{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I5G6U62DRWQX3IN5UTCM3ZXA6Q","short_pith_number":"pith:I5G6U62D","schema_version":"1.0","canonical_sha256":"474dea7b438da17da1bda4c4cde6e0f4247ae90e7b9a81c83596b896cf134a70","source":{"kind":"arxiv","id":"2403.01907","version":1},"attestation_state":"computed","paper":{"title":"Capacity of the Hebbian-Hopfield network associative memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.IT","cs.LG","math.IT","math.PR"],"primary_cat":"stat.ML","authors_text":"Mihailo Stojnic","submitted_at":"2024-03-04T10:10:23Z","abstract_excerpt":"In \\cite{Hop82}, Hopfield introduced a \\emph{Hebbian} learning rule based neural network model and suggested how it can efficiently operate as an associative memory. Studying random binary patterns, he also uncovered that, if a small fraction of errors is tolerated in the stored patterns retrieval, the capacity of the network (maximal number of memorized patterns, $m$) scales linearly with each pattern's size, $n$. Moreover, he famously predicted $\\alpha_c=\\lim_{n\\rightarrow\\infty}\\frac{m}{n}\\approx 0.14$. We study this very same scenario with two famous pattern's basins of attraction: \\textbf"},"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":"2403.01907","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-03-04T10:10:23Z","cross_cats_sorted":["cond-mat.dis-nn","cs.IT","cs.LG","math.IT","math.PR"],"title_canon_sha256":"eb97b904c64881a669de7df40476abc0fdf01edf430ec02bac5f510a7f04b22b","abstract_canon_sha256":"da4e9da8ac527d212afd122837dc2312c0f01702d8d7030de219cbe8f77c4c57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:53.876981Z","signature_b64":"TLInFk/5CnDnaHw6Wi4zlxvcxdyUAe2Ho+HRGWwHJSjen1Jdaxg7LWBb5Hkg4lA00TG1iAE746WtfrPhU2MbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"474dea7b438da17da1bda4c4cde6e0f4247ae90e7b9a81c83596b896cf134a70","last_reissued_at":"2026-07-05T07:51:53.876506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:53.876506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Capacity of the Hebbian-Hopfield network associative memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.IT","cs.LG","math.IT","math.PR"],"primary_cat":"stat.ML","authors_text":"Mihailo Stojnic","submitted_at":"2024-03-04T10:10:23Z","abstract_excerpt":"In \\cite{Hop82}, Hopfield introduced a \\emph{Hebbian} learning rule based neural network model and suggested how it can efficiently operate as an associative memory. Studying random binary patterns, he also uncovered that, if a small fraction of errors is tolerated in the stored patterns retrieval, the capacity of the network (maximal number of memorized patterns, $m$) scales linearly with each pattern's size, $n$. Moreover, he famously predicted $\\alpha_c=\\lim_{n\\rightarrow\\infty}\\frac{m}{n}\\approx 0.14$. We study this very same scenario with two famous pattern's basins of attraction: \\textbf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01907","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/2403.01907/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":"2403.01907","created_at":"2026-07-05T07:51:53.876567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.01907v1","created_at":"2026-07-05T07:51:53.876567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01907","created_at":"2026-07-05T07:51:53.876567+00:00"},{"alias_kind":"pith_short_12","alias_value":"I5G6U62DRWQX","created_at":"2026-07-05T07:51:53.876567+00:00"},{"alias_kind":"pith_short_16","alias_value":"I5G6U62DRWQX3IN5","created_at":"2026-07-05T07:51:53.876567+00:00"},{"alias_kind":"pith_short_8","alias_value":"I5G6U62D","created_at":"2026-07-05T07:51:53.876567+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22396","citing_title":"CLuP practically achieves $\\sim 1.77$ positive and $\\sim 0.33$ negative Hopfield model ground state free energy","ref_index":81,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I5G6U62DRWQX3IN5UTCM3ZXA6Q","json":"https://pith.science/pith/I5G6U62DRWQX3IN5UTCM3ZXA6Q.json","graph_json":"https://pith.science/api/pith-number/I5G6U62DRWQX3IN5UTCM3ZXA6Q/graph.json","events_json":"https://pith.science/api/pith-number/I5G6U62DRWQX3IN5UTCM3ZXA6Q/events.json","paper":"https://pith.science/paper/I5G6U62D"},"agent_actions":{"view_html":"https://pith.science/pith/I5G6U62DRWQX3IN5UTCM3ZXA6Q","download_json":"https://pith.science/pith/I5G6U62DRWQX3IN5UTCM3ZXA6Q.json","view_paper":"https://pith.science/paper/I5G6U62D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.01907&json=true","fetch_graph":"https://pith.science/api/pith-number/I5G6U62DRWQX3IN5UTCM3ZXA6Q/graph.json","fetch_events":"https://pith.science/api/pith-number/I5G6U62DRWQX3IN5UTCM3ZXA6Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I5G6U62DRWQX3IN5UTCM3ZXA6Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I5G6U62DRWQX3IN5UTCM3ZXA6Q/action/storage_attestation","attest_author":"https://pith.science/pith/I5G6U62DRWQX3IN5UTCM3ZXA6Q/action/author_attestation","sign_citation":"https://pith.science/pith/I5G6U62DRWQX3IN5UTCM3ZXA6Q/action/citation_signature","submit_replication":"https://pith.science/pith/I5G6U62DRWQX3IN5UTCM3ZXA6Q/action/replication_record"}},"created_at":"2026-07-05T07:51:53.876567+00:00","updated_at":"2026-07-05T07:51:53.876567+00:00"}