{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YJ7CNUAQ2PCGYC65HDZKBX3XUK","short_pith_number":"pith:YJ7CNUAQ","schema_version":"1.0","canonical_sha256":"c27e26d010d3c46c0bdd38f2a0df77a2aa74afa4843034f52e271477f8d0226b","source":{"kind":"arxiv","id":"2504.08148","version":1},"attestation_state":"computed","paper":{"title":"Orchestrating Agents and Data for Enterprise: A Blueprint Architecture for Compound AI","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.DB","cs.DC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Dan Zhang, Eser Kandogan, Estevam Hruschka, Nikita Bhutani, Rafael Li Chen, Sairam Gurajada","submitted_at":"2025-04-10T22:19:41Z","abstract_excerpt":"Large language models (LLMs) have gained significant interest in industry due to their impressive capabilities across a wide range of tasks. However, the widespread adoption of LLMs presents several challenges, such as integration into existing applications and infrastructure, utilization of company proprietary data, models, and APIs, and meeting cost, quality, responsiveness, and other requirements. To address these challenges, there is a notable shift from monolithic models to compound AI systems, with the premise of more powerful, versatile, and reliable applications. However, progress thus"},"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":"2504.08148","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-10T22:19:41Z","cross_cats_sorted":["cs.DB","cs.DC","cs.LG"],"title_canon_sha256":"056cebaf1839e078b8351b11e7e538d2101c785adbc4aee6f1e8e8a799b8715b","abstract_canon_sha256":"7c50af1fab228e8dd263222195f01e2aef490f81f0bea0c0a12d3d1ab1114d4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:43.797716Z","signature_b64":"C5bOzcp0pVsklVbeIkP8Ijr75A/8D2c0l/fMJ5ODMzny6oZDncpCJTqZBCTboDpKxfs3vyPwQuCDRNoM8W+lCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c27e26d010d3c46c0bdd38f2a0df77a2aa74afa4843034f52e271477f8d0226b","last_reissued_at":"2026-07-05T10:47:43.797221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:43.797221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Orchestrating Agents and Data for Enterprise: A Blueprint Architecture for Compound AI","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.DB","cs.DC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Dan Zhang, Eser Kandogan, Estevam Hruschka, Nikita Bhutani, Rafael Li Chen, Sairam Gurajada","submitted_at":"2025-04-10T22:19:41Z","abstract_excerpt":"Large language models (LLMs) have gained significant interest in industry due to their impressive capabilities across a wide range of tasks. However, the widespread adoption of LLMs presents several challenges, such as integration into existing applications and infrastructure, utilization of company proprietary data, models, and APIs, and meeting cost, quality, responsiveness, and other requirements. To address these challenges, there is a notable shift from monolithic models to compound AI systems, with the premise of more powerful, versatile, and reliable applications. However, progress thus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08148","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/2504.08148/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":"2504.08148","created_at":"2026-07-05T10:47:43.797280+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.08148v1","created_at":"2026-07-05T10:47:43.797280+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08148","created_at":"2026-07-05T10:47:43.797280+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJ7CNUAQ2PCG","created_at":"2026-07-05T10:47:43.797280+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJ7CNUAQ2PCGYC65","created_at":"2026-07-05T10:47:43.797280+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJ7CNUAQ","created_at":"2026-07-05T10:47:43.797280+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00828","citing_title":"Exploring the Semantic Gap in Agentic Data Systems: A Formative Study of Operationalization Failures in Analytical Workflows","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YJ7CNUAQ2PCGYC65HDZKBX3XUK","json":"https://pith.science/pith/YJ7CNUAQ2PCGYC65HDZKBX3XUK.json","graph_json":"https://pith.science/api/pith-number/YJ7CNUAQ2PCGYC65HDZKBX3XUK/graph.json","events_json":"https://pith.science/api/pith-number/YJ7CNUAQ2PCGYC65HDZKBX3XUK/events.json","paper":"https://pith.science/paper/YJ7CNUAQ"},"agent_actions":{"view_html":"https://pith.science/pith/YJ7CNUAQ2PCGYC65HDZKBX3XUK","download_json":"https://pith.science/pith/YJ7CNUAQ2PCGYC65HDZKBX3XUK.json","view_paper":"https://pith.science/paper/YJ7CNUAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.08148&json=true","fetch_graph":"https://pith.science/api/pith-number/YJ7CNUAQ2PCGYC65HDZKBX3XUK/graph.json","fetch_events":"https://pith.science/api/pith-number/YJ7CNUAQ2PCGYC65HDZKBX3XUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJ7CNUAQ2PCGYC65HDZKBX3XUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJ7CNUAQ2PCGYC65HDZKBX3XUK/action/storage_attestation","attest_author":"https://pith.science/pith/YJ7CNUAQ2PCGYC65HDZKBX3XUK/action/author_attestation","sign_citation":"https://pith.science/pith/YJ7CNUAQ2PCGYC65HDZKBX3XUK/action/citation_signature","submit_replication":"https://pith.science/pith/YJ7CNUAQ2PCGYC65HDZKBX3XUK/action/replication_record"}},"created_at":"2026-07-05T10:47:43.797280+00:00","updated_at":"2026-07-05T10:47:43.797280+00:00"}