{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:THBHO7MOYFM7L2BGAJAFRYU4JK","merge_version":"pith-open-graph-merge-v1","event_count":9,"valid_event_count":9,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2204816fa4edc3514aacf22f63033f48c1c919b2d68eff86d3289af6ed069a91","cross_cats_sorted":["cs.AI","cs.CV","stat.CO","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T17:59:52Z","title_canon_sha256":"73a2d5177f96602bf72fb5fbd5fae8aa668bc418046b8fc2369e87a86198203d"},"schema_version":"1.0","source":{"id":"2605.21489","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21489","created_at":"2026-05-21T02:05:39Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21489v1","created_at":"2026-05-21T02:05:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21489","created_at":"2026-05-21T02:05:39Z"},{"alias_kind":"pith_short_12","alias_value":"THBHO7MOYFM7","created_at":"2026-05-21T02:05:39Z"},{"alias_kind":"pith_short_16","alias_value":"THBHO7MOYFM7L2BG","created_at":"2026-05-21T02:05:39Z"},{"alias_kind":"pith_short_8","alias_value":"THBHO7MO","created_at":"2026-05-21T02:05:39Z"}],"graph_snapshots":[{"event_id":"sha256:38683b1acca5b6822d55787f2cabd2d683fdcd12edfdc30bed17d17e5fd07f4c","target":"graph","created_at":"2026-05-21T02:05:39Z","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/2605.21489/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained diffusion models serve as frozen teachers feeding downstream pipelines such as text-to-3D, single-step distillation, and data attribution. The teacher gradients these pipelines consume are Monte Carlo (MC) expectations over noise levels and Gaussian noise samples; their estimator variance dominates compute cost because each draw requires expensive upstream work (rendering, simulation, encoding). We introduce CARV, a compute-aware variance-accounting framework that motivates a hierarchical MC estimator: amortize the expensive upstream computation over cheap diffusion-noise resamples,","authors_text":"James Lucas, Jesse Bettencourt, Jonathan Lorraine, Matan Atzmon, Xindi Wu","cross_cats":["cs.AI","cs.CV","stat.CO","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T17:59:52Z","title":"Variance Reduction for Expectations with Diffusion Teachers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21489","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":"sha256:89d4ee01cd67b0c381f49c9af54ad2186480b5cd92b29d3e85f66647e84a59d6","target":"record","created_at":"2026-05-21T02:05:39Z","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":"2204816fa4edc3514aacf22f63033f48c1c919b2d68eff86d3289af6ed069a91","cross_cats_sorted":["cs.AI","cs.CV","stat.CO","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T17:59:52Z","title_canon_sha256":"73a2d5177f96602bf72fb5fbd5fae8aa668bc418046b8fc2369e87a86198203d"},"schema_version":"1.0","source":{"id":"2605.21489","kind":"arxiv","version":1}},"canonical_sha256":"99c2777d8ec159f5e826024058e29c4a9ff709b3c6ee830210750eb8509cf17d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99c2777d8ec159f5e826024058e29c4a9ff709b3c6ee830210750eb8509cf17d","first_computed_at":"2026-05-21T02:05:39.715955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T02:05:39.715955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0GqfrWmfz2wWqohZpP9IdI/bR5JEsWiVC2E4RnuGhYJuS1hzO3KAn7BJLPDcue+0XrHPtwn3WeXAOA99XgdSDA==","signature_status":"signed_v1","signed_at":"2026-05-21T02:05:39.716766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21489","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:20d4384fe76e4fb60f38ae72c0d1e2cb533b148e1bbcc08609d1617fac96681f","sha256:a006648db46e24c3611c072ec83442ce9a36c7ab75fcc1aac08c36e733a6e399","sha256:a18ff922b9de0c1ce3c00d1c5bb248290ba1aaeb61c5863f9760d2c715ca69ea","sha256:bf936357ebfa145eb7ec9aae5ea0d2911b68b627e75fd020bd9165a62ca6291f","sha256:d0239a66fa3f68f622c358bdbca6e5601198b7c66db6b619fced482d10b6bc6a","sha256:ec7014bd37be49e6ee72a334069cbcf329bd360f202576116b7ca9f616830aec","sha256:ed9c1049a2d1bd82ae3a25075e53696acd174fbdff1e2c22f3d2f8e3694fc9ba"]}],"invalid_events":[],"applied_event_ids":["sha256:89d4ee01cd67b0c381f49c9af54ad2186480b5cd92b29d3e85f66647e84a59d6","sha256:38683b1acca5b6822d55787f2cabd2d683fdcd12edfdc30bed17d17e5fd07f4c"],"state_sha256":"e9d1b1caf65672df299e7b533ed84d28e8a8805d715ec1f2a7bf5a724d8b4dab"}