{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:57IXJSICXNYHYQZMFTPJ6GF4Q6","short_pith_number":"pith:57IXJSIC","schema_version":"1.0","canonical_sha256":"efd174c902bb707c432c2cde9f18bc878b735593ad31f25503656b89aef3612a","source":{"kind":"arxiv","id":"2510.04961","version":2},"attestation_state":"computed","paper":{"title":"SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jakob Verbeek, Matthieu Cord, Th\\'eophane Vallaeys","submitted_at":"2025-10-06T15:57:31Z","abstract_excerpt":"Tokenizers are a key component of state-of-the-art generative image models, extracting the most important features from the signal while reducing data dimension and redundancy. Most current tokenizers are based on KL-regularized variational autoencoders (KL-VAE), trained with reconstruction, perceptual and adversarial losses. Diffusion decoders have been proposed as a more principled alternative to model the distribution over images conditioned on the latent. However, matching the performance of KL-VAE still requires adversarial losses, as well as a higher decoding time due to iterative sampli"},"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":"2510.04961","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-06T15:57:31Z","cross_cats_sorted":[],"title_canon_sha256":"78b5ac3df5b953c638de0ee2afede2420532bca29d3005e63c43154b90bc5ac6","abstract_canon_sha256":"a870f25ccbc015cf8df54cf06b280d2fb485bb9473579f0e31715a905c1bbc90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:04.977450Z","signature_b64":"vh/oDUCYD+4EA+TB0gpz10XKV1tTIi1i5uFDuidA6CyL353bKwwWheSYZhb3hkAXzj3TsxKIJe2EA0pz0e50CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efd174c902bb707c432c2cde9f18bc878b735593ad31f25503656b89aef3612a","last_reissued_at":"2026-06-30T02:18:04.976923Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:04.976923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jakob Verbeek, Matthieu Cord, Th\\'eophane Vallaeys","submitted_at":"2025-10-06T15:57:31Z","abstract_excerpt":"Tokenizers are a key component of state-of-the-art generative image models, extracting the most important features from the signal while reducing data dimension and redundancy. Most current tokenizers are based on KL-regularized variational autoencoders (KL-VAE), trained with reconstruction, perceptual and adversarial losses. Diffusion decoders have been proposed as a more principled alternative to model the distribution over images conditioned on the latent. However, matching the performance of KL-VAE still requires adversarial losses, as well as a higher decoding time due to iterative sampli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.04961","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/2510.04961/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":"2510.04961","created_at":"2026-06-30T02:18:04.977006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.04961v2","created_at":"2026-06-30T02:18:04.977006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.04961","created_at":"2026-06-30T02:18:04.977006+00:00"},{"alias_kind":"pith_short_12","alias_value":"57IXJSICXNYH","created_at":"2026-06-30T02:18:04.977006+00:00"},{"alias_kind":"pith_short_16","alias_value":"57IXJSICXNYHYQZM","created_at":"2026-06-30T02:18:04.977006+00:00"},{"alias_kind":"pith_short_8","alias_value":"57IXJSIC","created_at":"2026-06-30T02:18:04.977006+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.23902","citing_title":"PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/57IXJSICXNYHYQZMFTPJ6GF4Q6","json":"https://pith.science/pith/57IXJSICXNYHYQZMFTPJ6GF4Q6.json","graph_json":"https://pith.science/api/pith-number/57IXJSICXNYHYQZMFTPJ6GF4Q6/graph.json","events_json":"https://pith.science/api/pith-number/57IXJSICXNYHYQZMFTPJ6GF4Q6/events.json","paper":"https://pith.science/paper/57IXJSIC"},"agent_actions":{"view_html":"https://pith.science/pith/57IXJSICXNYHYQZMFTPJ6GF4Q6","download_json":"https://pith.science/pith/57IXJSICXNYHYQZMFTPJ6GF4Q6.json","view_paper":"https://pith.science/paper/57IXJSIC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.04961&json=true","fetch_graph":"https://pith.science/api/pith-number/57IXJSICXNYHYQZMFTPJ6GF4Q6/graph.json","fetch_events":"https://pith.science/api/pith-number/57IXJSICXNYHYQZMFTPJ6GF4Q6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57IXJSICXNYHYQZMFTPJ6GF4Q6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57IXJSICXNYHYQZMFTPJ6GF4Q6/action/storage_attestation","attest_author":"https://pith.science/pith/57IXJSICXNYHYQZMFTPJ6GF4Q6/action/author_attestation","sign_citation":"https://pith.science/pith/57IXJSICXNYHYQZMFTPJ6GF4Q6/action/citation_signature","submit_replication":"https://pith.science/pith/57IXJSICXNYHYQZMFTPJ6GF4Q6/action/replication_record"}},"created_at":"2026-06-30T02:18:04.977006+00:00","updated_at":"2026-06-30T02:18:04.977006+00:00"}