{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:A3G7GZEAUEWUJE3OMTQAQ47VFR","short_pith_number":"pith:A3G7GZEA","schema_version":"1.0","canonical_sha256":"06cdf36480a12d44936e64e00873f52c728eef84f033886ffacef13e13c2cc64","source":{"kind":"arxiv","id":"2605.27006","version":1},"attestation_state":"computed","paper":{"title":"Sampling Data with Chains of Forward-Backward Diffusion Steps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","stat.ML"],"primary_cat":"cs.LG","authors_text":"Corinna Elena Wegner, Daniel J. Korchinski, Hyunmo Kang, Matthieu Wyart, Noam Itzhak Levi","submitted_at":"2026-05-26T13:26:36Z","abstract_excerpt":"Sampling from learned high-dimensional distributions is a foundational computational problem. We introduce U-turn chains: Markov chains obtained by iterating short forward-backward steps of a diffusion model, in which each step proposes a move that remains on the learned data manifold and, paired with a Metropolis-Hastings correction, samples from energy-modified targets. For synthetic languages, we show that minimal U-turn dynamics undergoes an ergodicity-breaking phase transition driven by fragmentation of the data manifold; ergodicity is restored at larger U-turn magnitude. In the non-ergod"},"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":"2605.27006","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T13:26:36Z","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"title_canon_sha256":"2834cfa893e8bef92aeb6b1736b4e470f4003b4d16e6695927cbc21cab19e6ea","abstract_canon_sha256":"2feef8ec5e345f56e6f097c3360e2e41468db9596ebb079c3a6134e7615811c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:23.802800Z","signature_b64":"grbNLTNcVhqKUGMrjjam29VWVYYBvqTs7ci/DOaCV0v5N9pO5MbFL59PLW0fO2JWV3LL4kaG16pc/UPR1fSuBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06cdf36480a12d44936e64e00873f52c728eef84f033886ffacef13e13c2cc64","last_reissued_at":"2026-05-27T01:06:23.802243Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:23.802243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sampling Data with Chains of Forward-Backward Diffusion Steps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","stat.ML"],"primary_cat":"cs.LG","authors_text":"Corinna Elena Wegner, Daniel J. Korchinski, Hyunmo Kang, Matthieu Wyart, Noam Itzhak Levi","submitted_at":"2026-05-26T13:26:36Z","abstract_excerpt":"Sampling from learned high-dimensional distributions is a foundational computational problem. We introduce U-turn chains: Markov chains obtained by iterating short forward-backward steps of a diffusion model, in which each step proposes a move that remains on the learned data manifold and, paired with a Metropolis-Hastings correction, samples from energy-modified targets. For synthetic languages, we show that minimal U-turn dynamics undergoes an ergodicity-breaking phase transition driven by fragmentation of the data manifold; ergodicity is restored at larger U-turn magnitude. In the non-ergod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27006","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/2605.27006/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":"2605.27006","created_at":"2026-05-27T01:06:23.802323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27006v1","created_at":"2026-05-27T01:06:23.802323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27006","created_at":"2026-05-27T01:06:23.802323+00:00"},{"alias_kind":"pith_short_12","alias_value":"A3G7GZEAUEWU","created_at":"2026-05-27T01:06:23.802323+00:00"},{"alias_kind":"pith_short_16","alias_value":"A3G7GZEAUEWUJE3O","created_at":"2026-05-27T01:06:23.802323+00:00"},{"alias_kind":"pith_short_8","alias_value":"A3G7GZEA","created_at":"2026-05-27T01:06:23.802323+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/A3G7GZEAUEWUJE3OMTQAQ47VFR","json":"https://pith.science/pith/A3G7GZEAUEWUJE3OMTQAQ47VFR.json","graph_json":"https://pith.science/api/pith-number/A3G7GZEAUEWUJE3OMTQAQ47VFR/graph.json","events_json":"https://pith.science/api/pith-number/A3G7GZEAUEWUJE3OMTQAQ47VFR/events.json","paper":"https://pith.science/paper/A3G7GZEA"},"agent_actions":{"view_html":"https://pith.science/pith/A3G7GZEAUEWUJE3OMTQAQ47VFR","download_json":"https://pith.science/pith/A3G7GZEAUEWUJE3OMTQAQ47VFR.json","view_paper":"https://pith.science/paper/A3G7GZEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27006&json=true","fetch_graph":"https://pith.science/api/pith-number/A3G7GZEAUEWUJE3OMTQAQ47VFR/graph.json","fetch_events":"https://pith.science/api/pith-number/A3G7GZEAUEWUJE3OMTQAQ47VFR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A3G7GZEAUEWUJE3OMTQAQ47VFR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A3G7GZEAUEWUJE3OMTQAQ47VFR/action/storage_attestation","attest_author":"https://pith.science/pith/A3G7GZEAUEWUJE3OMTQAQ47VFR/action/author_attestation","sign_citation":"https://pith.science/pith/A3G7GZEAUEWUJE3OMTQAQ47VFR/action/citation_signature","submit_replication":"https://pith.science/pith/A3G7GZEAUEWUJE3OMTQAQ47VFR/action/replication_record"}},"created_at":"2026-05-27T01:06:23.802323+00:00","updated_at":"2026-05-27T01:06:23.802323+00:00"}