{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GZP4JU7UOJP4QQRO3IFVMEKZJ4","short_pith_number":"pith:GZP4JU7U","schema_version":"1.0","canonical_sha256":"365fc4d3f4725fc8422eda0b5611594f07b4bfc8209e72cb2c25927dfb5049a5","source":{"kind":"arxiv","id":"2511.09180","version":1},"attestation_state":"computed","paper":{"title":"FSampler: Training Free Acceleration of Diffusion Sampling via Epsilon Extrapolation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Michael A. Vladimir","submitted_at":"2025-11-12T10:21:25Z","abstract_excerpt":"FSampler is a training free, sampler agnostic execution layer that accelerates diffusion sampling by reducing the number of function evaluations (NFE). FSampler maintains a short history of denoising signals (epsilon) from recent real model calls and extrapolates the next epsilon using finite difference predictors at second order, third order, or fourth order, falling back to lower order when history is insufficient. On selected steps the predicted epsilon substitutes the model call while keeping each sampler's update rule unchanged. Predicted epsilons are validated for finiteness and magnitud"},"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":"2511.09180","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-12T10:21:25Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"58ed1c68310c7bb021d60c4148de66621b2725d78d283024644ac1b9f477470f","abstract_canon_sha256":"679fcbd681afc8a8475e4d0d9bcc851e837811a2863b2675763cd349a77d0495"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T20:23:29.159793Z","signature_b64":"sqmDZf/mc3iRHamGfDwviuJMCHH1q7V8Yjd1MhXH8gt9FXcJVfhopRa5gRUAoZeftmfxssFnaVXgfaKNhIsEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"365fc4d3f4725fc8422eda0b5611594f07b4bfc8209e72cb2c25927dfb5049a5","last_reissued_at":"2026-07-10T20:23:29.158377Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T20:23:29.158377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FSampler: Training Free Acceleration of Diffusion Sampling via Epsilon Extrapolation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Michael A. Vladimir","submitted_at":"2025-11-12T10:21:25Z","abstract_excerpt":"FSampler is a training free, sampler agnostic execution layer that accelerates diffusion sampling by reducing the number of function evaluations (NFE). FSampler maintains a short history of denoising signals (epsilon) from recent real model calls and extrapolates the next epsilon using finite difference predictors at second order, third order, or fourth order, falling back to lower order when history is insufficient. On selected steps the predicted epsilon substitutes the model call while keeping each sampler's update rule unchanged. Predicted epsilons are validated for finiteness and magnitud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.09180","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/2511.09180/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":"2511.09180","created_at":"2026-07-10T20:23:29.158445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.09180v1","created_at":"2026-07-10T20:23:29.158445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.09180","created_at":"2026-07-10T20:23:29.158445+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZP4JU7UOJP4","created_at":"2026-07-10T20:23:29.158445+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZP4JU7UOJP4QQRO","created_at":"2026-07-10T20:23:29.158445+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZP4JU7U","created_at":"2026-07-10T20:23:29.158445+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/GZP4JU7UOJP4QQRO3IFVMEKZJ4","json":"https://pith.science/pith/GZP4JU7UOJP4QQRO3IFVMEKZJ4.json","graph_json":"https://pith.science/api/pith-number/GZP4JU7UOJP4QQRO3IFVMEKZJ4/graph.json","events_json":"https://pith.science/api/pith-number/GZP4JU7UOJP4QQRO3IFVMEKZJ4/events.json","paper":"https://pith.science/paper/GZP4JU7U"},"agent_actions":{"view_html":"https://pith.science/pith/GZP4JU7UOJP4QQRO3IFVMEKZJ4","download_json":"https://pith.science/pith/GZP4JU7UOJP4QQRO3IFVMEKZJ4.json","view_paper":"https://pith.science/paper/GZP4JU7U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.09180&json=true","fetch_graph":"https://pith.science/api/pith-number/GZP4JU7UOJP4QQRO3IFVMEKZJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/GZP4JU7UOJP4QQRO3IFVMEKZJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZP4JU7UOJP4QQRO3IFVMEKZJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZP4JU7UOJP4QQRO3IFVMEKZJ4/action/storage_attestation","attest_author":"https://pith.science/pith/GZP4JU7UOJP4QQRO3IFVMEKZJ4/action/author_attestation","sign_citation":"https://pith.science/pith/GZP4JU7UOJP4QQRO3IFVMEKZJ4/action/citation_signature","submit_replication":"https://pith.science/pith/GZP4JU7UOJP4QQRO3IFVMEKZJ4/action/replication_record"}},"created_at":"2026-07-10T20:23:29.158445+00:00","updated_at":"2026-07-10T20:23:29.158445+00:00"}