{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X3LNXZFC5G344BGJNK4DBZFXWI","short_pith_number":"pith:X3LNXZFC","schema_version":"1.0","canonical_sha256":"bed6dbe4a2e9b7ce04c96ab830e4b7b23c366409b509a53ce8ebcabcb1b5dac0","source":{"kind":"arxiv","id":"2506.09742","version":1},"attestation_state":"computed","paper":{"title":"Feature Engineering for Agents: An Adaptive Cognitive Architecture for Interpretable ML Monitoring","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ajay Dholakia, David Ellison, Gusseppe Bravo-Rocca, Jordi Guitart, Peini Liu, Rodrigo M Carrillo-Larco","submitted_at":"2025-06-11T13:48:25Z","abstract_excerpt":"Monitoring Machine Learning (ML) models in production environments is crucial, yet traditional approaches often yield verbose, low-interpretability outputs that hinder effective decision-making. We propose a cognitive architecture for ML monitoring that applies feature engineering principles to agents based on Large Language Models (LLMs), significantly enhancing the interpretability of monitoring outputs. Central to our approach is a Decision Procedure module that simulates feature engineering through three key steps: Refactor, Break Down, and Compile. The Refactor step improves data represen"},"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":"2506.09742","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-11T13:48:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bce08a0fc96106e5a3b94949a1e888c8737285b6cf7f523560bf047a998e6cad","abstract_canon_sha256":"5cc9185b286f9772e13a01253eff865a19ee7acde8d6314d50c8eea6170bd4a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:56.220112Z","signature_b64":"53AFOEvghldJcz+RUEes1i0lpnDh/5PxssmEaPuPcpeXJvmf8QXTNsfQ5VpLrtKeZsScMxzTQ0Y4J/WsxDt8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bed6dbe4a2e9b7ce04c96ab830e4b7b23c366409b509a53ce8ebcabcb1b5dac0","last_reissued_at":"2026-07-05T11:19:56.219580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:56.219580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Engineering for Agents: An Adaptive Cognitive Architecture for Interpretable ML Monitoring","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ajay Dholakia, David Ellison, Gusseppe Bravo-Rocca, Jordi Guitart, Peini Liu, Rodrigo M Carrillo-Larco","submitted_at":"2025-06-11T13:48:25Z","abstract_excerpt":"Monitoring Machine Learning (ML) models in production environments is crucial, yet traditional approaches often yield verbose, low-interpretability outputs that hinder effective decision-making. We propose a cognitive architecture for ML monitoring that applies feature engineering principles to agents based on Large Language Models (LLMs), significantly enhancing the interpretability of monitoring outputs. Central to our approach is a Decision Procedure module that simulates feature engineering through three key steps: Refactor, Break Down, and Compile. The Refactor step improves data represen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09742","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/2506.09742/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":"2506.09742","created_at":"2026-07-05T11:19:56.219657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09742v1","created_at":"2026-07-05T11:19:56.219657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09742","created_at":"2026-07-05T11:19:56.219657+00:00"},{"alias_kind":"pith_short_12","alias_value":"X3LNXZFC5G34","created_at":"2026-07-05T11:19:56.219657+00:00"},{"alias_kind":"pith_short_16","alias_value":"X3LNXZFC5G344BGJ","created_at":"2026-07-05T11:19:56.219657+00:00"},{"alias_kind":"pith_short_8","alias_value":"X3LNXZFC","created_at":"2026-07-05T11:19:56.219657+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/X3LNXZFC5G344BGJNK4DBZFXWI","json":"https://pith.science/pith/X3LNXZFC5G344BGJNK4DBZFXWI.json","graph_json":"https://pith.science/api/pith-number/X3LNXZFC5G344BGJNK4DBZFXWI/graph.json","events_json":"https://pith.science/api/pith-number/X3LNXZFC5G344BGJNK4DBZFXWI/events.json","paper":"https://pith.science/paper/X3LNXZFC"},"agent_actions":{"view_html":"https://pith.science/pith/X3LNXZFC5G344BGJNK4DBZFXWI","download_json":"https://pith.science/pith/X3LNXZFC5G344BGJNK4DBZFXWI.json","view_paper":"https://pith.science/paper/X3LNXZFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09742&json=true","fetch_graph":"https://pith.science/api/pith-number/X3LNXZFC5G344BGJNK4DBZFXWI/graph.json","fetch_events":"https://pith.science/api/pith-number/X3LNXZFC5G344BGJNK4DBZFXWI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X3LNXZFC5G344BGJNK4DBZFXWI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X3LNXZFC5G344BGJNK4DBZFXWI/action/storage_attestation","attest_author":"https://pith.science/pith/X3LNXZFC5G344BGJNK4DBZFXWI/action/author_attestation","sign_citation":"https://pith.science/pith/X3LNXZFC5G344BGJNK4DBZFXWI/action/citation_signature","submit_replication":"https://pith.science/pith/X3LNXZFC5G344BGJNK4DBZFXWI/action/replication_record"}},"created_at":"2026-07-05T11:19:56.219657+00:00","updated_at":"2026-07-05T11:19:56.219657+00:00"}