{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FS7NOJXQHDAKYEBJHQ27L4BVHS","short_pith_number":"pith:FS7NOJXQ","schema_version":"1.0","canonical_sha256":"2cbed726f038c0ac10293c35f5f0353cb7bf028a09e7d901440707bf24f20c64","source":{"kind":"arxiv","id":"2306.09293","version":2},"attestation_state":"computed","paper":{"title":"[Experiments & Analysis] Evaluating the Feasibility of Sampling-Based Techniques for Training Multilayer Perceptrons","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abolfazl Asudeh, Rishi Advani, Sana Ebrahimi","submitted_at":"2023-06-15T17:19:48Z","abstract_excerpt":"The training process of neural networks is known to be time-consuming, and having a deep architecture only aggravates the issue. This process consists mostly of matrix operations, among which matrix multiplication is the bottleneck. Several sampling-based techniques have been proposed for speeding up the training time of deep neural networks by approximating the matrix products. These techniques fall under two categories: (i) sampling a subset of nodes in every hidden layer as active at every iteration and (ii) sampling a subset of nodes from the previous layer to approximate the current layer"},"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":"2306.09293","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T17:19:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f5cd9c328dd331730b1687c22d152550f6be84ebffc04d8d207e6122aedf0e75","abstract_canon_sha256":"31529b1dbc8d50f88219b1839638003548098aa17434ef833ba5862f05e7de86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:29.455074Z","signature_b64":"7eMR25sbl1tIYqe06drO/IhrzMHbsXwIqcatQCgrNXTY057sjFQLMhvJwIzooTJIz0AUNm3pxlwkPaf2qJ3oCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cbed726f038c0ac10293c35f5f0353cb7bf028a09e7d901440707bf24f20c64","last_reissued_at":"2026-07-05T11:21:29.454590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:29.454590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"[Experiments & Analysis] Evaluating the Feasibility of Sampling-Based Techniques for Training Multilayer Perceptrons","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abolfazl Asudeh, Rishi Advani, Sana Ebrahimi","submitted_at":"2023-06-15T17:19:48Z","abstract_excerpt":"The training process of neural networks is known to be time-consuming, and having a deep architecture only aggravates the issue. This process consists mostly of matrix operations, among which matrix multiplication is the bottleneck. Several sampling-based techniques have been proposed for speeding up the training time of deep neural networks by approximating the matrix products. These techniques fall under two categories: (i) sampling a subset of nodes in every hidden layer as active at every iteration and (ii) sampling a subset of nodes from the previous layer to approximate the current layer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09293","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/2306.09293/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":"2306.09293","created_at":"2026-07-05T11:21:29.454647+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.09293v2","created_at":"2026-07-05T11:21:29.454647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09293","created_at":"2026-07-05T11:21:29.454647+00:00"},{"alias_kind":"pith_short_12","alias_value":"FS7NOJXQHDAK","created_at":"2026-07-05T11:21:29.454647+00:00"},{"alias_kind":"pith_short_16","alias_value":"FS7NOJXQHDAKYEBJ","created_at":"2026-07-05T11:21:29.454647+00:00"},{"alias_kind":"pith_short_8","alias_value":"FS7NOJXQ","created_at":"2026-07-05T11:21:29.454647+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/FS7NOJXQHDAKYEBJHQ27L4BVHS","json":"https://pith.science/pith/FS7NOJXQHDAKYEBJHQ27L4BVHS.json","graph_json":"https://pith.science/api/pith-number/FS7NOJXQHDAKYEBJHQ27L4BVHS/graph.json","events_json":"https://pith.science/api/pith-number/FS7NOJXQHDAKYEBJHQ27L4BVHS/events.json","paper":"https://pith.science/paper/FS7NOJXQ"},"agent_actions":{"view_html":"https://pith.science/pith/FS7NOJXQHDAKYEBJHQ27L4BVHS","download_json":"https://pith.science/pith/FS7NOJXQHDAKYEBJHQ27L4BVHS.json","view_paper":"https://pith.science/paper/FS7NOJXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.09293&json=true","fetch_graph":"https://pith.science/api/pith-number/FS7NOJXQHDAKYEBJHQ27L4BVHS/graph.json","fetch_events":"https://pith.science/api/pith-number/FS7NOJXQHDAKYEBJHQ27L4BVHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FS7NOJXQHDAKYEBJHQ27L4BVHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FS7NOJXQHDAKYEBJHQ27L4BVHS/action/storage_attestation","attest_author":"https://pith.science/pith/FS7NOJXQHDAKYEBJHQ27L4BVHS/action/author_attestation","sign_citation":"https://pith.science/pith/FS7NOJXQHDAKYEBJHQ27L4BVHS/action/citation_signature","submit_replication":"https://pith.science/pith/FS7NOJXQHDAKYEBJHQ27L4BVHS/action/replication_record"}},"created_at":"2026-07-05T11:21:29.454647+00:00","updated_at":"2026-07-05T11:21:29.454647+00:00"}