{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PBQOYM6NPEUPNNLYDUYK6I7UTI","short_pith_number":"pith:PBQOYM6N","schema_version":"1.0","canonical_sha256":"7860ec33cd7928f6b5781d30af23f49a39002457f8610db28aef3493db01747a","source":{"kind":"arxiv","id":"2309.16750","version":2},"attestation_state":"computed","paper":{"title":"Memory in Plain Sight: Surveying the Uncanny Resemblances of Associative Memories and Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.DS"],"primary_cat":"cs.LG","authors_text":"Benjamin Hoover, Dmitry Krotov, Duen Horng Chau, Hendrik Strobelt, Judy Hoffman, Zsolt Kira","submitted_at":"2023-09-28T17:57:09Z","abstract_excerpt":"The generative process of Diffusion Models (DMs) has recently set state-of-the-art on many AI generation benchmarks. Though the generative process is traditionally understood as an \"iterative denoiser\", there is no universally accepted language to describe it. We introduce a novel perspective to describe DMs using the mathematical language of memory retrieval from the field of energy-based Associative Memories (AMs), making efforts to keep our presentation approachable to newcomers to both of these fields. Unifying these two fields provides insight that DMs can be seen as a particular kind of "},"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":"2309.16750","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-28T17:57:09Z","cross_cats_sorted":["cs.AI","math.DS"],"title_canon_sha256":"f800317919fe8fada05a32ac0eea6aaf9a6608bd8fbef92ffbb3305fde4d8e23","abstract_canon_sha256":"0d75f6aaf5dbd3ddddbe2080ef023c0b5e8941624362965769b164d62d961dd8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:55.924100Z","signature_b64":"q3Hw0xgvycouY/wa8V4pvkwpuzqx1awTOoFH+5JvvweJEcSCd5Ci2mxI3BQl5nKBKc0tRz6BmTAd73CH3ssLAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7860ec33cd7928f6b5781d30af23f49a39002457f8610db28aef3493db01747a","last_reissued_at":"2026-07-05T08:23:55.923620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:55.923620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory in Plain Sight: Surveying the Uncanny Resemblances of Associative Memories and Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.DS"],"primary_cat":"cs.LG","authors_text":"Benjamin Hoover, Dmitry Krotov, Duen Horng Chau, Hendrik Strobelt, Judy Hoffman, Zsolt Kira","submitted_at":"2023-09-28T17:57:09Z","abstract_excerpt":"The generative process of Diffusion Models (DMs) has recently set state-of-the-art on many AI generation benchmarks. Though the generative process is traditionally understood as an \"iterative denoiser\", there is no universally accepted language to describe it. We introduce a novel perspective to describe DMs using the mathematical language of memory retrieval from the field of energy-based Associative Memories (AMs), making efforts to keep our presentation approachable to newcomers to both of these fields. Unifying these two fields provides insight that DMs can be seen as a particular kind of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16750","kind":"arxiv","version":2},"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/2309.16750/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":"2309.16750","created_at":"2026-07-05T08:23:55.923680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.16750v2","created_at":"2026-07-05T08:23:55.923680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16750","created_at":"2026-07-05T08:23:55.923680+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBQOYM6NPEUP","created_at":"2026-07-05T08:23:55.923680+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBQOYM6NPEUPNNLY","created_at":"2026-07-05T08:23:55.923680+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBQOYM6N","created_at":"2026-07-05T08:23:55.923680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01645","citing_title":"Self-Regulating Annealing in Heavy-Tailed Diffusion Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31110","citing_title":"Explaining Machine Learning and Memorization with Statistical Mechanics","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00248","citing_title":"Geodesic Flow Matching for Denoising High-Dimensional Structured Representations","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2601.01253","citing_title":"Stochastic Thermodynamics of Associative Memory","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26841","citing_title":"Language Diffusion Models are Associative Memories Capable of Retrieving Unseen Data","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PBQOYM6NPEUPNNLYDUYK6I7UTI","json":"https://pith.science/pith/PBQOYM6NPEUPNNLYDUYK6I7UTI.json","graph_json":"https://pith.science/api/pith-number/PBQOYM6NPEUPNNLYDUYK6I7UTI/graph.json","events_json":"https://pith.science/api/pith-number/PBQOYM6NPEUPNNLYDUYK6I7UTI/events.json","paper":"https://pith.science/paper/PBQOYM6N"},"agent_actions":{"view_html":"https://pith.science/pith/PBQOYM6NPEUPNNLYDUYK6I7UTI","download_json":"https://pith.science/pith/PBQOYM6NPEUPNNLYDUYK6I7UTI.json","view_paper":"https://pith.science/paper/PBQOYM6N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.16750&json=true","fetch_graph":"https://pith.science/api/pith-number/PBQOYM6NPEUPNNLYDUYK6I7UTI/graph.json","fetch_events":"https://pith.science/api/pith-number/PBQOYM6NPEUPNNLYDUYK6I7UTI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBQOYM6NPEUPNNLYDUYK6I7UTI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBQOYM6NPEUPNNLYDUYK6I7UTI/action/storage_attestation","attest_author":"https://pith.science/pith/PBQOYM6NPEUPNNLYDUYK6I7UTI/action/author_attestation","sign_citation":"https://pith.science/pith/PBQOYM6NPEUPNNLYDUYK6I7UTI/action/citation_signature","submit_replication":"https://pith.science/pith/PBQOYM6NPEUPNNLYDUYK6I7UTI/action/replication_record"}},"created_at":"2026-07-05T08:23:55.923680+00:00","updated_at":"2026-07-05T08:23:55.923680+00:00"}