c5319da1a7688dd8386ffbe7dc962b194ba031","last_reissued_at":"2026-07-05T11:17:41.754014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:41.754014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving the Diffusability of Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Benran Hu, Ivan Skorokhodov, Rameen Abdal, Sergey Tulyakov, Sharath Girish, Willi Menapace, Yanyu Li","submitted_at":"2025-02-20T18:45:44Z","abstract_excerpt":"Latent diffusion models have emerged as the leading approach for generating high-quality images and videos, utilizing compressed latent representations to reduce the computational burden of the diffusion process. While recent advancements have primarily focused on scaling diffusion backbones and improving autoencoder reconstruction quality, the interaction between these components has received comparatively less attention. In this work, we perform a spectral analysis of modern autoencoders and identify inordinate high-frequency components in their latent spaces, which are especially pronounced"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14831","kind":"arxiv","version":3},"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/2502.14831/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":"2502.14831","created_at":"2026-07-05T11:17:41.754080+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14831v3","created_at":"2026-07-05T11:17:41.754080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14831","created_at":"2026-07-05T11:17:41.754080+00:00"},{"alias_kind":"pith_short_12","alias_value":"WWOBF6FIZQYR","created_at":"2026-07-05T11:17:41.754080+00:00"},{"alias_kind":"pith_short_16","alias_value":"WWOBF6FIZQYRNMPR","created_at":"2026-07-05T11:17:41.754080+00:00"},{"alias_kind":"pith_short_8","alias_value":"WWOBF6FI","created_at":"2026-07-05T11:17:41.754080+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24888","citing_title":"DiffusionBench: On Holistic Evaluation of Diffusion Transformers","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03578","citing_title":"Diffusing in the Right Space: A Systematic Study of Latent Diffusability","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15193","citing_title":"Aligning Latent Geometry for Spherical Flow Matching in Image Generation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00635","citing_title":"How Neural Losses Shape VAE Latents","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21981","citing_title":"RiT: Vanilla Diffusion Transformers Suffice in Representation Space","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17087","citing_title":"The Learnability Gap in Medical Latent Diffusion","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02134","citing_title":"Video Generation with Predictive Latents","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16479","citing_title":"Latent-Compressed Variational Autoencoder for Video Diffusion Models","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07915","citing_title":"What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WWOBF6FIZQYRNMPROX6ZJRJRTW","json":"https://pith.science/pith/WWOBF6FIZQYRNMPROX6ZJRJRTW.json","graph_json":"https://pith.science/api/pith-number/WWOBF6FIZQYRNMPROX6ZJRJRTW/graph.json","events_json":"https://pith.science/api/pith-number/WWOBF6FIZQYRNMPROX6ZJRJRTW/events.json","paper":"https://pith.science/paper/WWOBF6FI"},"agent_actions":{"view_html":"https://pith.science/pith/WWOBF6FIZQYRNMPROX6ZJRJRTW","download_json":"https://pith.science/pith/WWOBF6FIZQYRNMPROX6ZJRJRTW.json","view_paper":"https://pith.science/paper/WWOBF6FI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14831&json=true","fetch_graph":"https://pith.science/api/pith-number/WWOBF6FIZQYRNMPROX6ZJRJRTW/graph.json","fetch_events":"https://pith.science/api/pith-number/WWOBF6FIZQYRNMPROX6ZJRJRTW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WWOBF6FIZQYRNMPROX6ZJRJRTW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WWOBF6FIZQYRNMPROX6ZJRJRTW/action/storage_attestation","attest_author":"https://pith.science/pith/WWOBF6FIZQYRNMPROX6ZJRJRTW/action/author_attestation","sign_citation":"https://pith.science/pith/WWOBF6FIZQYRNMPROX6ZJRJRTW/action/citation_signature","submit_replication":"https://pith.science/pith/WWOBF6FIZQYRNMPROX6ZJRJRTW/action/replication_record"}},"created_at":"2026-07-05T11:17:41.754080+00:00","updated_at":"2026-07-05T11:17:41.754080+00:00"}