{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XATRLBDQWZMTODMJTGTJFBBSNS","short_pith_number":"pith:XATRLBDQ","schema_version":"1.0","canonical_sha256":"b827158470b659370d8999a69284326ca055d4ceddd58494eb8e1839c3971492","source":{"kind":"arxiv","id":"1906.02243","version":1},"attestation_state":"computed","paper":{"title":"Energy and Policy Considerations for Deep Learning in NLP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ananya Ganesh, Andrew McCallum, Emma Strubell","submitted_at":"2019-06-05T18:40:53Z","abstract_excerpt":"Recent progress in hardware and methodology for training neural networks has ushered in a new generation of large networks trained on abundant data. These models have obtained notable gains in accuracy across many NLP tasks. However, these accuracy improvements depend on the availability of exceptionally large computational resources that necessitate similarly substantial energy consumption. As a result these models are costly to train and develop, both financially, due to the cost of hardware and electricity or cloud compute time, and environmentally, due to the carbon footprint required to f"},"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":"1906.02243","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-05T18:40:53Z","cross_cats_sorted":[],"title_canon_sha256":"121654b00bdbd9836c23ff373bfbbd3b39c3c299ebab73d769a6cab5aa5224cc","abstract_canon_sha256":"5ef7bd73dee869330d10988ea99a61da22d2f76633397b299d0705b8adcd7386"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:01.819281Z","signature_b64":"JW0PjqDqL7t6+r2x/OHcN2hEexEi62IORZVmVUqvoldTViBZSuHPAfFWGcRjpbHAzMB7+WdqJnccftu5SgPiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b827158470b659370d8999a69284326ca055d4ceddd58494eb8e1839c3971492","last_reissued_at":"2026-05-17T23:44:01.818706Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:01.818706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Energy and Policy Considerations for Deep Learning in NLP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ananya Ganesh, Andrew McCallum, Emma Strubell","submitted_at":"2019-06-05T18:40:53Z","abstract_excerpt":"Recent progress in hardware and methodology for training neural networks has ushered in a new generation of large networks trained on abundant data. These models have obtained notable gains in accuracy across many NLP tasks. However, these accuracy improvements depend on the availability of exceptionally large computational resources that necessitate similarly substantial energy consumption. As a result these models are costly to train and develop, both financially, due to the cost of hardware and electricity or cloud compute time, and environmentally, due to the carbon footprint required to f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02243","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":""},"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":"1906.02243","created_at":"2026-05-17T23:44:01.818791+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.02243v1","created_at":"2026-05-17T23:44:01.818791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02243","created_at":"2026-05-17T23:44:01.818791+00:00"},{"alias_kind":"pith_short_12","alias_value":"XATRLBDQWZMT","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"XATRLBDQWZMTODMJ","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"XATRLBDQ","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":35,"internal_anchor_count":18,"sample":[{"citing_arxiv_id":"2110.01552","citing_title":"Perhaps PTLMs Should Go to School -- A Task to Assess Open Book and Closed Book QA","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22840","citing_title":"The Cognitive Kardashev Scale: Quantifying the Material Envelope of Civilisational Computation","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"1907.09881","citing_title":"Convolutional Dictionary Learning in Hierarchical Networks","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2107.06499","citing_title":"Deduplicating Training Data Makes Language Models Better","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2204.06745","citing_title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","ref_index":90,"is_internal_anchor":true},{"citing_arxiv_id":"2405.00892","citing_title":"Wake Vision: A Tailored Dataset and Benchmark Suite for TinyML Computer Vision Applications","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2509.24517","citing_title":"Physics Priors Offer Useful Accuracy-Carbon Trade-Offs in Spatio-Temporal Forecasting","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16291","citing_title":"AI of the People, by the People, for the People: A Social Choice Approach to Collective Control of Artificial Intelligence","ref_index":96,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17159","citing_title":"MADP: A Multi-Agent Pipeline for Sustainable Document Processing with Human-in-the-Loop","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18889","citing_title":"Soft Learning","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2305.17493","citing_title":"The Curse of Recursion: Training on Generated Data Makes Models Forget","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18012","citing_title":"SAS: Semantic-aware Sampling for Generative Dataset Distillation","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2506.06816","citing_title":"How do datasets, developers, and models affect biases in a low-resourced language?: The Case of the Bengali Language","ref_index":132,"is_internal_anchor":true},{"citing_arxiv_id":"2510.14235","citing_title":"Spiking Neural Network Architecture Search: A Survey","ref_index":112,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16353","citing_title":"AgriIR: A Scalable Framework for Domain-Specific Knowledge Retrieval","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2603.16951","citing_title":"Minimum-Action Learning: Energy-Constrained Symbolic Model Selection for Physical Law Identification from Noisy Data","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"1910.09700","citing_title":"Quantifying the Carbon Emissions of Machine Learning","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14249","citing_title":"EnergyLens: Predictive Energy-Aware Exploration for Multi-GPU LLM Inference Optimization","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11733","citing_title":"Position: LLM Inference Should Be Evaluated as Energy-to-Token Production","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2101.03961","citing_title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2202.08906","citing_title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2009.14794","citing_title":"Rethinking Attention with Performers","ref_index":149,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06856","citing_title":"Benchmarked Yet Not Measured -- Generative AI Should be Evaluated Against Real-World Utility","ref_index":202,"is_internal_anchor":false},{"citing_arxiv_id":"2204.14198","citing_title":"Flamingo: a Visual Language Model for Few-Shot Learning","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24805","citing_title":"minAction.net: Energy-First Neural Architecture Design -- From Biological Principles to Systematic Validation","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XATRLBDQWZMTODMJTGTJFBBSNS","json":"https://pith.science/pith/XATRLBDQWZMTODMJTGTJFBBSNS.json","graph_json":"https://pith.science/api/pith-number/XATRLBDQWZMTODMJTGTJFBBSNS/graph.json","events_json":"https://pith.science/api/pith-number/XATRLBDQWZMTODMJTGTJFBBSNS/events.json","paper":"https://pith.science/paper/XATRLBDQ"},"agent_actions":{"view_html":"https://pith.science/pith/XATRLBDQWZMTODMJTGTJFBBSNS","download_json":"https://pith.science/pith/XATRLBDQWZMTODMJTGTJFBBSNS.json","view_paper":"https://pith.science/paper/XATRLBDQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.02243&json=true","fetch_graph":"https://pith.science/api/pith-number/XATRLBDQWZMTODMJTGTJFBBSNS/graph.json","fetch_events":"https://pith.science/api/pith-number/XATRLBDQWZMTODMJTGTJFBBSNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XATRLBDQWZMTODMJTGTJFBBSNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XATRLBDQWZMTODMJTGTJFBBSNS/action/storage_attestation","attest_author":"https://pith.science/pith/XATRLBDQWZMTODMJTGTJFBBSNS/action/author_attestation","sign_citation":"https://pith.science/pith/XATRLBDQWZMTODMJTGTJFBBSNS/action/citation_signature","submit_replication":"https://pith.science/pith/XATRLBDQWZMTODMJTGTJFBBSNS/action/replication_record"}},"created_at":"2026-05-17T23:44:01.818791+00:00","updated_at":"2026-05-17T23:44:01.818791+00:00"}