{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OJAMLMRFUC53RKLTPIDBMEUAL6","short_pith_number":"pith:OJAMLMRF","schema_version":"1.0","canonical_sha256":"7240c5b225a0bbb8a9737a061612805fa414f7b742e4a447c9740c0798ab01b2","source":{"kind":"arxiv","id":"2501.14836","version":1},"attestation_state":"computed","paper":{"title":"Symbolic Knowledge Extraction and Injection with Sub-symbolic Predictors: A Systematic Literature Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.LO"],"primary_cat":"cs.AI","authors_text":"Andrea Agiollo, Andrea Omicini, Federico Sabbatini, Giovanni Ciatto, Matteo Magnini","submitted_at":"2025-01-23T18:00:05Z","abstract_excerpt":"In this paper we focus on the opacity issue of sub-symbolic machine learning predictors by promoting two complementary activities, namely, symbolic knowledge extraction (SKE) and injection (SKI) from and into sub-symbolic predictors. We consider as symbolic any language being intelligible and interpretable for both humans and computers. Accordingly, we propose general meta-models for both SKE and SKI, along with two taxonomies for the classification of SKE and SKI methods. By adopting an explainable artificial intelligence (XAI) perspective, we highlight how such methods can be exploited to mi"},"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":"2501.14836","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-23T18:00:05Z","cross_cats_sorted":["cs.LG","cs.LO"],"title_canon_sha256":"af785a94cb7784395cacf8a0ef956a6b21c83bf372d4d94a7a4c9b2b558fbf52","abstract_canon_sha256":"fbe196d8fb7e88e8c98f952c542df91402c20940066cb0fe518a40905cff6113"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:19.673795Z","signature_b64":"jsrB6UljngU4xGE3ao6QR+L9vvw+ch9xnUK+BJ8oLU25Dc1k6lCTT/PYWNNj3TzoPE86pZ471wT6T8tKy93cDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7240c5b225a0bbb8a9737a061612805fa414f7b742e4a447c9740c0798ab01b2","last_reissued_at":"2026-07-05T10:05:19.673332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:19.673332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symbolic Knowledge Extraction and Injection with Sub-symbolic Predictors: A Systematic Literature Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.LO"],"primary_cat":"cs.AI","authors_text":"Andrea Agiollo, Andrea Omicini, Federico Sabbatini, Giovanni Ciatto, Matteo Magnini","submitted_at":"2025-01-23T18:00:05Z","abstract_excerpt":"In this paper we focus on the opacity issue of sub-symbolic machine learning predictors by promoting two complementary activities, namely, symbolic knowledge extraction (SKE) and injection (SKI) from and into sub-symbolic predictors. We consider as symbolic any language being intelligible and interpretable for both humans and computers. Accordingly, we propose general meta-models for both SKE and SKI, along with two taxonomies for the classification of SKE and SKI methods. By adopting an explainable artificial intelligence (XAI) perspective, we highlight how such methods can be exploited to mi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14836","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/2501.14836/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":"2501.14836","created_at":"2026-07-05T10:05:19.673392+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14836v1","created_at":"2026-07-05T10:05:19.673392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14836","created_at":"2026-07-05T10:05:19.673392+00:00"},{"alias_kind":"pith_short_12","alias_value":"OJAMLMRFUC53","created_at":"2026-07-05T10:05:19.673392+00:00"},{"alias_kind":"pith_short_16","alias_value":"OJAMLMRFUC53RKLT","created_at":"2026-07-05T10:05:19.673392+00:00"},{"alias_kind":"pith_short_8","alias_value":"OJAMLMRF","created_at":"2026-07-05T10:05:19.673392+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/OJAMLMRFUC53RKLTPIDBMEUAL6","json":"https://pith.science/pith/OJAMLMRFUC53RKLTPIDBMEUAL6.json","graph_json":"https://pith.science/api/pith-number/OJAMLMRFUC53RKLTPIDBMEUAL6/graph.json","events_json":"https://pith.science/api/pith-number/OJAMLMRFUC53RKLTPIDBMEUAL6/events.json","paper":"https://pith.science/paper/OJAMLMRF"},"agent_actions":{"view_html":"https://pith.science/pith/OJAMLMRFUC53RKLTPIDBMEUAL6","download_json":"https://pith.science/pith/OJAMLMRFUC53RKLTPIDBMEUAL6.json","view_paper":"https://pith.science/paper/OJAMLMRF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14836&json=true","fetch_graph":"https://pith.science/api/pith-number/OJAMLMRFUC53RKLTPIDBMEUAL6/graph.json","fetch_events":"https://pith.science/api/pith-number/OJAMLMRFUC53RKLTPIDBMEUAL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OJAMLMRFUC53RKLTPIDBMEUAL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OJAMLMRFUC53RKLTPIDBMEUAL6/action/storage_attestation","attest_author":"https://pith.science/pith/OJAMLMRFUC53RKLTPIDBMEUAL6/action/author_attestation","sign_citation":"https://pith.science/pith/OJAMLMRFUC53RKLTPIDBMEUAL6/action/citation_signature","submit_replication":"https://pith.science/pith/OJAMLMRFUC53RKLTPIDBMEUAL6/action/replication_record"}},"created_at":"2026-07-05T10:05:19.673392+00:00","updated_at":"2026-07-05T10:05:19.673392+00:00"}