{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AVTG7A76GD3AQ2FFI3RFUI6SQL","short_pith_number":"pith:AVTG7A76","schema_version":"1.0","canonical_sha256":"05666f83fe30f60868a546e25a23d282f0d7eb4ecac10972aecb8c018099b193","source":{"kind":"arxiv","id":"1904.06194","version":2},"attestation_state":"computed","paper":{"title":"Compressing deep neural networks by matrix product operators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","physics.comp-ph","quant-ph"],"primary_cat":"cs.LG","authors_text":"Hui-Hai Zhao, Rong-Qiang He, Song Cheng, Tao Xiang, Ze-Feng Gao, Zhong-Yi Lu, Z. Y. Xie","submitted_at":"2019-04-11T17:59:00Z","abstract_excerpt":"A deep neural network is a parametrization of a multilayer mapping of signals in terms of many alternatively arranged linear and nonlinear transformations. The linear transformations, which are generally used in the fully connected as well as convolutional layers, contain most of the variational parameters that are trained and stored. Compressing a deep neural network to reduce its number of variational parameters but not its prediction power is an important but challenging problem toward the establishment of an optimized scheme in training efficiently these parameters and in lowering the risk"},"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":"1904.06194","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-11T17:59:00Z","cross_cats_sorted":["cs.CV","cs.NE","physics.comp-ph","quant-ph"],"title_canon_sha256":"fe1b182a9af43cbed07313fdde21340408fa92aa4a77cae761af67e0df45dc35","abstract_canon_sha256":"8ab46c6caf2bc73a23944a704f2e06873aed56a594bb6a6f7aded3579203e626"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:15:04.980438Z","signature_b64":"fb+YX6FRj2lI9L0iEsoQ0PnRNDylIbuKbBGs8VrxQ0GJHVoWx4ww/EvTdnfECdLFzYtfEKR+h+cAWxTFUKjpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05666f83fe30f60868a546e25a23d282f0d7eb4ecac10972aecb8c018099b193","last_reissued_at":"2026-07-05T01:15:04.979872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:15:04.979872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compressing deep neural networks by matrix product operators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","physics.comp-ph","quant-ph"],"primary_cat":"cs.LG","authors_text":"Hui-Hai Zhao, Rong-Qiang He, Song Cheng, Tao Xiang, Ze-Feng Gao, Zhong-Yi Lu, Z. Y. Xie","submitted_at":"2019-04-11T17:59:00Z","abstract_excerpt":"A deep neural network is a parametrization of a multilayer mapping of signals in terms of many alternatively arranged linear and nonlinear transformations. The linear transformations, which are generally used in the fully connected as well as convolutional layers, contain most of the variational parameters that are trained and stored. Compressing a deep neural network to reduce its number of variational parameters but not its prediction power is an important but challenging problem toward the establishment of an optimized scheme in training efficiently these parameters and in lowering the risk"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06194","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/1904.06194/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":"1904.06194","created_at":"2026-07-05T01:15:04.979929+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.06194v2","created_at":"2026-07-05T01:15:04.979929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06194","created_at":"2026-07-05T01:15:04.979929+00:00"},{"alias_kind":"pith_short_12","alias_value":"AVTG7A76GD3A","created_at":"2026-07-05T01:15:04.979929+00:00"},{"alias_kind":"pith_short_16","alias_value":"AVTG7A76GD3AQ2FF","created_at":"2026-07-05T01:15:04.979929+00:00"},{"alias_kind":"pith_short_8","alias_value":"AVTG7A76","created_at":"2026-07-05T01:15:04.979929+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/AVTG7A76GD3AQ2FFI3RFUI6SQL","json":"https://pith.science/pith/AVTG7A76GD3AQ2FFI3RFUI6SQL.json","graph_json":"https://pith.science/api/pith-number/AVTG7A76GD3AQ2FFI3RFUI6SQL/graph.json","events_json":"https://pith.science/api/pith-number/AVTG7A76GD3AQ2FFI3RFUI6SQL/events.json","paper":"https://pith.science/paper/AVTG7A76"},"agent_actions":{"view_html":"https://pith.science/pith/AVTG7A76GD3AQ2FFI3RFUI6SQL","download_json":"https://pith.science/pith/AVTG7A76GD3AQ2FFI3RFUI6SQL.json","view_paper":"https://pith.science/paper/AVTG7A76","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.06194&json=true","fetch_graph":"https://pith.science/api/pith-number/AVTG7A76GD3AQ2FFI3RFUI6SQL/graph.json","fetch_events":"https://pith.science/api/pith-number/AVTG7A76GD3AQ2FFI3RFUI6SQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AVTG7A76GD3AQ2FFI3RFUI6SQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AVTG7A76GD3AQ2FFI3RFUI6SQL/action/storage_attestation","attest_author":"https://pith.science/pith/AVTG7A76GD3AQ2FFI3RFUI6SQL/action/author_attestation","sign_citation":"https://pith.science/pith/AVTG7A76GD3AQ2FFI3RFUI6SQL/action/citation_signature","submit_replication":"https://pith.science/pith/AVTG7A76GD3AQ2FFI3RFUI6SQL/action/replication_record"}},"created_at":"2026-07-05T01:15:04.979929+00:00","updated_at":"2026-07-05T01:15:04.979929+00:00"}