{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RSXTKDAAIEFMRDAAPJOWG4QIJS","short_pith_number":"pith:RSXTKDAA","schema_version":"1.0","canonical_sha256":"8caf350c00410ac88c007a5d6372084c9f4b88f9b3aeac0a2057a7a8713b9e9e","source":{"kind":"arxiv","id":"2512.22431","version":6},"attestation_state":"computed","paper":{"title":"Monadic Context Engineering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.FL"],"primary_cat":"cs.AI","authors_text":"Andrew Chi-Chih Yao, Mengdi Wang, Yang Yuan, Yifan Zhang","submitted_at":"2025-12-27T01:52:06Z","abstract_excerpt":"The proliferation of Large Language Models (LLMs) has catalyzed a shift towards autonomous agents capable of complex reasoning and tool use. However, current agent architectures are frequently constructed using imperative, ad hoc patterns. This results in brittle systems plagued by difficulties in state management, error handling, and concurrency. This paper introduces Monadic Context Engineering (MCE), a novel architectural paradigm leveraging the algebraic structures of Functors, Applicative Functors, and Monads to provide a formal foundation for agent design. MCE treats agent workflows as c"},"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":"2512.22431","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-12-27T01:52:06Z","cross_cats_sorted":["cs.CL","cs.FL"],"title_canon_sha256":"066380f23e2655b0459d31d400b851749056d1a7185629fdd390357d13246557","abstract_canon_sha256":"c65a56150ca22c3e9f51b46c19b25fbd92ae103af441ccae76c45537d66d8105"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T00:16:51.699929Z","signature_b64":"VBYvLD7sVMcwEWAlB156Rl+0NH0UWmAZP0Le76pa1SV6JwmIDOnEFmjS0UwcLh0TN6VoBye9QLvatm7ifdfoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8caf350c00410ac88c007a5d6372084c9f4b88f9b3aeac0a2057a7a8713b9e9e","last_reissued_at":"2026-07-03T00:16:51.699449Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T00:16:51.699449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Monadic Context Engineering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.FL"],"primary_cat":"cs.AI","authors_text":"Andrew Chi-Chih Yao, Mengdi Wang, Yang Yuan, Yifan Zhang","submitted_at":"2025-12-27T01:52:06Z","abstract_excerpt":"The proliferation of Large Language Models (LLMs) has catalyzed a shift towards autonomous agents capable of complex reasoning and tool use. However, current agent architectures are frequently constructed using imperative, ad hoc patterns. This results in brittle systems plagued by difficulties in state management, error handling, and concurrency. This paper introduces Monadic Context Engineering (MCE), a novel architectural paradigm leveraging the algebraic structures of Functors, Applicative Functors, and Monads to provide a formal foundation for agent design. MCE treats agent workflows as c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.22431","kind":"arxiv","version":6},"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/2512.22431/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":"2512.22431","created_at":"2026-07-03T00:16:51.699508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.22431v6","created_at":"2026-07-03T00:16:51.699508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.22431","created_at":"2026-07-03T00:16:51.699508+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSXTKDAAIEFM","created_at":"2026-07-03T00:16:51.699508+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSXTKDAAIEFMRDAA","created_at":"2026-07-03T00:16:51.699508+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSXTKDAA","created_at":"2026-07-03T00:16:51.699508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2602.14690","citing_title":"Harness Engineering for Agentic AI Coding Tools: An Exploratory Study","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RSXTKDAAIEFMRDAAPJOWG4QIJS","json":"https://pith.science/pith/RSXTKDAAIEFMRDAAPJOWG4QIJS.json","graph_json":"https://pith.science/api/pith-number/RSXTKDAAIEFMRDAAPJOWG4QIJS/graph.json","events_json":"https://pith.science/api/pith-number/RSXTKDAAIEFMRDAAPJOWG4QIJS/events.json","paper":"https://pith.science/paper/RSXTKDAA"},"agent_actions":{"view_html":"https://pith.science/pith/RSXTKDAAIEFMRDAAPJOWG4QIJS","download_json":"https://pith.science/pith/RSXTKDAAIEFMRDAAPJOWG4QIJS.json","view_paper":"https://pith.science/paper/RSXTKDAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.22431&json=true","fetch_graph":"https://pith.science/api/pith-number/RSXTKDAAIEFMRDAAPJOWG4QIJS/graph.json","fetch_events":"https://pith.science/api/pith-number/RSXTKDAAIEFMRDAAPJOWG4QIJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSXTKDAAIEFMRDAAPJOWG4QIJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSXTKDAAIEFMRDAAPJOWG4QIJS/action/storage_attestation","attest_author":"https://pith.science/pith/RSXTKDAAIEFMRDAAPJOWG4QIJS/action/author_attestation","sign_citation":"https://pith.science/pith/RSXTKDAAIEFMRDAAPJOWG4QIJS/action/citation_signature","submit_replication":"https://pith.science/pith/RSXTKDAAIEFMRDAAPJOWG4QIJS/action/replication_record"}},"created_at":"2026-07-03T00:16:51.699508+00:00","updated_at":"2026-07-03T00:16:51.699508+00:00"}