{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L5G65FSX6BFKREO2QUS7NAMJCJ","short_pith_number":"pith:L5G65FSX","schema_version":"1.0","canonical_sha256":"5f4dee9657f04aa891da8525f6818912510b1f7829679de0769b9e2b8342d6b5","source":{"kind":"arxiv","id":"2412.14684","version":2},"attestation_state":"computed","paper":{"title":"Bel Esprit: Multi-Agent Framework for Building AI Model Pipelines","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.HC","cs.MA"],"primary_cat":"cs.AI","authors_text":"AhmedElmogtaba Abdelaziz, Hassan Sawaf, Mohamed Al-Badrashiny, Thiago castro Ferreira, Yunsu Kim","submitted_at":"2024-12-19T09:36:33Z","abstract_excerpt":"As the demand for artificial intelligence (AI) grows to address complex real-world tasks, single models are often insufficient, requiring the integration of multiple models into pipelines. This paper introduces Bel Esprit, a conversational agent designed to construct AI model pipelines based on user-defined requirements. Bel Esprit employs a multi-agent framework where subagents collaborate to clarify requirements, build, validate, and populate pipelines with appropriate models. We demonstrate the effectiveness of this framework in generating pipelines from ambiguous user queries, using both h"},"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":"2412.14684","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-19T09:36:33Z","cross_cats_sorted":["cs.HC","cs.MA"],"title_canon_sha256":"bdad52486fbd1ef523e72246e8c6b3041f9619b1c19361db9140c19e854b6234","abstract_canon_sha256":"80fb5757c85587c92ff25f91ced71b4eaab9907a901a6ea22a74edea5b781df9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:49.086756Z","signature_b64":"LQDbbH8x3kDsHgwCHOpPFWFi+wrKR+DfppE6XaFpKQBAATwCSDUiq4zCH4Sn4Ky+ROPqp8sSopGNZDpKg7FoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f4dee9657f04aa891da8525f6818912510b1f7829679de0769b9e2b8342d6b5","last_reissued_at":"2026-07-05T11:20:49.086308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:49.086308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bel Esprit: Multi-Agent Framework for Building AI Model Pipelines","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.HC","cs.MA"],"primary_cat":"cs.AI","authors_text":"AhmedElmogtaba Abdelaziz, Hassan Sawaf, Mohamed Al-Badrashiny, Thiago castro Ferreira, Yunsu Kim","submitted_at":"2024-12-19T09:36:33Z","abstract_excerpt":"As the demand for artificial intelligence (AI) grows to address complex real-world tasks, single models are often insufficient, requiring the integration of multiple models into pipelines. This paper introduces Bel Esprit, a conversational agent designed to construct AI model pipelines based on user-defined requirements. Bel Esprit employs a multi-agent framework where subagents collaborate to clarify requirements, build, validate, and populate pipelines with appropriate models. We demonstrate the effectiveness of this framework in generating pipelines from ambiguous user queries, using both h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14684","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/2412.14684/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":"2412.14684","created_at":"2026-07-05T11:20:49.086394+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14684v2","created_at":"2026-07-05T11:20:49.086394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14684","created_at":"2026-07-05T11:20:49.086394+00:00"},{"alias_kind":"pith_short_12","alias_value":"L5G65FSX6BFK","created_at":"2026-07-05T11:20:49.086394+00:00"},{"alias_kind":"pith_short_16","alias_value":"L5G65FSX6BFKREO2","created_at":"2026-07-05T11:20:49.086394+00:00"},{"alias_kind":"pith_short_8","alias_value":"L5G65FSX","created_at":"2026-07-05T11:20:49.086394+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18115","citing_title":"Agentic AI framework for End-to-End Medical Data Inference","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L5G65FSX6BFKREO2QUS7NAMJCJ","json":"https://pith.science/pith/L5G65FSX6BFKREO2QUS7NAMJCJ.json","graph_json":"https://pith.science/api/pith-number/L5G65FSX6BFKREO2QUS7NAMJCJ/graph.json","events_json":"https://pith.science/api/pith-number/L5G65FSX6BFKREO2QUS7NAMJCJ/events.json","paper":"https://pith.science/paper/L5G65FSX"},"agent_actions":{"view_html":"https://pith.science/pith/L5G65FSX6BFKREO2QUS7NAMJCJ","download_json":"https://pith.science/pith/L5G65FSX6BFKREO2QUS7NAMJCJ.json","view_paper":"https://pith.science/paper/L5G65FSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14684&json=true","fetch_graph":"https://pith.science/api/pith-number/L5G65FSX6BFKREO2QUS7NAMJCJ/graph.json","fetch_events":"https://pith.science/api/pith-number/L5G65FSX6BFKREO2QUS7NAMJCJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L5G65FSX6BFKREO2QUS7NAMJCJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L5G65FSX6BFKREO2QUS7NAMJCJ/action/storage_attestation","attest_author":"https://pith.science/pith/L5G65FSX6BFKREO2QUS7NAMJCJ/action/author_attestation","sign_citation":"https://pith.science/pith/L5G65FSX6BFKREO2QUS7NAMJCJ/action/citation_signature","submit_replication":"https://pith.science/pith/L5G65FSX6BFKREO2QUS7NAMJCJ/action/replication_record"}},"created_at":"2026-07-05T11:20:49.086394+00:00","updated_at":"2026-07-05T11:20:49.086394+00:00"}