{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:O62ZODFMN66S4YBNAF3DVXR5CP","short_pith_number":"pith:O62ZODFM","schema_version":"1.0","canonical_sha256":"77b5970cac6fbd2e602d01763ade3d13dbb8783162834acbf1964c8cd6822117","source":{"kind":"arxiv","id":"2108.12370","version":1},"attestation_state":"computed","paper":{"title":"DomiKnowS: A Library for Integration of Symbolic Domain Knowledge in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Aliakbar Nafar, Andrzej Uszok, Elaheh Raisi, Hossein Rajaby Faghihi, Parisa Kordjamshidi, Quan Guo","submitted_at":"2021-08-27T16:06:42Z","abstract_excerpt":"We demonstrate a library for the integration of domain knowledge in deep learning architectures. Using this library, the structure of the data is expressed symbolically via graph declarations and the logical constraints over outputs or latent variables can be seamlessly added to the deep models. The domain knowledge can be defined explicitly, which improves the models' explainability in addition to the performance and generalizability in the low-data regime. Several approaches for such an integration of symbolic and sub-symbolic models have been introduced; however, there is no library to faci"},"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":"2108.12370","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-27T16:06:42Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"6293e592b618a15e8475d42c926e9cbe0e5e1144753757be003ff5e755f3509e","abstract_canon_sha256":"e39eb4b7cc926e259002c126a997f54134a0bb27e48ad6436d76dd5a6ab1c0d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:09:24.919809Z","signature_b64":"e3tb5HIMjG6t1x/FUOgHw2zmVkGoyIjmsmLI+j5KcrMnPOHXK25T3v8nM+xmrm1LWaEgtpANpFlHQMchzBL5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77b5970cac6fbd2e602d01763ade3d13dbb8783162834acbf1964c8cd6822117","last_reissued_at":"2026-07-05T03:09:24.919451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:09:24.919451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DomiKnowS: A Library for Integration of Symbolic Domain Knowledge in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Aliakbar Nafar, Andrzej Uszok, Elaheh Raisi, Hossein Rajaby Faghihi, Parisa Kordjamshidi, Quan Guo","submitted_at":"2021-08-27T16:06:42Z","abstract_excerpt":"We demonstrate a library for the integration of domain knowledge in deep learning architectures. Using this library, the structure of the data is expressed symbolically via graph declarations and the logical constraints over outputs or latent variables can be seamlessly added to the deep models. The domain knowledge can be defined explicitly, which improves the models' explainability in addition to the performance and generalizability in the low-data regime. Several approaches for such an integration of symbolic and sub-symbolic models have been introduced; however, there is no library to faci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.12370","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/2108.12370/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":"2108.12370","created_at":"2026-07-05T03:09:24.919509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.12370v1","created_at":"2026-07-05T03:09:24.919509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.12370","created_at":"2026-07-05T03:09:24.919509+00:00"},{"alias_kind":"pith_short_12","alias_value":"O62ZODFMN66S","created_at":"2026-07-05T03:09:24.919509+00:00"},{"alias_kind":"pith_short_16","alias_value":"O62ZODFMN66S4YBN","created_at":"2026-07-05T03:09:24.919509+00:00"},{"alias_kind":"pith_short_8","alias_value":"O62ZODFM","created_at":"2026-07-05T03:09:24.919509+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.10249","citing_title":"Investigating Language Model Capabilities to Represent and Process Formal Knowledge: A Preliminary Study to Assist Ontology Engineering","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O62ZODFMN66S4YBNAF3DVXR5CP","json":"https://pith.science/pith/O62ZODFMN66S4YBNAF3DVXR5CP.json","graph_json":"https://pith.science/api/pith-number/O62ZODFMN66S4YBNAF3DVXR5CP/graph.json","events_json":"https://pith.science/api/pith-number/O62ZODFMN66S4YBNAF3DVXR5CP/events.json","paper":"https://pith.science/paper/O62ZODFM"},"agent_actions":{"view_html":"https://pith.science/pith/O62ZODFMN66S4YBNAF3DVXR5CP","download_json":"https://pith.science/pith/O62ZODFMN66S4YBNAF3DVXR5CP.json","view_paper":"https://pith.science/paper/O62ZODFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.12370&json=true","fetch_graph":"https://pith.science/api/pith-number/O62ZODFMN66S4YBNAF3DVXR5CP/graph.json","fetch_events":"https://pith.science/api/pith-number/O62ZODFMN66S4YBNAF3DVXR5CP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O62ZODFMN66S4YBNAF3DVXR5CP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O62ZODFMN66S4YBNAF3DVXR5CP/action/storage_attestation","attest_author":"https://pith.science/pith/O62ZODFMN66S4YBNAF3DVXR5CP/action/author_attestation","sign_citation":"https://pith.science/pith/O62ZODFMN66S4YBNAF3DVXR5CP/action/citation_signature","submit_replication":"https://pith.science/pith/O62ZODFMN66S4YBNAF3DVXR5CP/action/replication_record"}},"created_at":"2026-07-05T03:09:24.919509+00:00","updated_at":"2026-07-05T03:09:24.919509+00:00"}