{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PFNXQZDTYF6NICIU6K26TAA7FK","short_pith_number":"pith:PFNXQZDT","schema_version":"1.0","canonical_sha256":"795b786473c17cd40914f2b5e9801f2aae20a3dff7f61db3895762c52fef5732","source":{"kind":"arxiv","id":"2009.00540","version":1},"attestation_state":"computed","paper":{"title":"Training Deep Neural Networks with Constrained Learning Parameters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher D. Carothers, James A. Hendler, John E. Mitchell, Malik Magdon-Ismail, Prasanna Date","submitted_at":"2020-09-01T16:20:11Z","abstract_excerpt":"Today's deep learning models are primarily trained on CPUs and GPUs. Although these models tend to have low error, they consume high power and utilize large amount of memory owing to double precision floating point learning parameters. Beyond the Moore's law, a significant portion of deep learning tasks would run on edge computing systems, which will form an indispensable part of the entire computation fabric. Subsequently, training deep learning models for such systems will have to be tailored and adopted to generate models that have the following desirable characteristics: low error, low mem"},"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":"2009.00540","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-01T16:20:11Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"6e2b1280d100b064ee8b01a37c17e77d9b3a768485d77b5d1b06a542013d8e30","abstract_canon_sha256":"35c4cb0d30cb21d9cbf7e243ea9d00972f49282752344b5c092ac938e3befab6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:22.603789Z","signature_b64":"HUy22qTupkXE/nvwX7VP5elKj9zSd9Yl3toG9MzBwBNv5yDwmSuyGgQ7+gro0mcIqcQquhEwVDfucMUPeSmDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"795b786473c17cd40914f2b5e9801f2aae20a3dff7f61db3895762c52fef5732","last_reissued_at":"2026-07-05T03:31:22.603426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:22.603426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Deep Neural Networks with Constrained Learning Parameters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher D. Carothers, James A. Hendler, John E. Mitchell, Malik Magdon-Ismail, Prasanna Date","submitted_at":"2020-09-01T16:20:11Z","abstract_excerpt":"Today's deep learning models are primarily trained on CPUs and GPUs. Although these models tend to have low error, they consume high power and utilize large amount of memory owing to double precision floating point learning parameters. Beyond the Moore's law, a significant portion of deep learning tasks would run on edge computing systems, which will form an indispensable part of the entire computation fabric. Subsequently, training deep learning models for such systems will have to be tailored and adopted to generate models that have the following desirable characteristics: low error, low mem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.00540","kind":"arxiv","version":1},"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/2009.00540/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":"2009.00540","created_at":"2026-07-05T03:31:22.603482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.00540v1","created_at":"2026-07-05T03:31:22.603482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.00540","created_at":"2026-07-05T03:31:22.603482+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFNXQZDTYF6N","created_at":"2026-07-05T03:31:22.603482+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFNXQZDTYF6NICIU","created_at":"2026-07-05T03:31:22.603482+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFNXQZDT","created_at":"2026-07-05T03:31:22.603482+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/PFNXQZDTYF6NICIU6K26TAA7FK","json":"https://pith.science/pith/PFNXQZDTYF6NICIU6K26TAA7FK.json","graph_json":"https://pith.science/api/pith-number/PFNXQZDTYF6NICIU6K26TAA7FK/graph.json","events_json":"https://pith.science/api/pith-number/PFNXQZDTYF6NICIU6K26TAA7FK/events.json","paper":"https://pith.science/paper/PFNXQZDT"},"agent_actions":{"view_html":"https://pith.science/pith/PFNXQZDTYF6NICIU6K26TAA7FK","download_json":"https://pith.science/pith/PFNXQZDTYF6NICIU6K26TAA7FK.json","view_paper":"https://pith.science/paper/PFNXQZDT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.00540&json=true","fetch_graph":"https://pith.science/api/pith-number/PFNXQZDTYF6NICIU6K26TAA7FK/graph.json","fetch_events":"https://pith.science/api/pith-number/PFNXQZDTYF6NICIU6K26TAA7FK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFNXQZDTYF6NICIU6K26TAA7FK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFNXQZDTYF6NICIU6K26TAA7FK/action/storage_attestation","attest_author":"https://pith.science/pith/PFNXQZDTYF6NICIU6K26TAA7FK/action/author_attestation","sign_citation":"https://pith.science/pith/PFNXQZDTYF6NICIU6K26TAA7FK/action/citation_signature","submit_replication":"https://pith.science/pith/PFNXQZDTYF6NICIU6K26TAA7FK/action/replication_record"}},"created_at":"2026-07-05T03:31:22.603482+00:00","updated_at":"2026-07-05T03:31:22.603482+00:00"}