{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LK672JMUJZO7UNJTSG2RVDCLYT","short_pith_number":"pith:LK672JMU","schema_version":"1.0","canonical_sha256":"5abdfd25944e5dfa353391b51a8c4bc4ef663a9e9b7c143ef290037cf7023a8d","source":{"kind":"arxiv","id":"2006.16867","version":2},"attestation_state":"computed","paper":{"title":"Boosting Deep Neural Networks with Geometrical Prior Knowledge: A Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexandru Paul Condurache, Matthias Rath","submitted_at":"2020-06-30T14:56:05Z","abstract_excerpt":"Deep Neural Networks achieve state-of-the-art results in many different problem settings by exploiting vast amounts of training data. However, collecting, storing and - in the case of supervised learning - labelling the data is expensive and time-consuming. Additionally, assessing the networks' generalization abilities or predicting how the inferred output changes under input transformations is complicated since the networks are usually treated as a black box. Both of these problems can be mitigated by incorporating prior knowledge into the neural network. One promising approach, inspired by t"},"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":"2006.16867","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2020-06-30T14:56:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6bda3dd45d08f56635e1a98ab223fc4417d767a6069004409ea8e4302e771f0e","abstract_canon_sha256":"50161b0ed186525e68e06541b728a4748e6b3d2d5bc22ee6f24df540cdc1ecc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:42.970044Z","signature_b64":"QpQxuCuQy5MZohPhWpN86F6vSGlVGJUpv+9FD1AmqddkldhrRcjlgPCdBRD0vI0fGCTYaeCpzAYfYK8sGRNFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5abdfd25944e5dfa353391b51a8c4bc4ef663a9e9b7c143ef290037cf7023a8d","last_reissued_at":"2026-07-05T05:47:42.969640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:42.969640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Deep Neural Networks with Geometrical Prior Knowledge: A Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexandru Paul Condurache, Matthias Rath","submitted_at":"2020-06-30T14:56:05Z","abstract_excerpt":"Deep Neural Networks achieve state-of-the-art results in many different problem settings by exploiting vast amounts of training data. However, collecting, storing and - in the case of supervised learning - labelling the data is expensive and time-consuming. Additionally, assessing the networks' generalization abilities or predicting how the inferred output changes under input transformations is complicated since the networks are usually treated as a black box. Both of these problems can be mitigated by incorporating prior knowledge into the neural network. One promising approach, inspired by t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.16867","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/2006.16867/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":"2006.16867","created_at":"2026-07-05T05:47:42.969694+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.16867v2","created_at":"2026-07-05T05:47:42.969694+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.16867","created_at":"2026-07-05T05:47:42.969694+00:00"},{"alias_kind":"pith_short_12","alias_value":"LK672JMUJZO7","created_at":"2026-07-05T05:47:42.969694+00:00"},{"alias_kind":"pith_short_16","alias_value":"LK672JMUJZO7UNJT","created_at":"2026-07-05T05:47:42.969694+00:00"},{"alias_kind":"pith_short_8","alias_value":"LK672JMU","created_at":"2026-07-05T05:47:42.969694+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12493","citing_title":"Symmetry-preserving neural networks in lattice field theories","ref_index":72,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LK672JMUJZO7UNJTSG2RVDCLYT","json":"https://pith.science/pith/LK672JMUJZO7UNJTSG2RVDCLYT.json","graph_json":"https://pith.science/api/pith-number/LK672JMUJZO7UNJTSG2RVDCLYT/graph.json","events_json":"https://pith.science/api/pith-number/LK672JMUJZO7UNJTSG2RVDCLYT/events.json","paper":"https://pith.science/paper/LK672JMU"},"agent_actions":{"view_html":"https://pith.science/pith/LK672JMUJZO7UNJTSG2RVDCLYT","download_json":"https://pith.science/pith/LK672JMUJZO7UNJTSG2RVDCLYT.json","view_paper":"https://pith.science/paper/LK672JMU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.16867&json=true","fetch_graph":"https://pith.science/api/pith-number/LK672JMUJZO7UNJTSG2RVDCLYT/graph.json","fetch_events":"https://pith.science/api/pith-number/LK672JMUJZO7UNJTSG2RVDCLYT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LK672JMUJZO7UNJTSG2RVDCLYT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LK672JMUJZO7UNJTSG2RVDCLYT/action/storage_attestation","attest_author":"https://pith.science/pith/LK672JMUJZO7UNJTSG2RVDCLYT/action/author_attestation","sign_citation":"https://pith.science/pith/LK672JMUJZO7UNJTSG2RVDCLYT/action/citation_signature","submit_replication":"https://pith.science/pith/LK672JMUJZO7UNJTSG2RVDCLYT/action/replication_record"}},"created_at":"2026-07-05T05:47:42.969694+00:00","updated_at":"2026-07-05T05:47:42.969694+00:00"}