{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AFBMDY24CVMHLXCSMAVRLDIBI7","short_pith_number":"pith:AFBMDY24","schema_version":"1.0","canonical_sha256":"0142c1e35c155875dc52602b158d0147d506d3ae4d9e399a0f85a05c87f9cf97","source":{"kind":"arxiv","id":"1905.10307","version":4},"attestation_state":"computed","paper":{"title":"An Explicitly Relational Neural Network Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Antonia Creswell, Christos Kaplanis, David Barrett, Kyriacos Nikiforou, Marta Garnelo, Murray Shanahan","submitted_at":"2019-05-24T16:03:06Z","abstract_excerpt":"With a view to bridging the gap between deep learning and symbolic AI, we present a novel end-to-end neural network architecture that learns to form propositional representations with an explicitly relational structure from raw pixel data. In order to evaluate and analyse the architecture, we introduce a family of simple visual relational reasoning tasks of varying complexity. We show that the proposed architecture, when pre-trained on a curriculum of such tasks, learns to generate reusable representations that better facilitate subsequent learning on previously unseen tasks when compared to a"},"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":"1905.10307","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T16:03:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"565efe2064b834d91fd2f5e2f3a2daaa595aa990981bb73f6b5d8e92fd57a016","abstract_canon_sha256":"9e59c3d8d7a979edd1c9dded14c7cca8038e4d3c0e42235fdbc733a271a445bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:12:19.544680Z","signature_b64":"iFFT8jsx5PXZEiHSSo5QRiPCGyqTNL8fmDQxZ6QSsiNcCnCjuByBarQVGhxXleG1M0Z0YHeQ5AUK6rBNwINjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0142c1e35c155875dc52602b158d0147d506d3ae4d9e399a0f85a05c87f9cf97","last_reissued_at":"2026-07-05T01:12:19.544283Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:12:19.544283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Explicitly Relational Neural Network Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Antonia Creswell, Christos Kaplanis, David Barrett, Kyriacos Nikiforou, Marta Garnelo, Murray Shanahan","submitted_at":"2019-05-24T16:03:06Z","abstract_excerpt":"With a view to bridging the gap between deep learning and symbolic AI, we present a novel end-to-end neural network architecture that learns to form propositional representations with an explicitly relational structure from raw pixel data. In order to evaluate and analyse the architecture, we introduce a family of simple visual relational reasoning tasks of varying complexity. We show that the proposed architecture, when pre-trained on a curriculum of such tasks, learns to generate reusable representations that better facilitate subsequent learning on previously unseen tasks when compared to a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10307","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/1905.10307/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":"1905.10307","created_at":"2026-07-05T01:12:19.544342+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.10307v4","created_at":"2026-07-05T01:12:19.544342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10307","created_at":"2026-07-05T01:12:19.544342+00:00"},{"alias_kind":"pith_short_12","alias_value":"AFBMDY24CVMH","created_at":"2026-07-05T01:12:19.544342+00:00"},{"alias_kind":"pith_short_16","alias_value":"AFBMDY24CVMHLXCS","created_at":"2026-07-05T01:12:19.544342+00:00"},{"alias_kind":"pith_short_8","alias_value":"AFBMDY24","created_at":"2026-07-05T01:12:19.544342+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/AFBMDY24CVMHLXCSMAVRLDIBI7","json":"https://pith.science/pith/AFBMDY24CVMHLXCSMAVRLDIBI7.json","graph_json":"https://pith.science/api/pith-number/AFBMDY24CVMHLXCSMAVRLDIBI7/graph.json","events_json":"https://pith.science/api/pith-number/AFBMDY24CVMHLXCSMAVRLDIBI7/events.json","paper":"https://pith.science/paper/AFBMDY24"},"agent_actions":{"view_html":"https://pith.science/pith/AFBMDY24CVMHLXCSMAVRLDIBI7","download_json":"https://pith.science/pith/AFBMDY24CVMHLXCSMAVRLDIBI7.json","view_paper":"https://pith.science/paper/AFBMDY24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.10307&json=true","fetch_graph":"https://pith.science/api/pith-number/AFBMDY24CVMHLXCSMAVRLDIBI7/graph.json","fetch_events":"https://pith.science/api/pith-number/AFBMDY24CVMHLXCSMAVRLDIBI7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AFBMDY24CVMHLXCSMAVRLDIBI7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AFBMDY24CVMHLXCSMAVRLDIBI7/action/storage_attestation","attest_author":"https://pith.science/pith/AFBMDY24CVMHLXCSMAVRLDIBI7/action/author_attestation","sign_citation":"https://pith.science/pith/AFBMDY24CVMHLXCSMAVRLDIBI7/action/citation_signature","submit_replication":"https://pith.science/pith/AFBMDY24CVMHLXCSMAVRLDIBI7/action/replication_record"}},"created_at":"2026-07-05T01:12:19.544342+00:00","updated_at":"2026-07-05T01:12:19.544342+00:00"}