{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LGQRSVR6CQT2G5KVXTWKD6GEMZ","short_pith_number":"pith:LGQRSVR6","schema_version":"1.0","canonical_sha256":"59a119563e1427a37555bceca1f8c46669a52bb240202dcd2e98c415b9ac52da","source":{"kind":"arxiv","id":"2509.05584","version":1},"attestation_state":"computed","paper":{"title":"ProfilingAgent: Profiling-Guided Agentic Reasoning for Adaptive Model Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.PF"],"primary_cat":"cs.LG","authors_text":"Aishwarya Sarkar, Ali Jannesari, Mohiuddin Bilwal, Sadegh Jafari","submitted_at":"2025-09-06T04:02:04Z","abstract_excerpt":"Foundation models face growing compute and memory bottlenecks, hindering deployment on resource-limited platforms. While compression techniques such as pruning and quantization are widely used, most rely on uniform heuristics that ignore architectural and runtime heterogeneity. Profiling tools expose per-layer latency, memory, and compute cost, yet are rarely integrated into automated pipelines. We propose ProfilingAgent, a profiling-guided, agentic approach that uses large language models (LLMs) to automate compression via structured pruning and post-training dynamic quantization. Our modular"},"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":"2509.05584","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-06T04:02:04Z","cross_cats_sorted":["cs.CV","cs.PF"],"title_canon_sha256":"6e879d481ee60354b62d0a250afe437c7270afe6f828f8568650e087678ecd16","abstract_canon_sha256":"0ab7f34b39786193f2d375238d4defc2dce903e7dc9850c572bed79bc17c4f1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:50.313234Z","signature_b64":"QE555lGRZZRg7fsPrA4WPH+fPFqXrrY+aUeRzkOZGN5WaV9g578D5HnQEPh7KSqShU/TYk7lyA4VDXJhWXAXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59a119563e1427a37555bceca1f8c46669a52bb240202dcd2e98c415b9ac52da","last_reissued_at":"2026-07-05T12:05:50.312762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:50.312762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProfilingAgent: Profiling-Guided Agentic Reasoning for Adaptive Model Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.PF"],"primary_cat":"cs.LG","authors_text":"Aishwarya Sarkar, Ali Jannesari, Mohiuddin Bilwal, Sadegh Jafari","submitted_at":"2025-09-06T04:02:04Z","abstract_excerpt":"Foundation models face growing compute and memory bottlenecks, hindering deployment on resource-limited platforms. While compression techniques such as pruning and quantization are widely used, most rely on uniform heuristics that ignore architectural and runtime heterogeneity. Profiling tools expose per-layer latency, memory, and compute cost, yet are rarely integrated into automated pipelines. We propose ProfilingAgent, a profiling-guided, agentic approach that uses large language models (LLMs) to automate compression via structured pruning and post-training dynamic quantization. Our modular"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05584","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/2509.05584/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":"2509.05584","created_at":"2026-07-05T12:05:50.312820+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.05584v1","created_at":"2026-07-05T12:05:50.312820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05584","created_at":"2026-07-05T12:05:50.312820+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGQRSVR6CQT2","created_at":"2026-07-05T12:05:50.312820+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGQRSVR6CQT2G5KV","created_at":"2026-07-05T12:05:50.312820+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGQRSVR6","created_at":"2026-07-05T12:05:50.312820+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/LGQRSVR6CQT2G5KVXTWKD6GEMZ","json":"https://pith.science/pith/LGQRSVR6CQT2G5KVXTWKD6GEMZ.json","graph_json":"https://pith.science/api/pith-number/LGQRSVR6CQT2G5KVXTWKD6GEMZ/graph.json","events_json":"https://pith.science/api/pith-number/LGQRSVR6CQT2G5KVXTWKD6GEMZ/events.json","paper":"https://pith.science/paper/LGQRSVR6"},"agent_actions":{"view_html":"https://pith.science/pith/LGQRSVR6CQT2G5KVXTWKD6GEMZ","download_json":"https://pith.science/pith/LGQRSVR6CQT2G5KVXTWKD6GEMZ.json","view_paper":"https://pith.science/paper/LGQRSVR6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.05584&json=true","fetch_graph":"https://pith.science/api/pith-number/LGQRSVR6CQT2G5KVXTWKD6GEMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/LGQRSVR6CQT2G5KVXTWKD6GEMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGQRSVR6CQT2G5KVXTWKD6GEMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGQRSVR6CQT2G5KVXTWKD6GEMZ/action/storage_attestation","attest_author":"https://pith.science/pith/LGQRSVR6CQT2G5KVXTWKD6GEMZ/action/author_attestation","sign_citation":"https://pith.science/pith/LGQRSVR6CQT2G5KVXTWKD6GEMZ/action/citation_signature","submit_replication":"https://pith.science/pith/LGQRSVR6CQT2G5KVXTWKD6GEMZ/action/replication_record"}},"created_at":"2026-07-05T12:05:50.312820+00:00","updated_at":"2026-07-05T12:05:50.312820+00:00"}