{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NV6ABYI5P6OSTMA4CNXUGDFZTL","short_pith_number":"pith:NV6ABYI5","schema_version":"1.0","canonical_sha256":"6d7c00e11d7f9d29b01c136f430cb99ae8757d7554b99331c192f7bf40d7faa0","source":{"kind":"arxiv","id":"1710.09825","version":2},"attestation_state":"computed","paper":{"title":"On the role of synaptic stochasticity in training low-precision neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cond-mat.dis-nn","authors_text":"Carlo Baldassi, Carlo Lucibello, Enzo Tartaglione, Federica Gerace, Hilbert J. Kappen, Luca Saglietti, Riccardo Zecchina","submitted_at":"2017-10-26T17:42:23Z","abstract_excerpt":"Stochasticity and limited precision of synaptic weights in neural network models are key aspects of both biological and hardware modeling of learning processes. Here we show that a neural network model with stochastic binary weights naturally gives prominence to exponentially rare dense regions of solutions with a number of desirable properties such as robustness and good generalization performance, while typical solutions are isolated and hard to find. Binary solutions of the standard perceptron problem are obtained from a simple gradient descent procedure on a set of real values parametrizin"},"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":"1710.09825","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2017-10-26T17:42:23Z","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"9069dbe67e8591d8373ac3ff38bb3991d3167fa33bc0499b097a58270e55b4c7","abstract_canon_sha256":"13218faf63b35015ecb262bb0d98868a4d5eb9c159f5c02b07d88593ef6aae82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:40.354824Z","signature_b64":"EE8NHcHBLH6f3vLP2tQiy1yaXejEbhqKppS3a9gbaJK91VKyIWr4H2n0svkMi9PRID9TEB/L3GG0v6BqZdqWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d7c00e11d7f9d29b01c136f430cb99ae8757d7554b99331c192f7bf40d7faa0","last_reissued_at":"2026-05-18T00:11:40.353951Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:40.353951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the role of synaptic stochasticity in training low-precision neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cond-mat.dis-nn","authors_text":"Carlo Baldassi, Carlo Lucibello, Enzo Tartaglione, Federica Gerace, Hilbert J. Kappen, Luca Saglietti, Riccardo Zecchina","submitted_at":"2017-10-26T17:42:23Z","abstract_excerpt":"Stochasticity and limited precision of synaptic weights in neural network models are key aspects of both biological and hardware modeling of learning processes. Here we show that a neural network model with stochastic binary weights naturally gives prominence to exponentially rare dense regions of solutions with a number of desirable properties such as robustness and good generalization performance, while typical solutions are isolated and hard to find. Binary solutions of the standard perceptron problem are obtained from a simple gradient descent procedure on a set of real values parametrizin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.09825","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":""},"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":"1710.09825","created_at":"2026-05-18T00:11:40.354100+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.09825v2","created_at":"2026-05-18T00:11:40.354100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.09825","created_at":"2026-05-18T00:11:40.354100+00:00"},{"alias_kind":"pith_short_12","alias_value":"NV6ABYI5P6OS","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"NV6ABYI5P6OSTMA4","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"NV6ABYI5","created_at":"2026-05-18T12:31:34.259226+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/NV6ABYI5P6OSTMA4CNXUGDFZTL","json":"https://pith.science/pith/NV6ABYI5P6OSTMA4CNXUGDFZTL.json","graph_json":"https://pith.science/api/pith-number/NV6ABYI5P6OSTMA4CNXUGDFZTL/graph.json","events_json":"https://pith.science/api/pith-number/NV6ABYI5P6OSTMA4CNXUGDFZTL/events.json","paper":"https://pith.science/paper/NV6ABYI5"},"agent_actions":{"view_html":"https://pith.science/pith/NV6ABYI5P6OSTMA4CNXUGDFZTL","download_json":"https://pith.science/pith/NV6ABYI5P6OSTMA4CNXUGDFZTL.json","view_paper":"https://pith.science/paper/NV6ABYI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.09825&json=true","fetch_graph":"https://pith.science/api/pith-number/NV6ABYI5P6OSTMA4CNXUGDFZTL/graph.json","fetch_events":"https://pith.science/api/pith-number/NV6ABYI5P6OSTMA4CNXUGDFZTL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NV6ABYI5P6OSTMA4CNXUGDFZTL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NV6ABYI5P6OSTMA4CNXUGDFZTL/action/storage_attestation","attest_author":"https://pith.science/pith/NV6ABYI5P6OSTMA4CNXUGDFZTL/action/author_attestation","sign_citation":"https://pith.science/pith/NV6ABYI5P6OSTMA4CNXUGDFZTL/action/citation_signature","submit_replication":"https://pith.science/pith/NV6ABYI5P6OSTMA4CNXUGDFZTL/action/replication_record"}},"created_at":"2026-05-18T00:11:40.354100+00:00","updated_at":"2026-05-18T00:11:40.354100+00:00"}