{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5UVYJGGIZSPPMRBNSZ4CNCITAK","short_pith_number":"pith:5UVYJGGI","schema_version":"1.0","canonical_sha256":"ed2b8498c8cc9ef6442d967826891302b494e163360a51694ab19665f9fa9eee","source":{"kind":"arxiv","id":"2309.17290","version":2},"attestation_state":"computed","paper":{"title":"In search of dispersed memories: Generative diffusion models are associative memory networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Luca Ambrogioni","submitted_at":"2023-09-29T14:48:24Z","abstract_excerpt":"Uncovering the mechanisms behind long-term memory is one of the most fascinating open problems in neuroscience and artificial intelligence. Artificial associative memory networks have been used to formalize important aspects of biological memory. Generative diffusion models are a type of generative machine learning techniques that have shown great performance in many tasks. Like associative memory systems, these networks define a dynamical system that converges to a set of target states. In this work we show that generative diffusion models can be interpreted as energy-based models and that, w"},"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":"2309.17290","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-09-29T14:48:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b690b85ba84e87fb5df2cca421be225f3ea586b8498865e6f7bea453ff54b68e","abstract_canon_sha256":"23e2ef1bc9ddd276b6a549b5039bbaf42f104276fea8bb18fb75adc3a2e97ebf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:44.924078Z","signature_b64":"I87lfSS0nUGuiHe7ZOGhdGyPHCuyHhsfp93vUdsal9vFST0xlpCu5A+DdYXTDabiCeDMXKRQQ/O/U1tf+VWtAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed2b8498c8cc9ef6442d967826891302b494e163360a51694ab19665f9fa9eee","last_reissued_at":"2026-07-05T07:13:44.923610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:44.923610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In search of dispersed memories: Generative diffusion models are associative memory networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Luca Ambrogioni","submitted_at":"2023-09-29T14:48:24Z","abstract_excerpt":"Uncovering the mechanisms behind long-term memory is one of the most fascinating open problems in neuroscience and artificial intelligence. Artificial associative memory networks have been used to formalize important aspects of biological memory. Generative diffusion models are a type of generative machine learning techniques that have shown great performance in many tasks. Like associative memory systems, these networks define a dynamical system that converges to a set of target states. In this work we show that generative diffusion models can be interpreted as energy-based models and that, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.17290","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/2309.17290/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":"2309.17290","created_at":"2026-07-05T07:13:44.923670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.17290v2","created_at":"2026-07-05T07:13:44.923670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17290","created_at":"2026-07-05T07:13:44.923670+00:00"},{"alias_kind":"pith_short_12","alias_value":"5UVYJGGIZSPP","created_at":"2026-07-05T07:13:44.923670+00:00"},{"alias_kind":"pith_short_16","alias_value":"5UVYJGGIZSPPMRBN","created_at":"2026-07-05T07:13:44.923670+00:00"},{"alias_kind":"pith_short_8","alias_value":"5UVYJGGI","created_at":"2026-07-05T07:13:44.923670+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.20292","citing_title":"An analytic theory of creativity in convolutional diffusion models","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5UVYJGGIZSPPMRBNSZ4CNCITAK","json":"https://pith.science/pith/5UVYJGGIZSPPMRBNSZ4CNCITAK.json","graph_json":"https://pith.science/api/pith-number/5UVYJGGIZSPPMRBNSZ4CNCITAK/graph.json","events_json":"https://pith.science/api/pith-number/5UVYJGGIZSPPMRBNSZ4CNCITAK/events.json","paper":"https://pith.science/paper/5UVYJGGI"},"agent_actions":{"view_html":"https://pith.science/pith/5UVYJGGIZSPPMRBNSZ4CNCITAK","download_json":"https://pith.science/pith/5UVYJGGIZSPPMRBNSZ4CNCITAK.json","view_paper":"https://pith.science/paper/5UVYJGGI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.17290&json=true","fetch_graph":"https://pith.science/api/pith-number/5UVYJGGIZSPPMRBNSZ4CNCITAK/graph.json","fetch_events":"https://pith.science/api/pith-number/5UVYJGGIZSPPMRBNSZ4CNCITAK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5UVYJGGIZSPPMRBNSZ4CNCITAK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5UVYJGGIZSPPMRBNSZ4CNCITAK/action/storage_attestation","attest_author":"https://pith.science/pith/5UVYJGGIZSPPMRBNSZ4CNCITAK/action/author_attestation","sign_citation":"https://pith.science/pith/5UVYJGGIZSPPMRBNSZ4CNCITAK/action/citation_signature","submit_replication":"https://pith.science/pith/5UVYJGGIZSPPMRBNSZ4CNCITAK/action/replication_record"}},"created_at":"2026-07-05T07:13:44.923670+00:00","updated_at":"2026-07-05T07:13:44.923670+00:00"}