{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PD7BSUL7IEX465NPZ4ZKNM6C4K","short_pith_number":"pith:PD7BSUL7","schema_version":"1.0","canonical_sha256":"78fe19517f412fcf75afcf32a6b3c2e2b585d327b0599f85a5705bbc816dcda9","source":{"kind":"arxiv","id":"2308.14085","version":1},"attestation_state":"computed","paper":{"title":"Sampling with flows, diffusion and autoregressive neural networks: A spin-glass perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.LG"],"primary_cat":"cond-mat.dis-nn","authors_text":"Davide Ghio, Florent Krzakala, Lenka Zdeborov\\'a, Yatin Dandi","submitted_at":"2023-08-27T12:16:33Z","abstract_excerpt":"Recent years witnessed the development of powerful generative models based on flows, diffusion or autoregressive neural networks, achieving remarkable success in generating data from examples with applications in a broad range of areas. A theoretical analysis of the performance and understanding of the limitations of these methods remain, however, challenging. In this paper, we undertake a step in this direction by analysing the efficiency of sampling by these methods on a class of problems with a known probability distribution and comparing it with the sampling performance of more traditional"},"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":"2308.14085","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2023-08-27T12:16:33Z","cross_cats_sorted":["cond-mat.stat-mech","cs.LG"],"title_canon_sha256":"e25f97c504baeb1c389aede19be1aee166d04aece829530632435d66b7e01e86","abstract_canon_sha256":"84485139a10dcea1dc5f85f85a7efa986659ea288282c6021f87320eb5a3f04c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:46.569592Z","signature_b64":"NvpNEbMiXApYttx5UlIsKPXjYYmikv30lDxfJWFiGpaQ/gpjUtqCFW/k7Qg19XZLZLXI55UswLTb6CLM2TAuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78fe19517f412fcf75afcf32a6b3c2e2b585d327b0599f85a5705bbc816dcda9","last_reissued_at":"2026-07-05T08:45:46.569204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:46.569204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sampling with flows, diffusion and autoregressive neural networks: A spin-glass perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.LG"],"primary_cat":"cond-mat.dis-nn","authors_text":"Davide Ghio, Florent Krzakala, Lenka Zdeborov\\'a, Yatin Dandi","submitted_at":"2023-08-27T12:16:33Z","abstract_excerpt":"Recent years witnessed the development of powerful generative models based on flows, diffusion or autoregressive neural networks, achieving remarkable success in generating data from examples with applications in a broad range of areas. A theoretical analysis of the performance and understanding of the limitations of these methods remain, however, challenging. In this paper, we undertake a step in this direction by analysing the efficiency of sampling by these methods on a class of problems with a known probability distribution and comparing it with the sampling performance of more traditional"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14085","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/2308.14085/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":"2308.14085","created_at":"2026-07-05T08:45:46.569263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.14085v1","created_at":"2026-07-05T08:45:46.569263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14085","created_at":"2026-07-05T08:45:46.569263+00:00"},{"alias_kind":"pith_short_12","alias_value":"PD7BSUL7IEX4","created_at":"2026-07-05T08:45:46.569263+00:00"},{"alias_kind":"pith_short_16","alias_value":"PD7BSUL7IEX465NP","created_at":"2026-07-05T08:45:46.569263+00:00"},{"alias_kind":"pith_short_8","alias_value":"PD7BSUL7","created_at":"2026-07-05T08:45:46.569263+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.12398","citing_title":"A Hierarchical Energy-Based Model for Multimodal Cognition","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PD7BSUL7IEX465NPZ4ZKNM6C4K","json":"https://pith.science/pith/PD7BSUL7IEX465NPZ4ZKNM6C4K.json","graph_json":"https://pith.science/api/pith-number/PD7BSUL7IEX465NPZ4ZKNM6C4K/graph.json","events_json":"https://pith.science/api/pith-number/PD7BSUL7IEX465NPZ4ZKNM6C4K/events.json","paper":"https://pith.science/paper/PD7BSUL7"},"agent_actions":{"view_html":"https://pith.science/pith/PD7BSUL7IEX465NPZ4ZKNM6C4K","download_json":"https://pith.science/pith/PD7BSUL7IEX465NPZ4ZKNM6C4K.json","view_paper":"https://pith.science/paper/PD7BSUL7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.14085&json=true","fetch_graph":"https://pith.science/api/pith-number/PD7BSUL7IEX465NPZ4ZKNM6C4K/graph.json","fetch_events":"https://pith.science/api/pith-number/PD7BSUL7IEX465NPZ4ZKNM6C4K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PD7BSUL7IEX465NPZ4ZKNM6C4K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PD7BSUL7IEX465NPZ4ZKNM6C4K/action/storage_attestation","attest_author":"https://pith.science/pith/PD7BSUL7IEX465NPZ4ZKNM6C4K/action/author_attestation","sign_citation":"https://pith.science/pith/PD7BSUL7IEX465NPZ4ZKNM6C4K/action/citation_signature","submit_replication":"https://pith.science/pith/PD7BSUL7IEX465NPZ4ZKNM6C4K/action/replication_record"}},"created_at":"2026-07-05T08:45:46.569263+00:00","updated_at":"2026-07-05T08:45:46.569263+00:00"}