{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:E4IBG3HYCOVDOBSNEMEN46RNXW","short_pith_number":"pith:E4IBG3HY","schema_version":"1.0","canonical_sha256":"2710136cf813aa37064d2308de7a2dbd87f81ea39d96839bbb9a5ab9367b54a1","source":{"kind":"arxiv","id":"2308.13057","version":1},"attestation_state":"computed","paper":{"title":"Data-Side Efficiencies for Lightweight Convolutional Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bryan Bo Cao, Lawrence O'Gorman, Michael Coss, Shubham Jain","submitted_at":"2023-08-24T19:50:25Z","abstract_excerpt":"We examine how the choice of data-side attributes for two important visual tasks of image classification and object detection can aid in the choice or design of lightweight convolutional neural networks. We show by experimentation how four data attributes - number of classes, object color, image resolution, and object scale affect neural network model size and efficiency. Intra- and inter-class similarity metrics, based on metric learning, are defined to guide the evaluation of these attributes toward achieving lightweight models. Evaluations made using these metrics are shown to require 30x l"},"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":"2308.13057","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-24T19:50:25Z","cross_cats_sorted":[],"title_canon_sha256":"02b5fa350b979311a93fdb588cf435821737ffc72a4f25c3fde6cd725644819d","abstract_canon_sha256":"bc827107cecc837bbe2e3bffabc6fef5e9caf0cc2b31b211345021440a60a0b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:37.919568Z","signature_b64":"2cYpXULTRt1UowcLiYa9Kd4E4drqRf2D5B1j4DWN2HzxrHMFnVeYtVkDE9rR0+W2Y5HTCXDdiUOUndGyi9NhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2710136cf813aa37064d2308de7a2dbd87f81ea39d96839bbb9a5ab9367b54a1","last_reissued_at":"2026-07-05T06:44:37.919077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:37.919077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Side Efficiencies for Lightweight Convolutional Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bryan Bo Cao, Lawrence O'Gorman, Michael Coss, Shubham Jain","submitted_at":"2023-08-24T19:50:25Z","abstract_excerpt":"We examine how the choice of data-side attributes for two important visual tasks of image classification and object detection can aid in the choice or design of lightweight convolutional neural networks. We show by experimentation how four data attributes - number of classes, object color, image resolution, and object scale affect neural network model size and efficiency. Intra- and inter-class similarity metrics, based on metric learning, are defined to guide the evaluation of these attributes toward achieving lightweight models. Evaluations made using these metrics are shown to require 30x l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13057","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/2308.13057/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":"2308.13057","created_at":"2026-07-05T06:44:37.919142+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.13057v1","created_at":"2026-07-05T06:44:37.919142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13057","created_at":"2026-07-05T06:44:37.919142+00:00"},{"alias_kind":"pith_short_12","alias_value":"E4IBG3HYCOVD","created_at":"2026-07-05T06:44:37.919142+00:00"},{"alias_kind":"pith_short_16","alias_value":"E4IBG3HYCOVDOBSN","created_at":"2026-07-05T06:44:37.919142+00:00"},{"alias_kind":"pith_short_8","alias_value":"E4IBG3HY","created_at":"2026-07-05T06:44:37.919142+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19712","citing_title":"Efficient Neural Network Model Selection for Few-Class Application Datasets","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E4IBG3HYCOVDOBSNEMEN46RNXW","json":"https://pith.science/pith/E4IBG3HYCOVDOBSNEMEN46RNXW.json","graph_json":"https://pith.science/api/pith-number/E4IBG3HYCOVDOBSNEMEN46RNXW/graph.json","events_json":"https://pith.science/api/pith-number/E4IBG3HYCOVDOBSNEMEN46RNXW/events.json","paper":"https://pith.science/paper/E4IBG3HY"},"agent_actions":{"view_html":"https://pith.science/pith/E4IBG3HYCOVDOBSNEMEN46RNXW","download_json":"https://pith.science/pith/E4IBG3HYCOVDOBSNEMEN46RNXW.json","view_paper":"https://pith.science/paper/E4IBG3HY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.13057&json=true","fetch_graph":"https://pith.science/api/pith-number/E4IBG3HYCOVDOBSNEMEN46RNXW/graph.json","fetch_events":"https://pith.science/api/pith-number/E4IBG3HYCOVDOBSNEMEN46RNXW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4IBG3HYCOVDOBSNEMEN46RNXW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4IBG3HYCOVDOBSNEMEN46RNXW/action/storage_attestation","attest_author":"https://pith.science/pith/E4IBG3HYCOVDOBSNEMEN46RNXW/action/author_attestation","sign_citation":"https://pith.science/pith/E4IBG3HYCOVDOBSNEMEN46RNXW/action/citation_signature","submit_replication":"https://pith.science/pith/E4IBG3HYCOVDOBSNEMEN46RNXW/action/replication_record"}},"created_at":"2026-07-05T06:44:37.919142+00:00","updated_at":"2026-07-05T06:44:37.919142+00:00"}