{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:F2K7CZNGWW3MJTVWL6OS3532PD","short_pith_number":"pith:F2K7CZNG","schema_version":"1.0","canonical_sha256":"2e95f165a6b5b6c4ceb65f9d2df77a78feca2da782688a777f2b8c7d9c61ad38","source":{"kind":"arxiv","id":"2102.11965","version":2},"attestation_state":"computed","paper":{"title":"Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Andr\\'e Meyer-Vitali, Annette ten Teije, Frank van Harmelen, Maaike de Boer, Michael van Bekkum","submitted_at":"2021-02-23T22:16:05Z","abstract_excerpt":"The unification of statistical (data-driven) and symbolic (knowledge-driven) methods is widely recognised as one of the key challenges of modern AI. Recent years have seen large number of publications on such hybrid neuro-symbolic AI systems. That rapidly growing literature is highly diverse and mostly empirical, and is lacking a unifying view of the large variety of these hybrid systems. In this paper we analyse a large body of recent literature and we propose a set of modular design patterns for such hybrid, neuro-symbolic systems. We are able to describe the architecture of a very large num"},"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":"2102.11965","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-02-23T22:16:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9046bbe9f899878788d4a909ffb7b8026b08eac3aa3c59748f134d9c6b36280e","abstract_canon_sha256":"5db204ba9c750a6514b358ec065a64245f8c45d4193cc8af37d499a973507003"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:17.906230Z","signature_b64":"bpe8qe17qgPdi6uu2YtLpoyZMU8jjNcOni9e4HHDUoPJoS3lHc+dBF7+hP9+zV6+tj/du/nco/jXnMUnBZ05Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e95f165a6b5b6c4ceb65f9d2df77a78feca2da782688a777f2b8c7d9c61ad38","last_reissued_at":"2026-07-05T02:26:17.905711Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:17.905711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Andr\\'e Meyer-Vitali, Annette ten Teije, Frank van Harmelen, Maaike de Boer, Michael van Bekkum","submitted_at":"2021-02-23T22:16:05Z","abstract_excerpt":"The unification of statistical (data-driven) and symbolic (knowledge-driven) methods is widely recognised as one of the key challenges of modern AI. Recent years have seen large number of publications on such hybrid neuro-symbolic AI systems. That rapidly growing literature is highly diverse and mostly empirical, and is lacking a unifying view of the large variety of these hybrid systems. In this paper we analyse a large body of recent literature and we propose a set of modular design patterns for such hybrid, neuro-symbolic systems. We are able to describe the architecture of a very large num"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.11965","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/2102.11965/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":"2102.11965","created_at":"2026-07-05T02:26:17.905778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.11965v2","created_at":"2026-07-05T02:26:17.905778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.11965","created_at":"2026-07-05T02:26:17.905778+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2K7CZNGWW3M","created_at":"2026-07-05T02:26:17.905778+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2K7CZNGWW3MJTVW","created_at":"2026-07-05T02:26:17.905778+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2K7CZNG","created_at":"2026-07-05T02:26:17.905778+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11113","citing_title":"A Neurosymbolic Prolog Skill for LLM-Driven Service Placement","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19339","citing_title":"Stitching Gaps: Fusing Situated Perceptual Knowledge with Vision Transformers for High-Level Image Classification","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F2K7CZNGWW3MJTVWL6OS3532PD","json":"https://pith.science/pith/F2K7CZNGWW3MJTVWL6OS3532PD.json","graph_json":"https://pith.science/api/pith-number/F2K7CZNGWW3MJTVWL6OS3532PD/graph.json","events_json":"https://pith.science/api/pith-number/F2K7CZNGWW3MJTVWL6OS3532PD/events.json","paper":"https://pith.science/paper/F2K7CZNG"},"agent_actions":{"view_html":"https://pith.science/pith/F2K7CZNGWW3MJTVWL6OS3532PD","download_json":"https://pith.science/pith/F2K7CZNGWW3MJTVWL6OS3532PD.json","view_paper":"https://pith.science/paper/F2K7CZNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.11965&json=true","fetch_graph":"https://pith.science/api/pith-number/F2K7CZNGWW3MJTVWL6OS3532PD/graph.json","fetch_events":"https://pith.science/api/pith-number/F2K7CZNGWW3MJTVWL6OS3532PD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2K7CZNGWW3MJTVWL6OS3532PD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2K7CZNGWW3MJTVWL6OS3532PD/action/storage_attestation","attest_author":"https://pith.science/pith/F2K7CZNGWW3MJTVWL6OS3532PD/action/author_attestation","sign_citation":"https://pith.science/pith/F2K7CZNGWW3MJTVWL6OS3532PD/action/citation_signature","submit_replication":"https://pith.science/pith/F2K7CZNGWW3MJTVWL6OS3532PD/action/replication_record"}},"created_at":"2026-07-05T02:26:17.905778+00:00","updated_at":"2026-07-05T02:26:17.905778+00:00"}