{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XAZ3N4GZD46SCQ67M7TDWD7JY5","short_pith_number":"pith:XAZ3N4GZ","schema_version":"1.0","canonical_sha256":"b833b6f0d91f3d2143df67e63b0fe9c74fade2b4b925d62da8799903e8398293","source":{"kind":"arxiv","id":"2607.29554","version":1},"attestation_state":"computed","paper":{"title":"Exponential Capacity in Multilayer Hetero-Associative Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cond-mat.dis-nn","authors_text":"Adriano Barra, Andrea Ladiana, Andrea Lepre, Elena Agliari","submitted_at":"2026-07-31T15:46:21Z","abstract_excerpt":"Exponential Hopfield networks store a number of patterns that grows exponentially with the number of neurons, and in their classical formulation they are auto-associative: they complete a corrupted copy of a memory into the memory itself. Many of the tasks one wants such a network to perform are instead hetero-associative, mapping a cue to a different target. We introduce and analyse an exponential neural network of $L$ layers of $N$ binary neurons, each layer carrying its own dataset, whose energy is an exponential of the product of the per-layer Mattis overlaps, so that it is minimised preci"},"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":"2607.29554","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2026-07-31T15:46:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4d1c394c63c2a1b0c09f2ded79b12211c99f5d24389c80a9335f0aa4c2c1bbff","abstract_canon_sha256":"08570562f6989a8589c6b79bc06b5e92c1b653c2278d3a2f914a133c73c695cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:38:23.738160Z","signature_b64":"lAdW5CP+ZvjHsjDO0ZBWTnFJtGDFjEo/OxetTPWT+43AH3xG9wtOtidXAMhA8MZm3r+pXnEhPNtzY9mLOlm+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b833b6f0d91f3d2143df67e63b0fe9c74fade2b4b925d62da8799903e8398293","last_reissued_at":"2026-08-03T01:38:23.736480Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:38:23.736480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exponential Capacity in Multilayer Hetero-Associative Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cond-mat.dis-nn","authors_text":"Adriano Barra, Andrea Ladiana, Andrea Lepre, Elena Agliari","submitted_at":"2026-07-31T15:46:21Z","abstract_excerpt":"Exponential Hopfield networks store a number of patterns that grows exponentially with the number of neurons, and in their classical formulation they are auto-associative: they complete a corrupted copy of a memory into the memory itself. Many of the tasks one wants such a network to perform are instead hetero-associative, mapping a cue to a different target. We introduce and analyse an exponential neural network of $L$ layers of $N$ binary neurons, each layer carrying its own dataset, whose energy is an exponential of the product of the per-layer Mattis overlaps, so that it is minimised preci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29554","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/2607.29554/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":"2607.29554","created_at":"2026-08-03T01:38:23.737374+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.29554v1","created_at":"2026-08-03T01:38:23.737374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29554","created_at":"2026-08-03T01:38:23.737374+00:00"},{"alias_kind":"pith_short_12","alias_value":"XAZ3N4GZD46S","created_at":"2026-08-03T01:38:23.737374+00:00"},{"alias_kind":"pith_short_16","alias_value":"XAZ3N4GZD46SCQ67","created_at":"2026-08-03T01:38:23.737374+00:00"},{"alias_kind":"pith_short_8","alias_value":"XAZ3N4GZ","created_at":"2026-08-03T01:38:23.737374+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/XAZ3N4GZD46SCQ67M7TDWD7JY5","json":"https://pith.science/pith/XAZ3N4GZD46SCQ67M7TDWD7JY5.json","graph_json":"https://pith.science/api/pith-number/XAZ3N4GZD46SCQ67M7TDWD7JY5/graph.json","events_json":"https://pith.science/api/pith-number/XAZ3N4GZD46SCQ67M7TDWD7JY5/events.json","paper":"https://pith.science/paper/XAZ3N4GZ"},"agent_actions":{"view_html":"https://pith.science/pith/XAZ3N4GZD46SCQ67M7TDWD7JY5","download_json":"https://pith.science/pith/XAZ3N4GZD46SCQ67M7TDWD7JY5.json","view_paper":"https://pith.science/paper/XAZ3N4GZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.29554&json=true","fetch_graph":"https://pith.science/api/pith-number/XAZ3N4GZD46SCQ67M7TDWD7JY5/graph.json","fetch_events":"https://pith.science/api/pith-number/XAZ3N4GZD46SCQ67M7TDWD7JY5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XAZ3N4GZD46SCQ67M7TDWD7JY5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XAZ3N4GZD46SCQ67M7TDWD7JY5/action/storage_attestation","attest_author":"https://pith.science/pith/XAZ3N4GZD46SCQ67M7TDWD7JY5/action/author_attestation","sign_citation":"https://pith.science/pith/XAZ3N4GZD46SCQ67M7TDWD7JY5/action/citation_signature","submit_replication":"https://pith.science/pith/XAZ3N4GZD46SCQ67M7TDWD7JY5/action/replication_record"}},"created_at":"2026-08-03T01:38:23.737374+00:00","updated_at":"2026-08-03T01:38:23.737374+00:00"}