{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q3KBHTZVZTMVQPRZ22VCPMLI3R","short_pith_number":"pith:Q3KBHTZV","schema_version":"1.0","canonical_sha256":"86d413cf35ccd9583e39d6aa27b168dc7a7a2a67a6b6e8a14d5a545f9dde1c0f","source":{"kind":"arxiv","id":"2403.12900","version":1},"attestation_state":"computed","paper":{"title":"Toward Sustainable GenAI using Generation Directives for Carbon-Friendly Large Language Model Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.DC","authors_text":"Baolin Li, Devesh Tiwari, Vijay Gadepally, Yankai Jiang","submitted_at":"2024-03-19T16:53:53Z","abstract_excerpt":"The rapid advancement of Generative Artificial Intelligence (GenAI) across diverse sectors raises significant environmental concerns, notably the carbon emissions from their cloud and high performance computing (HPC) infrastructure. This paper presents Sprout, an innovative framework designed to address these concerns by reducing the carbon footprint of generative Large Language Model (LLM) inference services. Sprout leverages the innovative concept of \"generation directives\" to guide the autoregressive generation process, thereby enhancing carbon efficiency. Our proposed method meticulously b"},"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":"2403.12900","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-03-19T16:53:53Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"eeca89ccb7b9b91852540a121cd70413ec070d28cd456a631c30ed627c728edd","abstract_canon_sha256":"4bf47f6f3cd900c07a9bc9636e84192357cf6bd8c5853f9efc9dbeb564c4cfe4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:09.238786Z","signature_b64":"wPe9jFikSIITkw89Ta1cBEgeDc9mpO+6WEK57edwQ2OfwODUJbuucmH4rjrHz/jdllON1NlErB/bH1SeAM/BAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86d413cf35ccd9583e39d6aa27b168dc7a7a2a67a6b6e8a14d5a545f9dde1c0f","last_reissued_at":"2026-07-05T07:58:09.238213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:09.238213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Sustainable GenAI using Generation Directives for Carbon-Friendly Large Language Model Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.DC","authors_text":"Baolin Li, Devesh Tiwari, Vijay Gadepally, Yankai Jiang","submitted_at":"2024-03-19T16:53:53Z","abstract_excerpt":"The rapid advancement of Generative Artificial Intelligence (GenAI) across diverse sectors raises significant environmental concerns, notably the carbon emissions from their cloud and high performance computing (HPC) infrastructure. This paper presents Sprout, an innovative framework designed to address these concerns by reducing the carbon footprint of generative Large Language Model (LLM) inference services. Sprout leverages the innovative concept of \"generation directives\" to guide the autoregressive generation process, thereby enhancing carbon efficiency. Our proposed method meticulously b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12900","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/2403.12900/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":"2403.12900","created_at":"2026-07-05T07:58:09.238276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12900v1","created_at":"2026-07-05T07:58:09.238276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12900","created_at":"2026-07-05T07:58:09.238276+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3KBHTZVZTMV","created_at":"2026-07-05T07:58:09.238276+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3KBHTZVZTMVQPRZ","created_at":"2026-07-05T07:58:09.238276+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3KBHTZV","created_at":"2026-07-05T07:58:09.238276+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.13217","citing_title":"Sustainability via LLM Right-sizing","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25903","citing_title":"Carbon-Taxed Transformers: A Green Compression Pipeline for Overgrown Language Models","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q3KBHTZVZTMVQPRZ22VCPMLI3R","json":"https://pith.science/pith/Q3KBHTZVZTMVQPRZ22VCPMLI3R.json","graph_json":"https://pith.science/api/pith-number/Q3KBHTZVZTMVQPRZ22VCPMLI3R/graph.json","events_json":"https://pith.science/api/pith-number/Q3KBHTZVZTMVQPRZ22VCPMLI3R/events.json","paper":"https://pith.science/paper/Q3KBHTZV"},"agent_actions":{"view_html":"https://pith.science/pith/Q3KBHTZVZTMVQPRZ22VCPMLI3R","download_json":"https://pith.science/pith/Q3KBHTZVZTMVQPRZ22VCPMLI3R.json","view_paper":"https://pith.science/paper/Q3KBHTZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12900&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3KBHTZVZTMVQPRZ22VCPMLI3R/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3KBHTZVZTMVQPRZ22VCPMLI3R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3KBHTZVZTMVQPRZ22VCPMLI3R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3KBHTZVZTMVQPRZ22VCPMLI3R/action/storage_attestation","attest_author":"https://pith.science/pith/Q3KBHTZVZTMVQPRZ22VCPMLI3R/action/author_attestation","sign_citation":"https://pith.science/pith/Q3KBHTZVZTMVQPRZ22VCPMLI3R/action/citation_signature","submit_replication":"https://pith.science/pith/Q3KBHTZVZTMVQPRZ22VCPMLI3R/action/replication_record"}},"created_at":"2026-07-05T07:58:09.238276+00:00","updated_at":"2026-07-05T07:58:09.238276+00:00"}