{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SYXLG63VJHJCM54QR5SG4EPFEO","short_pith_number":"pith:SYXLG63V","schema_version":"1.0","canonical_sha256":"962eb37b7549d22677908f646e11e523a7ef97a58d8e0af109620c1ced998382","source":{"kind":"arxiv","id":"2106.01199","version":1},"attestation_state":"computed","paper":{"title":"IrEne: Interpretable Energy Prediction for Transformers","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aruna Balasubramanian, Harsh Trivedi, Niranjan Balasubramanian, Qingqing Cao, Yash Kumar Lal","submitted_at":"2021-06-02T14:43:51Z","abstract_excerpt":"Existing software-based energy measurements of NLP models are not accurate because they do not consider the complex interactions between energy consumption and model execution. We present IrEne, an interpretable and extensible energy prediction system that accurately predicts the inference energy consumption of a wide range of Transformer-based NLP models. IrEne constructs a model tree graph that breaks down the NLP model into modules that are further broken down into low-level machine learning (ML) primitives. IrEne predicts the inference energy consumption of the ML primitives as a function "},"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":"2106.01199","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-02T14:43:51Z","cross_cats_sorted":[],"title_canon_sha256":"ff6fd0433fce42c6f7014b7cbfcf678482da4ea5d11b2626e3182b127295d222","abstract_canon_sha256":"aa887bebb3e7975def62a176737ccf3d00d759a6f545511d2d317fd1915e83cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:44.751881Z","signature_b64":"NdHZ9JgerP0uLWi9Ij/zcOwPLAwArrWcwhR7OYIeA0y7+2nlLdvHmCbfGjeSPta9plXDC0F4q/M10qukBSpmDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"962eb37b7549d22677908f646e11e523a7ef97a58d8e0af109620c1ced998382","last_reissued_at":"2026-07-05T02:45:44.751410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:44.751410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IrEne: Interpretable Energy Prediction for Transformers","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aruna Balasubramanian, Harsh Trivedi, Niranjan Balasubramanian, Qingqing Cao, Yash Kumar Lal","submitted_at":"2021-06-02T14:43:51Z","abstract_excerpt":"Existing software-based energy measurements of NLP models are not accurate because they do not consider the complex interactions between energy consumption and model execution. We present IrEne, an interpretable and extensible energy prediction system that accurately predicts the inference energy consumption of a wide range of Transformer-based NLP models. IrEne constructs a model tree graph that breaks down the NLP model into modules that are further broken down into low-level machine learning (ML) primitives. IrEne predicts the inference energy consumption of the ML primitives as a function "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01199","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/2106.01199/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":"2106.01199","created_at":"2026-07-05T02:45:44.751479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.01199v1","created_at":"2026-07-05T02:45:44.751479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01199","created_at":"2026-07-05T02:45:44.751479+00:00"},{"alias_kind":"pith_short_12","alias_value":"SYXLG63VJHJC","created_at":"2026-07-05T02:45:44.751479+00:00"},{"alias_kind":"pith_short_16","alias_value":"SYXLG63VJHJCM54Q","created_at":"2026-07-05T02:45:44.751479+00:00"},{"alias_kind":"pith_short_8","alias_value":"SYXLG63V","created_at":"2026-07-05T02:45:44.751479+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01774","citing_title":"Greening AI-enabled Systems with Software Engineering: A Research Agenda for Environmentally Sustainable AI Practices","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SYXLG63VJHJCM54QR5SG4EPFEO","json":"https://pith.science/pith/SYXLG63VJHJCM54QR5SG4EPFEO.json","graph_json":"https://pith.science/api/pith-number/SYXLG63VJHJCM54QR5SG4EPFEO/graph.json","events_json":"https://pith.science/api/pith-number/SYXLG63VJHJCM54QR5SG4EPFEO/events.json","paper":"https://pith.science/paper/SYXLG63V"},"agent_actions":{"view_html":"https://pith.science/pith/SYXLG63VJHJCM54QR5SG4EPFEO","download_json":"https://pith.science/pith/SYXLG63VJHJCM54QR5SG4EPFEO.json","view_paper":"https://pith.science/paper/SYXLG63V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.01199&json=true","fetch_graph":"https://pith.science/api/pith-number/SYXLG63VJHJCM54QR5SG4EPFEO/graph.json","fetch_events":"https://pith.science/api/pith-number/SYXLG63VJHJCM54QR5SG4EPFEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SYXLG63VJHJCM54QR5SG4EPFEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SYXLG63VJHJCM54QR5SG4EPFEO/action/storage_attestation","attest_author":"https://pith.science/pith/SYXLG63VJHJCM54QR5SG4EPFEO/action/author_attestation","sign_citation":"https://pith.science/pith/SYXLG63VJHJCM54QR5SG4EPFEO/action/citation_signature","submit_replication":"https://pith.science/pith/SYXLG63VJHJCM54QR5SG4EPFEO/action/replication_record"}},"created_at":"2026-07-05T02:45:44.751479+00:00","updated_at":"2026-07-05T02:45:44.751479+00:00"}