{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WEZBJ6KBYUWIRTC7D2H3A4GBAD","short_pith_number":"pith:WEZBJ6KB","schema_version":"1.0","canonical_sha256":"b13214f941c52c88cc5f1e8fb070c100fc175cb5393428184ee1a5296b5b51b6","source":{"kind":"arxiv","id":"2301.08292","version":2},"attestation_state":"computed","paper":{"title":"Quantum HyperNetworks: Training Binary Neural Networks in Quantum Superposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"quant-ph","authors_text":"Alireza Makhzani, Estelle Inack, Giacomo Torlai, Graham W. Taylor, Juan Carrasquilla, Kirill Neklyudov, Mohamed Hibat-Allah","submitted_at":"2023-01-19T20:06:48Z","abstract_excerpt":"Binary neural networks, i.e., neural networks whose parameters and activations are constrained to only two possible values, offer a compelling avenue for the deployment of deep learning models on energy- and memory-limited devices. However, their training, architectural design, and hyperparameter tuning remain challenging as these involve multiple computationally expensive combinatorial optimization problems. Here we introduce quantum hypernetworks as a mechanism to train binary neural networks on quantum computers, which unify the search over parameters, hyperparameters, and architectures in "},"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":"2301.08292","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2023-01-19T20:06:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"87404790d51a6f1a2eedca32d84a1d999db07d1efc983aa68b4d91852f7a5f79","abstract_canon_sha256":"0c92b2a522428945f93e1eb5fa56c32c4b1948b09edf900dd39f2a1996ef04dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:21.253917Z","signature_b64":"6KB8BfNT241/zSsIKZ0NEK2cXO2QcNxWiZpNdh9EO54tS1lQNpFT1uh/hIjoBeLAiSceyFRN+Z6d0FaUoO4QDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b13214f941c52c88cc5f1e8fb070c100fc175cb5393428184ee1a5296b5b51b6","last_reissued_at":"2026-07-05T11:38:21.253363Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:21.253363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantum HyperNetworks: Training Binary Neural Networks in Quantum Superposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"quant-ph","authors_text":"Alireza Makhzani, Estelle Inack, Giacomo Torlai, Graham W. Taylor, Juan Carrasquilla, Kirill Neklyudov, Mohamed Hibat-Allah","submitted_at":"2023-01-19T20:06:48Z","abstract_excerpt":"Binary neural networks, i.e., neural networks whose parameters and activations are constrained to only two possible values, offer a compelling avenue for the deployment of deep learning models on energy- and memory-limited devices. However, their training, architectural design, and hyperparameter tuning remain challenging as these involve multiple computationally expensive combinatorial optimization problems. Here we introduce quantum hypernetworks as a mechanism to train binary neural networks on quantum computers, which unify the search over parameters, hyperparameters, and architectures in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.08292","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/2301.08292/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":"2301.08292","created_at":"2026-07-05T11:38:21.253435+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.08292v2","created_at":"2026-07-05T11:38:21.253435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.08292","created_at":"2026-07-05T11:38:21.253435+00:00"},{"alias_kind":"pith_short_12","alias_value":"WEZBJ6KBYUWI","created_at":"2026-07-05T11:38:21.253435+00:00"},{"alias_kind":"pith_short_16","alias_value":"WEZBJ6KBYUWIRTC7","created_at":"2026-07-05T11:38:21.253435+00:00"},{"alias_kind":"pith_short_8","alias_value":"WEZBJ6KB","created_at":"2026-07-05T11:38:21.253435+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00987","citing_title":"Quantum Information Processing, Sensing and Communications: Their Myths, Realities and Futures","ref_index":234,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WEZBJ6KBYUWIRTC7D2H3A4GBAD","json":"https://pith.science/pith/WEZBJ6KBYUWIRTC7D2H3A4GBAD.json","graph_json":"https://pith.science/api/pith-number/WEZBJ6KBYUWIRTC7D2H3A4GBAD/graph.json","events_json":"https://pith.science/api/pith-number/WEZBJ6KBYUWIRTC7D2H3A4GBAD/events.json","paper":"https://pith.science/paper/WEZBJ6KB"},"agent_actions":{"view_html":"https://pith.science/pith/WEZBJ6KBYUWIRTC7D2H3A4GBAD","download_json":"https://pith.science/pith/WEZBJ6KBYUWIRTC7D2H3A4GBAD.json","view_paper":"https://pith.science/paper/WEZBJ6KB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.08292&json=true","fetch_graph":"https://pith.science/api/pith-number/WEZBJ6KBYUWIRTC7D2H3A4GBAD/graph.json","fetch_events":"https://pith.science/api/pith-number/WEZBJ6KBYUWIRTC7D2H3A4GBAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WEZBJ6KBYUWIRTC7D2H3A4GBAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WEZBJ6KBYUWIRTC7D2H3A4GBAD/action/storage_attestation","attest_author":"https://pith.science/pith/WEZBJ6KBYUWIRTC7D2H3A4GBAD/action/author_attestation","sign_citation":"https://pith.science/pith/WEZBJ6KBYUWIRTC7D2H3A4GBAD/action/citation_signature","submit_replication":"https://pith.science/pith/WEZBJ6KBYUWIRTC7D2H3A4GBAD/action/replication_record"}},"created_at":"2026-07-05T11:38:21.253435+00:00","updated_at":"2026-07-05T11:38:21.253435+00:00"}