{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FKCTE7I4VJFHVZDVHDIQWJGOAV","short_pith_number":"pith:FKCTE7I4","schema_version":"1.0","canonical_sha256":"2a85327d1caa4a7ae47538d10b24ce05765dcfb40c011c84caabd787117fb0ca","source":{"kind":"arxiv","id":"2608.10506","version":1},"attestation_state":"computed","paper":{"title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.PF"],"primary_cat":"cs.AR","authors_text":"Linh Nguyen, Zhixin Pan","submitted_at":"2026-08-11T05:27:53Z","abstract_excerpt":"Accurate pre-deployment estimation of CNN inference cost--energy, latency, and peak memory--is increasingly critical as models are deployed on resource-constrained GPU platforms. Existing approaches rely on FLOPs, latency measurements, or single-device profiling as energy proxies, overlooking the non-linear interactions between architectural design and hardware load. We present a workload characterization study of 13 419 CNN configurations on two GPU platforms (RTX 5090 and RTX 3080) under GPU telemetry, revealing that energy, latency, and memory exhibit fundamentally distinct scaling behavior"},"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":"2608.10506","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2026-08-11T05:27:53Z","cross_cats_sorted":["cs.LG","cs.PF"],"title_canon_sha256":"116dd9b9e4cdc5cdc185d416f10d18964291387fd28b6c86551adad90c076376","abstract_canon_sha256":"b12581f91d26355d4abec9220c16be7d30b30bfccf180dca8d3f70674d686ad8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:22:37.715688Z","signature_b64":"HHSjsbMoOdVjXvhO1oggWl4LJdpDnztaqWNKZL3aVqh3WW6bZhQGcOrfL0LiQ1pnZmcd7ComxNll5clw3fK0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a85327d1caa4a7ae47538d10b24ce05765dcfb40c011c84caabd787117fb0ca","last_reissued_at":"2026-08-12T01:22:37.714214Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:22:37.714214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.PF"],"primary_cat":"cs.AR","authors_text":"Linh Nguyen, Zhixin Pan","submitted_at":"2026-08-11T05:27:53Z","abstract_excerpt":"Accurate pre-deployment estimation of CNN inference cost--energy, latency, and peak memory--is increasingly critical as models are deployed on resource-constrained GPU platforms. Existing approaches rely on FLOPs, latency measurements, or single-device profiling as energy proxies, overlooking the non-linear interactions between architectural design and hardware load. We present a workload characterization study of 13 419 CNN configurations on two GPU platforms (RTX 5090 and RTX 3080) under GPU telemetry, revealing that energy, latency, and memory exhibit fundamentally distinct scaling behavior"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10506","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/2608.10506/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":"2608.10506","created_at":"2026-08-12T01:22:37.717963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.10506v1","created_at":"2026-08-12T01:22:37.717963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10506","created_at":"2026-08-12T01:22:37.717963+00:00"},{"alias_kind":"pith_short_12","alias_value":"FKCTE7I4VJFH","created_at":"2026-08-12T01:22:37.717963+00:00"},{"alias_kind":"pith_short_16","alias_value":"FKCTE7I4VJFHVZDV","created_at":"2026-08-12T01:22:37.717963+00:00"},{"alias_kind":"pith_short_8","alias_value":"FKCTE7I4","created_at":"2026-08-12T01:22:37.717963+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/FKCTE7I4VJFHVZDVHDIQWJGOAV","json":"https://pith.science/pith/FKCTE7I4VJFHVZDVHDIQWJGOAV.json","graph_json":"https://pith.science/api/pith-number/FKCTE7I4VJFHVZDVHDIQWJGOAV/graph.json","events_json":"https://pith.science/api/pith-number/FKCTE7I4VJFHVZDVHDIQWJGOAV/events.json","paper":"https://pith.science/paper/FKCTE7I4"},"agent_actions":{"view_html":"https://pith.science/pith/FKCTE7I4VJFHVZDVHDIQWJGOAV","download_json":"https://pith.science/pith/FKCTE7I4VJFHVZDVHDIQWJGOAV.json","view_paper":"https://pith.science/paper/FKCTE7I4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.10506&json=true","fetch_graph":"https://pith.science/api/pith-number/FKCTE7I4VJFHVZDVHDIQWJGOAV/graph.json","fetch_events":"https://pith.science/api/pith-number/FKCTE7I4VJFHVZDVHDIQWJGOAV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FKCTE7I4VJFHVZDVHDIQWJGOAV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FKCTE7I4VJFHVZDVHDIQWJGOAV/action/storage_attestation","attest_author":"https://pith.science/pith/FKCTE7I4VJFHVZDVHDIQWJGOAV/action/author_attestation","sign_citation":"https://pith.science/pith/FKCTE7I4VJFHVZDVHDIQWJGOAV/action/citation_signature","submit_replication":"https://pith.science/pith/FKCTE7I4VJFHVZDVHDIQWJGOAV/action/replication_record"}},"created_at":"2026-08-12T01:22:37.717963+00:00","updated_at":"2026-08-12T01:22:37.717963+00:00"}