{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MXFJ72EOBDALX7WW56GS4YB2ET","short_pith_number":"pith:MXFJ72EO","schema_version":"1.0","canonical_sha256":"65ca9fe88e08c0bbfed6ef8d2e603a24f5c7cb5dc1f4d77a6ba790e45172071f","source":{"kind":"arxiv","id":"1801.07372","version":2},"attestation_state":"computed","paper":{"title":"Numerical Coordinate Regression with Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aiden Nibali, Luke Prendergast, Stuart Morgan, Zhen He","submitted_at":"2018-01-23T02:18:04Z","abstract_excerpt":"We study deep learning approaches to inferring numerical coordinates for points of interest in an input image. Existing convolutional neural network-based solutions to this problem either take a heatmap matching approach or regress to coordinates with a fully connected output layer. Neither of these approaches is ideal, since the former is not entirely differentiable, and the latter lacks inherent spatial generalization. We propose our differentiable spatial to numerical transform (DSNT) to fill this gap. The DSNT layer adds no trainable parameters, is fully differentiable, and exhibits good s"},"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":"1801.07372","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-23T02:18:04Z","cross_cats_sorted":[],"title_canon_sha256":"24084887b78963582c68e89cf107acf77d2bb50af937d66a563c7cf2d686cd96","abstract_canon_sha256":"3985def7469da2d876d236b78b9c3f5e277fcfd234eac1f56de71e74a90512f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:50.228156Z","signature_b64":"Xe3RtH4Qp3aCJZsxLt8Rt6OTkt9H63m7cl6LsMoSlxlYRc7YllHNhH8tB4k5rnqu03LHT0EXjjVN9AoCsEUtCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65ca9fe88e08c0bbfed6ef8d2e603a24f5c7cb5dc1f4d77a6ba790e45172071f","last_reissued_at":"2026-05-18T00:16:50.227504Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:50.227504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Numerical Coordinate Regression with Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aiden Nibali, Luke Prendergast, Stuart Morgan, Zhen He","submitted_at":"2018-01-23T02:18:04Z","abstract_excerpt":"We study deep learning approaches to inferring numerical coordinates for points of interest in an input image. Existing convolutional neural network-based solutions to this problem either take a heatmap matching approach or regress to coordinates with a fully connected output layer. Neither of these approaches is ideal, since the former is not entirely differentiable, and the latter lacks inherent spatial generalization. We propose our differentiable spatial to numerical transform (DSNT) to fill this gap. The DSNT layer adds no trainable parameters, is fully differentiable, and exhibits good s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.07372","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":""},"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":"1801.07372","created_at":"2026-05-18T00:16:50.227601+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.07372v2","created_at":"2026-05-18T00:16:50.227601+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.07372","created_at":"2026-05-18T00:16:50.227601+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXFJ72EOBDAL","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXFJ72EOBDALX7WW","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXFJ72EO","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06043","citing_title":"Domain Generalization through Spatial Relation Induction over Visual Primitives","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02912","citing_title":"Reasoning-Guided Grounding: Elevating Video Anomaly Detection through Multimodal Large Language Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18267","citing_title":"MARCO: Navigating the Unseen Space of Semantic Correspondence","ref_index":122,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MXFJ72EOBDALX7WW56GS4YB2ET","json":"https://pith.science/pith/MXFJ72EOBDALX7WW56GS4YB2ET.json","graph_json":"https://pith.science/api/pith-number/MXFJ72EOBDALX7WW56GS4YB2ET/graph.json","events_json":"https://pith.science/api/pith-number/MXFJ72EOBDALX7WW56GS4YB2ET/events.json","paper":"https://pith.science/paper/MXFJ72EO"},"agent_actions":{"view_html":"https://pith.science/pith/MXFJ72EOBDALX7WW56GS4YB2ET","download_json":"https://pith.science/pith/MXFJ72EOBDALX7WW56GS4YB2ET.json","view_paper":"https://pith.science/paper/MXFJ72EO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.07372&json=true","fetch_graph":"https://pith.science/api/pith-number/MXFJ72EOBDALX7WW56GS4YB2ET/graph.json","fetch_events":"https://pith.science/api/pith-number/MXFJ72EOBDALX7WW56GS4YB2ET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXFJ72EOBDALX7WW56GS4YB2ET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXFJ72EOBDALX7WW56GS4YB2ET/action/storage_attestation","attest_author":"https://pith.science/pith/MXFJ72EOBDALX7WW56GS4YB2ET/action/author_attestation","sign_citation":"https://pith.science/pith/MXFJ72EOBDALX7WW56GS4YB2ET/action/citation_signature","submit_replication":"https://pith.science/pith/MXFJ72EOBDALX7WW56GS4YB2ET/action/replication_record"}},"created_at":"2026-05-18T00:16:50.227601+00:00","updated_at":"2026-05-18T00:16:50.227601+00:00"}