{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JP7INTA5YCEQXPSI3LJJVPLSUM","short_pith_number":"pith:JP7INTA5","schema_version":"1.0","canonical_sha256":"4bfe86cc1dc0890bbe48dad29abd72a301c2022975be5090dcf8ba1d45aeb5cd","source":{"kind":"arxiv","id":"2504.20348","version":2},"attestation_state":"computed","paper":{"title":"CarbonCall: Sustainability-Aware Function Calling for Large Language Models on Edge Devices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.PF","authors_text":"Andreas Karatzas, Dimitrios Stamoulis, Iraklis Anagnostopoulos, Varatheepan Paramanayakam","submitted_at":"2025-04-29T01:37:08Z","abstract_excerpt":"Large Language Models (LLMs) enable real-time function calling in edge AI systems but introduce significant computational overhead, leading to high power consumption and carbon emissions. Existing methods optimize for performance while neglecting sustainability, making them inefficient for energy-constrained environments. We introduce CarbonCall, a sustainability-aware function-calling framework that integrates dynamic tool selection, carbon-aware execution, and quantized LLM adaptation. CarbonCall adjusts power thresholds based on real-time carbon intensity forecasts and switches between mode"},"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":"2504.20348","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PF","submitted_at":"2025-04-29T01:37:08Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"b2e30e524abbb28395d9bf32ecd09c4f3a2efbf20445145b0384d14862758ea3","abstract_canon_sha256":"510f4cde80dd1e594fb343be554aa42b62a81017b77bb040a1212a0212969b17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:57.439377Z","signature_b64":"dumaeQEQwKCXIdW5hGj7AAuol2dAjTvcVH3hapq3TO50wqtmKT/g/7oU4ngXg8v3umcRZWXAM3uItowDM+8+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bfe86cc1dc0890bbe48dad29abd72a301c2022975be5090dcf8ba1d45aeb5cd","last_reissued_at":"2026-07-05T10:57:57.438872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:57.438872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CarbonCall: Sustainability-Aware Function Calling for Large Language Models on Edge Devices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.PF","authors_text":"Andreas Karatzas, Dimitrios Stamoulis, Iraklis Anagnostopoulos, Varatheepan Paramanayakam","submitted_at":"2025-04-29T01:37:08Z","abstract_excerpt":"Large Language Models (LLMs) enable real-time function calling in edge AI systems but introduce significant computational overhead, leading to high power consumption and carbon emissions. Existing methods optimize for performance while neglecting sustainability, making them inefficient for energy-constrained environments. We introduce CarbonCall, a sustainability-aware function-calling framework that integrates dynamic tool selection, carbon-aware execution, and quantized LLM adaptation. CarbonCall adjusts power thresholds based on real-time carbon intensity forecasts and switches between mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20348","kind":"arxiv","version":2},"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/2504.20348/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":"2504.20348","created_at":"2026-07-05T10:57:57.438929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.20348v2","created_at":"2026-07-05T10:57:57.438929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20348","created_at":"2026-07-05T10:57:57.438929+00:00"},{"alias_kind":"pith_short_12","alias_value":"JP7INTA5YCEQ","created_at":"2026-07-05T10:57:57.438929+00:00"},{"alias_kind":"pith_short_16","alias_value":"JP7INTA5YCEQXPSI","created_at":"2026-07-05T10:57:57.438929+00:00"},{"alias_kind":"pith_short_8","alias_value":"JP7INTA5","created_at":"2026-07-05T10:57:57.438929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01712","citing_title":"A Vertical Approach to Designing and Managing Sustainable Heterogeneous Edge Data Centers","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JP7INTA5YCEQXPSI3LJJVPLSUM","json":"https://pith.science/pith/JP7INTA5YCEQXPSI3LJJVPLSUM.json","graph_json":"https://pith.science/api/pith-number/JP7INTA5YCEQXPSI3LJJVPLSUM/graph.json","events_json":"https://pith.science/api/pith-number/JP7INTA5YCEQXPSI3LJJVPLSUM/events.json","paper":"https://pith.science/paper/JP7INTA5"},"agent_actions":{"view_html":"https://pith.science/pith/JP7INTA5YCEQXPSI3LJJVPLSUM","download_json":"https://pith.science/pith/JP7INTA5YCEQXPSI3LJJVPLSUM.json","view_paper":"https://pith.science/paper/JP7INTA5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.20348&json=true","fetch_graph":"https://pith.science/api/pith-number/JP7INTA5YCEQXPSI3LJJVPLSUM/graph.json","fetch_events":"https://pith.science/api/pith-number/JP7INTA5YCEQXPSI3LJJVPLSUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JP7INTA5YCEQXPSI3LJJVPLSUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JP7INTA5YCEQXPSI3LJJVPLSUM/action/storage_attestation","attest_author":"https://pith.science/pith/JP7INTA5YCEQXPSI3LJJVPLSUM/action/author_attestation","sign_citation":"https://pith.science/pith/JP7INTA5YCEQXPSI3LJJVPLSUM/action/citation_signature","submit_replication":"https://pith.science/pith/JP7INTA5YCEQXPSI3LJJVPLSUM/action/replication_record"}},"created_at":"2026-07-05T10:57:57.438929+00:00","updated_at":"2026-07-05T10:57:57.438929+00:00"}