{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KQVUY2WOMCMIODHWNU7IXJZNVZ","short_pith_number":"pith:KQVUY2WO","schema_version":"1.0","canonical_sha256":"542b4c6ace6098870cf66d3e8ba72dae62676bd3fdb68ea7ed63107ca52b9291","source":{"kind":"arxiv","id":"2606.27841","version":1},"attestation_state":"computed","paper":{"title":"WattLayer: Get Layers Right to Estimate Inference Energy of Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adrien Sardi, Fr\\'ed\\'eric Giroire, Joanna Moulierac, Marie-Line Alberi Morel, Sara Alouf","submitted_at":"2026-06-26T08:27:04Z","abstract_excerpt":"The widespread adoption of Artificial Intelligence (AI) has led to increasing concerns about energy consumption, yet there is a lack of standardized methodologies to accurately estimate AI inference energy consumption, particularly across various tasks and architectures. In this study, we propose a task independent, layer-wise energy estimation model for AI architectures. Our model is evaluated on a large dataset of more than 100,000 layers for 295 neural network architectures across 3 widely-used tasks and 3 distinct hardware platforms. Our approach achieves a median error of 19.6%, outperfor"},"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":"2606.27841","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T08:27:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"61690cfb9ef7caaedff8f6f368e6a2f9d4108dfe1094a407fd02a28ea9b1ad3a","abstract_canon_sha256":"0f0fc375ff42f13f7b1b65b1462cccd95651d2c3c5c4db1d7688c424c589bb56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:50.096670Z","signature_b64":"3BojnZPenYHPajvuB6m+6yPBxJxtBGKGbthmShkEPCjkJQiaEx9DJdnrVyFNkd7qeAS8VRHzH3B84uJE3P0wAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"542b4c6ace6098870cf66d3e8ba72dae62676bd3fdb68ea7ed63107ca52b9291","last_reissued_at":"2026-06-29T01:14:50.096253Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:50.096253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WattLayer: Get Layers Right to Estimate Inference Energy of Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adrien Sardi, Fr\\'ed\\'eric Giroire, Joanna Moulierac, Marie-Line Alberi Morel, Sara Alouf","submitted_at":"2026-06-26T08:27:04Z","abstract_excerpt":"The widespread adoption of Artificial Intelligence (AI) has led to increasing concerns about energy consumption, yet there is a lack of standardized methodologies to accurately estimate AI inference energy consumption, particularly across various tasks and architectures. In this study, we propose a task independent, layer-wise energy estimation model for AI architectures. Our model is evaluated on a large dataset of more than 100,000 layers for 295 neural network architectures across 3 widely-used tasks and 3 distinct hardware platforms. Our approach achieves a median error of 19.6%, outperfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27841","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/2606.27841/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":"2606.27841","created_at":"2026-06-29T01:14:50.096311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27841v1","created_at":"2026-06-29T01:14:50.096311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27841","created_at":"2026-06-29T01:14:50.096311+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQVUY2WOMCMI","created_at":"2026-06-29T01:14:50.096311+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQVUY2WOMCMIODHW","created_at":"2026-06-29T01:14:50.096311+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQVUY2WO","created_at":"2026-06-29T01:14:50.096311+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/KQVUY2WOMCMIODHWNU7IXJZNVZ","json":"https://pith.science/pith/KQVUY2WOMCMIODHWNU7IXJZNVZ.json","graph_json":"https://pith.science/api/pith-number/KQVUY2WOMCMIODHWNU7IXJZNVZ/graph.json","events_json":"https://pith.science/api/pith-number/KQVUY2WOMCMIODHWNU7IXJZNVZ/events.json","paper":"https://pith.science/paper/KQVUY2WO"},"agent_actions":{"view_html":"https://pith.science/pith/KQVUY2WOMCMIODHWNU7IXJZNVZ","download_json":"https://pith.science/pith/KQVUY2WOMCMIODHWNU7IXJZNVZ.json","view_paper":"https://pith.science/paper/KQVUY2WO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27841&json=true","fetch_graph":"https://pith.science/api/pith-number/KQVUY2WOMCMIODHWNU7IXJZNVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/KQVUY2WOMCMIODHWNU7IXJZNVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQVUY2WOMCMIODHWNU7IXJZNVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQVUY2WOMCMIODHWNU7IXJZNVZ/action/storage_attestation","attest_author":"https://pith.science/pith/KQVUY2WOMCMIODHWNU7IXJZNVZ/action/author_attestation","sign_citation":"https://pith.science/pith/KQVUY2WOMCMIODHWNU7IXJZNVZ/action/citation_signature","submit_replication":"https://pith.science/pith/KQVUY2WOMCMIODHWNU7IXJZNVZ/action/replication_record"}},"created_at":"2026-06-29T01:14:50.096311+00:00","updated_at":"2026-06-29T01:14:50.096311+00:00"}