{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XETYMARNSBTHEN5QIV2UABGQCB","short_pith_number":"pith:XETYMARN","schema_version":"1.0","canonical_sha256":"b92786022d90667237b045754004d0107eedb9217c6d548cc22cd04ba2d246b5","source":{"kind":"arxiv","id":"2606.00708","version":1},"attestation_state":"computed","paper":{"title":"MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Anthony K.H. Tung, Hao Ni, Kevin Zhang, Lei Jiang, Lukasz Szpruch, Raad Khraishi, Wen Ge, Xinyu Liu, Xinyu Xi, Yifan Bao, Yihao Ang","submitted_at":"2026-05-30T12:31:13Z","abstract_excerpt":"Automated data science is a structured model-selection problem. A solution must choose data transformations, feature representations, architecture, training procedure, evaluation protocol, and refinement strategy for a task. AutoML systems automate parts of this process, but typically search within predefined pipeline, model, and hyperparameter spaces. LLM-based agents offer greater flexibility through retrieval, code generation, and execution feedback, yet their modelling decisions are often unstructured, difficult to verify, and hard to reuse. We introduce \\textsc{MOSAIC} (Modular Orchestrat"},"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":"2606.00708","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-30T12:31:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"022237e2d9776f45a238001d5500cd3517cbd6976aecae32b871146e8e6e3d34","abstract_canon_sha256":"c41994de9f56bb1825b94222d0e1c11cef9307a3b9d2f022e6f279d5af8af50c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:03.392422Z","signature_b64":"r+JABpvYtfjVTlUqknXuuAp0ll6Hjte2faMvb8jnt0jQjUYp0w8+b9QVFxIcGOe1Cy5xVkiME/QwQApwMXvKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b92786022d90667237b045754004d0107eedb9217c6d548cc22cd04ba2d246b5","last_reissued_at":"2026-06-02T01:04:03.391972Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:03.391972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Anthony K.H. Tung, Hao Ni, Kevin Zhang, Lei Jiang, Lukasz Szpruch, Raad Khraishi, Wen Ge, Xinyu Liu, Xinyu Xi, Yifan Bao, Yihao Ang","submitted_at":"2026-05-30T12:31:13Z","abstract_excerpt":"Automated data science is a structured model-selection problem. A solution must choose data transformations, feature representations, architecture, training procedure, evaluation protocol, and refinement strategy for a task. AutoML systems automate parts of this process, but typically search within predefined pipeline, model, and hyperparameter spaces. LLM-based agents offer greater flexibility through retrieval, code generation, and execution feedback, yet their modelling decisions are often unstructured, difficult to verify, and hard to reuse. We introduce \\textsc{MOSAIC} (Modular Orchestrat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00708","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/2606.00708/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":"2606.00708","created_at":"2026-06-02T01:04:03.392032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00708v1","created_at":"2026-06-02T01:04:03.392032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00708","created_at":"2026-06-02T01:04:03.392032+00:00"},{"alias_kind":"pith_short_12","alias_value":"XETYMARNSBTH","created_at":"2026-06-02T01:04:03.392032+00:00"},{"alias_kind":"pith_short_16","alias_value":"XETYMARNSBTHEN5Q","created_at":"2026-06-02T01:04:03.392032+00:00"},{"alias_kind":"pith_short_8","alias_value":"XETYMARN","created_at":"2026-06-02T01:04:03.392032+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/XETYMARNSBTHEN5QIV2UABGQCB","json":"https://pith.science/pith/XETYMARNSBTHEN5QIV2UABGQCB.json","graph_json":"https://pith.science/api/pith-number/XETYMARNSBTHEN5QIV2UABGQCB/graph.json","events_json":"https://pith.science/api/pith-number/XETYMARNSBTHEN5QIV2UABGQCB/events.json","paper":"https://pith.science/paper/XETYMARN"},"agent_actions":{"view_html":"https://pith.science/pith/XETYMARNSBTHEN5QIV2UABGQCB","download_json":"https://pith.science/pith/XETYMARNSBTHEN5QIV2UABGQCB.json","view_paper":"https://pith.science/paper/XETYMARN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00708&json=true","fetch_graph":"https://pith.science/api/pith-number/XETYMARNSBTHEN5QIV2UABGQCB/graph.json","fetch_events":"https://pith.science/api/pith-number/XETYMARNSBTHEN5QIV2UABGQCB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XETYMARNSBTHEN5QIV2UABGQCB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XETYMARNSBTHEN5QIV2UABGQCB/action/storage_attestation","attest_author":"https://pith.science/pith/XETYMARNSBTHEN5QIV2UABGQCB/action/author_attestation","sign_citation":"https://pith.science/pith/XETYMARNSBTHEN5QIV2UABGQCB/action/citation_signature","submit_replication":"https://pith.science/pith/XETYMARNSBTHEN5QIV2UABGQCB/action/replication_record"}},"created_at":"2026-06-02T01:04:03.392032+00:00","updated_at":"2026-06-02T01:04:03.392032+00:00"}