{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OLA76COXBYY66KQ7JCBRTR3DMX","short_pith_number":"pith:OLA76COX","schema_version":"1.0","canonical_sha256":"72c1ff09d70e31ef2a1f488319c76365e8268e8160c1d3393e4997be92864e3c","source":{"kind":"arxiv","id":"2507.18993","version":1},"attestation_state":"computed","paper":{"title":"Agent0: Leveraging LLM Agents to Discover Multi-value Features from Text for Enhanced Recommendations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Andra\\v{z} Tori, Beno\\^it Guilleminot, Bla\\v{z} \\v{S}krlj","submitted_at":"2025-07-25T06:45:10Z","abstract_excerpt":"Large language models (LLMs) and their associated agent-based frameworks have significantly advanced automated information extraction, a critical component of modern recommender systems. While these multitask frameworks are widely used in code generation, their application in data-centric research is still largely untapped. This paper presents Agent0, an LLM-driven, agent-based system designed to automate information extraction and feature construction from raw, unstructured text. Categorical features are crucial for large-scale recommender systems but are often expensive to acquire. Agent0 co"},"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":"2507.18993","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-25T06:45:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1af9ad8e058502570f20b82f3ffc803e88bf4e2e546697fd989b3655596b78c5","abstract_canon_sha256":"5df197cb66909e46d0be11f359db7c850daec9b6dbeb8c6fec8c2a3fdc9a280d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:17.518286Z","signature_b64":"28MTBW/UJPI462ittvURqqILTU4z+en0/eFo3joqYWXJKI706rJAk8qmxgGdKyg17sBJOowY9ejMWM1Czv4TBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72c1ff09d70e31ef2a1f488319c76365e8268e8160c1d3393e4997be92864e3c","last_reissued_at":"2026-07-05T11:43:17.517780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:17.517780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agent0: Leveraging LLM Agents to Discover Multi-value Features from Text for Enhanced Recommendations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Andra\\v{z} Tori, Beno\\^it Guilleminot, Bla\\v{z} \\v{S}krlj","submitted_at":"2025-07-25T06:45:10Z","abstract_excerpt":"Large language models (LLMs) and their associated agent-based frameworks have significantly advanced automated information extraction, a critical component of modern recommender systems. While these multitask frameworks are widely used in code generation, their application in data-centric research is still largely untapped. This paper presents Agent0, an LLM-driven, agent-based system designed to automate information extraction and feature construction from raw, unstructured text. Categorical features are crucial for large-scale recommender systems but are often expensive to acquire. Agent0 co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18993","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/2507.18993/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":"2507.18993","created_at":"2026-07-05T11:43:17.517845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18993v1","created_at":"2026-07-05T11:43:17.517845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18993","created_at":"2026-07-05T11:43:17.517845+00:00"},{"alias_kind":"pith_short_12","alias_value":"OLA76COXBYY6","created_at":"2026-07-05T11:43:17.517845+00:00"},{"alias_kind":"pith_short_16","alias_value":"OLA76COXBYY66KQ7","created_at":"2026-07-05T11:43:17.517845+00:00"},{"alias_kind":"pith_short_8","alias_value":"OLA76COX","created_at":"2026-07-05T11:43:17.517845+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/OLA76COXBYY66KQ7JCBRTR3DMX","json":"https://pith.science/pith/OLA76COXBYY66KQ7JCBRTR3DMX.json","graph_json":"https://pith.science/api/pith-number/OLA76COXBYY66KQ7JCBRTR3DMX/graph.json","events_json":"https://pith.science/api/pith-number/OLA76COXBYY66KQ7JCBRTR3DMX/events.json","paper":"https://pith.science/paper/OLA76COX"},"agent_actions":{"view_html":"https://pith.science/pith/OLA76COXBYY66KQ7JCBRTR3DMX","download_json":"https://pith.science/pith/OLA76COXBYY66KQ7JCBRTR3DMX.json","view_paper":"https://pith.science/paper/OLA76COX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18993&json=true","fetch_graph":"https://pith.science/api/pith-number/OLA76COXBYY66KQ7JCBRTR3DMX/graph.json","fetch_events":"https://pith.science/api/pith-number/OLA76COXBYY66KQ7JCBRTR3DMX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OLA76COXBYY66KQ7JCBRTR3DMX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OLA76COXBYY66KQ7JCBRTR3DMX/action/storage_attestation","attest_author":"https://pith.science/pith/OLA76COXBYY66KQ7JCBRTR3DMX/action/author_attestation","sign_citation":"https://pith.science/pith/OLA76COXBYY66KQ7JCBRTR3DMX/action/citation_signature","submit_replication":"https://pith.science/pith/OLA76COXBYY66KQ7JCBRTR3DMX/action/replication_record"}},"created_at":"2026-07-05T11:43:17.517845+00:00","updated_at":"2026-07-05T11:43:17.517845+00:00"}