{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:X3EDENFZVSOXQMH5L35ILV5HT3","short_pith_number":"pith:X3EDENFZ","schema_version":"1.0","canonical_sha256":"bec83234b9ac9d7830fd5efa85d7a79efedca716b4b5eefeb2399da7a9e981da","source":{"kind":"arxiv","id":"2605.21484","version":1},"attestation_state":"computed","paper":{"title":"One-Step Distillation of Discrete Diffusion Image Generators via Fixed-Point Iteration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoyang Wang, Yunhai Tong","submitted_at":"2026-05-20T17:59:10Z","abstract_excerpt":"Discrete diffusion models excel at visual synthesis but rely on slow, iterative decoding. Existing single-step distillation methods attempt to bypass this bottleneck, either by training auxiliary score networks that effectively double compute, or by introducing specialized parameterizations and multi-stage pipelines that fragment optimization. In this paper, we introduce Fixed-Point Distillation (FPD), an end-to-end framework that constructs local correction targets by partially corrupting the student's one-step draft and refining it with a single teacher step. To compute the training objectiv"},"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":"2605.21484","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T17:59:10Z","cross_cats_sorted":[],"title_canon_sha256":"a62e339e271c823711e3e551dbd65f12220214e0bee88c5abe285caafb2ecb8d","abstract_canon_sha256":"3989e5f63c8521955f31b9dd7d90a3671081eb08188c4b97c050bbd114206111"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:39.480161Z","signature_b64":"8gW4nJ07ygGKP3lPzlUvIVm+MFrGbHbc0UX8P0cxZ3z++EmuHDgqu/SovXnuuITVlKW8f7V0ftJBDri6P0q+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bec83234b9ac9d7830fd5efa85d7a79efedca716b4b5eefeb2399da7a9e981da","last_reissued_at":"2026-05-21T02:05:39.479265Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:39.479265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-Step Distillation of Discrete Diffusion Image Generators via Fixed-Point Iteration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoyang Wang, Yunhai Tong","submitted_at":"2026-05-20T17:59:10Z","abstract_excerpt":"Discrete diffusion models excel at visual synthesis but rely on slow, iterative decoding. Existing single-step distillation methods attempt to bypass this bottleneck, either by training auxiliary score networks that effectively double compute, or by introducing specialized parameterizations and multi-stage pipelines that fragment optimization. In this paper, we introduce Fixed-Point Distillation (FPD), an end-to-end framework that constructs local correction targets by partially corrupting the student's one-step draft and refining it with a single teacher step. To compute the training objectiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21484","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/2605.21484/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":"2605.21484","created_at":"2026-05-21T02:05:39.479468+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21484v1","created_at":"2026-05-21T02:05:39.479468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21484","created_at":"2026-05-21T02:05:39.479468+00:00"},{"alias_kind":"pith_short_12","alias_value":"X3EDENFZVSOX","created_at":"2026-05-21T02:05:39.479468+00:00"},{"alias_kind":"pith_short_16","alias_value":"X3EDENFZVSOXQMH5","created_at":"2026-05-21T02:05:39.479468+00:00"},{"alias_kind":"pith_short_8","alias_value":"X3EDENFZ","created_at":"2026-05-21T02:05:39.479468+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/X3EDENFZVSOXQMH5L35ILV5HT3","json":"https://pith.science/pith/X3EDENFZVSOXQMH5L35ILV5HT3.json","graph_json":"https://pith.science/api/pith-number/X3EDENFZVSOXQMH5L35ILV5HT3/graph.json","events_json":"https://pith.science/api/pith-number/X3EDENFZVSOXQMH5L35ILV5HT3/events.json","paper":"https://pith.science/paper/X3EDENFZ"},"agent_actions":{"view_html":"https://pith.science/pith/X3EDENFZVSOXQMH5L35ILV5HT3","download_json":"https://pith.science/pith/X3EDENFZVSOXQMH5L35ILV5HT3.json","view_paper":"https://pith.science/paper/X3EDENFZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21484&json=true","fetch_graph":"https://pith.science/api/pith-number/X3EDENFZVSOXQMH5L35ILV5HT3/graph.json","fetch_events":"https://pith.science/api/pith-number/X3EDENFZVSOXQMH5L35ILV5HT3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X3EDENFZVSOXQMH5L35ILV5HT3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X3EDENFZVSOXQMH5L35ILV5HT3/action/storage_attestation","attest_author":"https://pith.science/pith/X3EDENFZVSOXQMH5L35ILV5HT3/action/author_attestation","sign_citation":"https://pith.science/pith/X3EDENFZVSOXQMH5L35ILV5HT3/action/citation_signature","submit_replication":"https://pith.science/pith/X3EDENFZVSOXQMH5L35ILV5HT3/action/replication_record"}},"created_at":"2026-05-21T02:05:39.479468+00:00","updated_at":"2026-05-21T02:05:39.479468+00:00"}