{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BRA3JABUNOAMUOKDWAXT7XEXXM","short_pith_number":"pith:BRA3JABU","schema_version":"1.0","canonical_sha256":"0c41b480346b80ca3943b02f3fdc97bb0b950bbe0cef49afa4f3600a9eca64c0","source":{"kind":"arxiv","id":"2412.09731","version":1},"attestation_state":"computed","paper":{"title":"Double-Exponential Increases in Inference Energy: The Cost of the Race for Accuracy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Karel Adamek, Wesley Armour, Zeyu Yang","submitted_at":"2024-12-12T21:44:08Z","abstract_excerpt":"Deep learning models in computer vision have achieved significant success but pose increasing concerns about energy consumption and sustainability. Despite these concerns, there is a lack of comprehensive understanding of their energy efficiency during inference. In this study, we conduct a comprehensive analysis of the inference energy consumption of 1,200 ImageNet classification models - the largest evaluation of its kind to date. Our findings reveal a steep diminishing return in accuracy gains relative to the increase in energy usage, highlighting sustainability concerns in the pursuit of m"},"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":"2412.09731","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T21:44:08Z","cross_cats_sorted":[],"title_canon_sha256":"d4278f5386c47d758fb3716f57371aadb052e231a147b790d79e95378ec99ade","abstract_canon_sha256":"9260765d7de65d7947b7525af9790e2dbc9115ea751192839c1c8e61d359cadd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:40.622545Z","signature_b64":"khuFYA//SNS+hG/ZUYpkClqlNeVmsxGT3Okqjwe+hJkXKSkGoRFeigv/J7DB11G61Ea3/jcehv7wWsL1i1TFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c41b480346b80ca3943b02f3fdc97bb0b950bbe0cef49afa4f3600a9eca64c0","last_reissued_at":"2026-07-05T09:48:40.622074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:40.622074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Double-Exponential Increases in Inference Energy: The Cost of the Race for Accuracy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Karel Adamek, Wesley Armour, Zeyu Yang","submitted_at":"2024-12-12T21:44:08Z","abstract_excerpt":"Deep learning models in computer vision have achieved significant success but pose increasing concerns about energy consumption and sustainability. Despite these concerns, there is a lack of comprehensive understanding of their energy efficiency during inference. In this study, we conduct a comprehensive analysis of the inference energy consumption of 1,200 ImageNet classification models - the largest evaluation of its kind to date. Our findings reveal a steep diminishing return in accuracy gains relative to the increase in energy usage, highlighting sustainability concerns in the pursuit of m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09731","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/2412.09731/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":"2412.09731","created_at":"2026-07-05T09:48:40.622136+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09731v1","created_at":"2026-07-05T09:48:40.622136+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09731","created_at":"2026-07-05T09:48:40.622136+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRA3JABUNOAM","created_at":"2026-07-05T09:48:40.622136+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRA3JABUNOAMUOKD","created_at":"2026-07-05T09:48:40.622136+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRA3JABU","created_at":"2026-07-05T09:48:40.622136+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05416","citing_title":"From Cradle to Cloud: A Life Cycle Review of AI's Environmental Footprint","ref_index":99,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BRA3JABUNOAMUOKDWAXT7XEXXM","json":"https://pith.science/pith/BRA3JABUNOAMUOKDWAXT7XEXXM.json","graph_json":"https://pith.science/api/pith-number/BRA3JABUNOAMUOKDWAXT7XEXXM/graph.json","events_json":"https://pith.science/api/pith-number/BRA3JABUNOAMUOKDWAXT7XEXXM/events.json","paper":"https://pith.science/paper/BRA3JABU"},"agent_actions":{"view_html":"https://pith.science/pith/BRA3JABUNOAMUOKDWAXT7XEXXM","download_json":"https://pith.science/pith/BRA3JABUNOAMUOKDWAXT7XEXXM.json","view_paper":"https://pith.science/paper/BRA3JABU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09731&json=true","fetch_graph":"https://pith.science/api/pith-number/BRA3JABUNOAMUOKDWAXT7XEXXM/graph.json","fetch_events":"https://pith.science/api/pith-number/BRA3JABUNOAMUOKDWAXT7XEXXM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRA3JABUNOAMUOKDWAXT7XEXXM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRA3JABUNOAMUOKDWAXT7XEXXM/action/storage_attestation","attest_author":"https://pith.science/pith/BRA3JABUNOAMUOKDWAXT7XEXXM/action/author_attestation","sign_citation":"https://pith.science/pith/BRA3JABUNOAMUOKDWAXT7XEXXM/action/citation_signature","submit_replication":"https://pith.science/pith/BRA3JABUNOAMUOKDWAXT7XEXXM/action/replication_record"}},"created_at":"2026-07-05T09:48:40.622136+00:00","updated_at":"2026-07-05T09:48:40.622136+00:00"}