{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:T2FEVJUBQLMSU75JM3ILNAI2HW","short_pith_number":"pith:T2FEVJUB","schema_version":"1.0","canonical_sha256":"9e8a4aa68182d92a7fa966d0b6811a3d8b014c97322ed2263db12cf4b4803550","source":{"kind":"arxiv","id":"2107.10295","version":4},"attestation_state":"computed","paper":{"title":"A Review of Some Techniques for Inclusion of Domain-Knowledge into Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Aditya Ahuja, Ashwin Srinivasan, Sharad Chitlangia, Tirtharaj Dash","submitted_at":"2021-07-21T18:18:02Z","abstract_excerpt":"We present a survey of ways in which existing scientific knowledge are included when constructing models with neural networks. The inclusion of domain-knowledge is of special interest not just to constructing scientific assistants, but also, many other areas that involve understanding data using human-machine collaboration. In many such instances, machine-based model construction may benefit significantly from being provided with human-knowledge of the domain encoded in a sufficiently precise form. This paper examines the inclusion of domain-knowledge by means of changes to: the input, the los"},"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":"2107.10295","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-21T18:18:02Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"a3f5eb45c359506544754c926958c20de791af7f546c1c49b61fa20c39b78a38","abstract_canon_sha256":"ee32b80d8b9a00518906c9d1d05f06d9c6b8260060d99b1f85caf3355775800c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:50:35.842568Z","signature_b64":"aj3X5kmg2JNrywVL+2O0MuZYWYXRqCpFPuCXZh5WBqEBFNN608dFCkkuwHoL/n4pydzh4rODchaa9peUQFd+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e8a4aa68182d92a7fa966d0b6811a3d8b014c97322ed2263db12cf4b4803550","last_reissued_at":"2026-07-05T03:50:35.842081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:50:35.842081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Review of Some Techniques for Inclusion of Domain-Knowledge into Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Aditya Ahuja, Ashwin Srinivasan, Sharad Chitlangia, Tirtharaj Dash","submitted_at":"2021-07-21T18:18:02Z","abstract_excerpt":"We present a survey of ways in which existing scientific knowledge are included when constructing models with neural networks. The inclusion of domain-knowledge is of special interest not just to constructing scientific assistants, but also, many other areas that involve understanding data using human-machine collaboration. In many such instances, machine-based model construction may benefit significantly from being provided with human-knowledge of the domain encoded in a sufficiently precise form. This paper examines the inclusion of domain-knowledge by means of changes to: the input, the los"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.10295","kind":"arxiv","version":4},"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/2107.10295/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":"2107.10295","created_at":"2026-07-05T03:50:35.842139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.10295v4","created_at":"2026-07-05T03:50:35.842139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.10295","created_at":"2026-07-05T03:50:35.842139+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2FEVJUBQLMS","created_at":"2026-07-05T03:50:35.842139+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2FEVJUBQLMSU75J","created_at":"2026-07-05T03:50:35.842139+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2FEVJUB","created_at":"2026-07-05T03:50:35.842139+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.11127","citing_title":"Defining neurosymbolic AI","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T2FEVJUBQLMSU75JM3ILNAI2HW","json":"https://pith.science/pith/T2FEVJUBQLMSU75JM3ILNAI2HW.json","graph_json":"https://pith.science/api/pith-number/T2FEVJUBQLMSU75JM3ILNAI2HW/graph.json","events_json":"https://pith.science/api/pith-number/T2FEVJUBQLMSU75JM3ILNAI2HW/events.json","paper":"https://pith.science/paper/T2FEVJUB"},"agent_actions":{"view_html":"https://pith.science/pith/T2FEVJUBQLMSU75JM3ILNAI2HW","download_json":"https://pith.science/pith/T2FEVJUBQLMSU75JM3ILNAI2HW.json","view_paper":"https://pith.science/paper/T2FEVJUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.10295&json=true","fetch_graph":"https://pith.science/api/pith-number/T2FEVJUBQLMSU75JM3ILNAI2HW/graph.json","fetch_events":"https://pith.science/api/pith-number/T2FEVJUBQLMSU75JM3ILNAI2HW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2FEVJUBQLMSU75JM3ILNAI2HW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2FEVJUBQLMSU75JM3ILNAI2HW/action/storage_attestation","attest_author":"https://pith.science/pith/T2FEVJUBQLMSU75JM3ILNAI2HW/action/author_attestation","sign_citation":"https://pith.science/pith/T2FEVJUBQLMSU75JM3ILNAI2HW/action/citation_signature","submit_replication":"https://pith.science/pith/T2FEVJUBQLMSU75JM3ILNAI2HW/action/replication_record"}},"created_at":"2026-07-05T03:50:35.842139+00:00","updated_at":"2026-07-05T03:50:35.842139+00:00"}