{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:T5FAS7ACVJSY2JRI64GSGEA5IU","short_pith_number":"pith:T5FAS7AC","schema_version":"1.0","canonical_sha256":"9f4a097c02aa658d2628f70d23101d4504c690bca4ff98a1e3661bdea50f8b94","source":{"kind":"arxiv","id":"1802.03390","version":3},"attestation_state":"computed","paper":{"title":"Same-different problems strain convolutional neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.NC"],"primary_cat":"cs.CV","authors_text":"Junkyung Kim, Matthew Ricci, Thomas Serre","submitted_at":"2018-02-09T18:55:34Z","abstract_excerpt":"The robust and efficient recognition of visual relations in images is a hallmark of biological vision. We argue that, despite recent progress in visual recognition, modern machine vision algorithms are severely limited in their ability to learn visual relations. Through controlled experiments, we demonstrate that visual-relation problems strain convolutional neural networks (CNNs). The networks eventually break altogether when rote memorization becomes impossible, as when intra-class variability exceeds network capacity. Motivated by the comparable success of biological vision, we argue that f"},"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":"1802.03390","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-09T18:55:34Z","cross_cats_sorted":["cs.AI","cs.LG","q-bio.NC"],"title_canon_sha256":"d14d90444b72c646f37c110c112e3477f16fc9c6975398824af241450e28695d","abstract_canon_sha256":"dd147c8e7c3cc65818b6521379c4c5f293e9aba1039bb8dc8b20a4240e6f1341"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:59.515468Z","signature_b64":"xB+JamuIeEO0O/mdT1kbcm+zHrcPAZGthx/4NIsUEoCY9KZePoVHOZJ0BCGqNH16NL9jC20m4gF1V4bBY0jnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f4a097c02aa658d2628f70d23101d4504c690bca4ff98a1e3661bdea50f8b94","last_reissued_at":"2026-05-18T00:14:59.514659Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:59.514659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Same-different problems strain convolutional neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.NC"],"primary_cat":"cs.CV","authors_text":"Junkyung Kim, Matthew Ricci, Thomas Serre","submitted_at":"2018-02-09T18:55:34Z","abstract_excerpt":"The robust and efficient recognition of visual relations in images is a hallmark of biological vision. We argue that, despite recent progress in visual recognition, modern machine vision algorithms are severely limited in their ability to learn visual relations. Through controlled experiments, we demonstrate that visual-relation problems strain convolutional neural networks (CNNs). The networks eventually break altogether when rote memorization becomes impossible, as when intra-class variability exceeds network capacity. Motivated by the comparable success of biological vision, we argue that f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03390","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1802.03390","created_at":"2026-05-18T00:14:59.514795+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.03390v3","created_at":"2026-05-18T00:14:59.514795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03390","created_at":"2026-05-18T00:14:59.514795+00:00"},{"alias_kind":"pith_short_12","alias_value":"T5FAS7ACVJSY","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"T5FAS7ACVJSY2JRI","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"T5FAS7AC","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.08290","citing_title":"RESOLVE: Relational Reasoning with Symbolic and Object-Level Features Using Vector Symbolic Processing","ref_index":1938,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T5FAS7ACVJSY2JRI64GSGEA5IU","json":"https://pith.science/pith/T5FAS7ACVJSY2JRI64GSGEA5IU.json","graph_json":"https://pith.science/api/pith-number/T5FAS7ACVJSY2JRI64GSGEA5IU/graph.json","events_json":"https://pith.science/api/pith-number/T5FAS7ACVJSY2JRI64GSGEA5IU/events.json","paper":"https://pith.science/paper/T5FAS7AC"},"agent_actions":{"view_html":"https://pith.science/pith/T5FAS7ACVJSY2JRI64GSGEA5IU","download_json":"https://pith.science/pith/T5FAS7ACVJSY2JRI64GSGEA5IU.json","view_paper":"https://pith.science/paper/T5FAS7AC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.03390&json=true","fetch_graph":"https://pith.science/api/pith-number/T5FAS7ACVJSY2JRI64GSGEA5IU/graph.json","fetch_events":"https://pith.science/api/pith-number/T5FAS7ACVJSY2JRI64GSGEA5IU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T5FAS7ACVJSY2JRI64GSGEA5IU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T5FAS7ACVJSY2JRI64GSGEA5IU/action/storage_attestation","attest_author":"https://pith.science/pith/T5FAS7ACVJSY2JRI64GSGEA5IU/action/author_attestation","sign_citation":"https://pith.science/pith/T5FAS7ACVJSY2JRI64GSGEA5IU/action/citation_signature","submit_replication":"https://pith.science/pith/T5FAS7ACVJSY2JRI64GSGEA5IU/action/replication_record"}},"created_at":"2026-05-18T00:14:59.514795+00:00","updated_at":"2026-05-18T00:14:59.514795+00:00"}