{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:B2RRAZMXBZRMHN2UHGOJ76T5EV","short_pith_number":"pith:B2RRAZMX","schema_version":"1.0","canonical_sha256":"0ea31065970e62c3b754399c9ffa7d25714160a0926fde64f9eb7f05fe428067","source":{"kind":"arxiv","id":"2212.03659","version":2},"attestation_state":"computed","paper":{"title":"Multi-Objective Linear Ensembles for Robust and Sparse Training of Few-Bit Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Ambrogio Maria Bernardelli, Hoong Chuin LAU, Neil Yorke-Smith, Simone Milanesi, Stefano Gualandi","submitted_at":"2022-12-07T14:23:43Z","abstract_excerpt":"Training neural networks (NNs) using combinatorial optimization solvers has gained attention in recent years. In low-data settings, state-of-the-art mixed integer linear programming solvers can train exactly a NN, avoiding intensive GPU-based training and hyper-parameter tuning and simultaneously training and sparsifying the network. We study the case of few-bit discrete-valued neural networks, both Binarized Neural Networks (BNNs), whose values are restricted to +-1, and Integer Neural Networks (INNs), whose values lie in a range {-P, ..., P}. Few-bit NNs receive increasing recognition due to"},"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":"2212.03659","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-12-07T14:23:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"517f4a9f6c48b5044aa2c70805fea08c7eaef1daba72adba255b9502111c59af","abstract_canon_sha256":"cafecaf94bf9ada79977de79535b5525bccf11d652aed299d779da49bd8de9f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:29.713124Z","signature_b64":"f/o8+ZFySXpHokT26umKfCPOSbTfML290M+ALwKh/RTAtEru8HJ/UVapAj2Co46jHGsFrfnmQX65bqzGWUjdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ea31065970e62c3b754399c9ffa7d25714160a0926fde64f9eb7f05fe428067","last_reissued_at":"2026-07-05T09:05:29.712614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:29.712614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Objective Linear Ensembles for Robust and Sparse Training of Few-Bit Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Ambrogio Maria Bernardelli, Hoong Chuin LAU, Neil Yorke-Smith, Simone Milanesi, Stefano Gualandi","submitted_at":"2022-12-07T14:23:43Z","abstract_excerpt":"Training neural networks (NNs) using combinatorial optimization solvers has gained attention in recent years. In low-data settings, state-of-the-art mixed integer linear programming solvers can train exactly a NN, avoiding intensive GPU-based training and hyper-parameter tuning and simultaneously training and sparsifying the network. We study the case of few-bit discrete-valued neural networks, both Binarized Neural Networks (BNNs), whose values are restricted to +-1, and Integer Neural Networks (INNs), whose values lie in a range {-P, ..., P}. Few-bit NNs receive increasing recognition due to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.03659","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/2212.03659/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":"2212.03659","created_at":"2026-07-05T09:05:29.712674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.03659v2","created_at":"2026-07-05T09:05:29.712674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.03659","created_at":"2026-07-05T09:05:29.712674+00:00"},{"alias_kind":"pith_short_12","alias_value":"B2RRAZMXBZRM","created_at":"2026-07-05T09:05:29.712674+00:00"},{"alias_kind":"pith_short_16","alias_value":"B2RRAZMXBZRMHN2U","created_at":"2026-07-05T09:05:29.712674+00:00"},{"alias_kind":"pith_short_8","alias_value":"B2RRAZMX","created_at":"2026-07-05T09:05:29.712674+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/B2RRAZMXBZRMHN2UHGOJ76T5EV","json":"https://pith.science/pith/B2RRAZMXBZRMHN2UHGOJ76T5EV.json","graph_json":"https://pith.science/api/pith-number/B2RRAZMXBZRMHN2UHGOJ76T5EV/graph.json","events_json":"https://pith.science/api/pith-number/B2RRAZMXBZRMHN2UHGOJ76T5EV/events.json","paper":"https://pith.science/paper/B2RRAZMX"},"agent_actions":{"view_html":"https://pith.science/pith/B2RRAZMXBZRMHN2UHGOJ76T5EV","download_json":"https://pith.science/pith/B2RRAZMXBZRMHN2UHGOJ76T5EV.json","view_paper":"https://pith.science/paper/B2RRAZMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.03659&json=true","fetch_graph":"https://pith.science/api/pith-number/B2RRAZMXBZRMHN2UHGOJ76T5EV/graph.json","fetch_events":"https://pith.science/api/pith-number/B2RRAZMXBZRMHN2UHGOJ76T5EV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B2RRAZMXBZRMHN2UHGOJ76T5EV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B2RRAZMXBZRMHN2UHGOJ76T5EV/action/storage_attestation","attest_author":"https://pith.science/pith/B2RRAZMXBZRMHN2UHGOJ76T5EV/action/author_attestation","sign_citation":"https://pith.science/pith/B2RRAZMXBZRMHN2UHGOJ76T5EV/action/citation_signature","submit_replication":"https://pith.science/pith/B2RRAZMXBZRMHN2UHGOJ76T5EV/action/replication_record"}},"created_at":"2026-07-05T09:05:29.712674+00:00","updated_at":"2026-07-05T09:05:29.712674+00:00"}