{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:6SAG7JKGJ7UHOV4HR76QUUQCIT","short_pith_number":"pith:6SAG7JKG","canonical_record":{"source":{"id":"1409.6070","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-09-22T02:39:27Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"5db91fbbac5bcb86537d6d9ad0705a89ec6b69041308f8315d09f564ac094abf","abstract_canon_sha256":"b4b599cda3a1a4d07ed314ef9323b6ecc3f492b2fe8bc9cfcf9320012ae14f5a"},"schema_version":"1.0"},"canonical_sha256":"f4806fa5464fe87757878ffd0a520244df91ee72d78e7ca69b77400bfbb3cd85","source":{"kind":"arxiv","id":"1409.6070","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1409.6070","created_at":"2026-05-18T02:42:13Z"},{"alias_kind":"arxiv_version","alias_value":"1409.6070v1","created_at":"2026-05-18T02:42:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.6070","created_at":"2026-05-18T02:42:13Z"},{"alias_kind":"pith_short_12","alias_value":"6SAG7JKGJ7UH","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"6SAG7JKGJ7UHOV4H","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"6SAG7JKG","created_at":"2026-05-18T12:28:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:6SAG7JKGJ7UHOV4HR76QUUQCIT","target":"record","payload":{"canonical_record":{"source":{"id":"1409.6070","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-09-22T02:39:27Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"5db91fbbac5bcb86537d6d9ad0705a89ec6b69041308f8315d09f564ac094abf","abstract_canon_sha256":"b4b599cda3a1a4d07ed314ef9323b6ecc3f492b2fe8bc9cfcf9320012ae14f5a"},"schema_version":"1.0"},"canonical_sha256":"f4806fa5464fe87757878ffd0a520244df91ee72d78e7ca69b77400bfbb3cd85","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:42:13.820513Z","signature_b64":"ng7iFGFb9v3tN4VkJX6UtjTd5VaIX5ndsWfoMG1gJb4aUdPjIR1ylDLZb9flTVXXt7Cmlk9Ytg9q/Cjqu6IqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4806fa5464fe87757878ffd0a520244df91ee72d78e7ca69b77400bfbb3cd85","last_reissued_at":"2026-05-18T02:42:13.820134Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:42:13.820134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1409.6070","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:42:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3DbznRYTaHgqBTq/0VwBhRwSa9jQBZYhswn4z/tZ5nk+V9KnF+GJEAfYUN3kWol/K5R1la6Z0jqIpIbJiGf8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T20:15:29.529137Z"},"content_sha256":"f5f5b64bf1de723fd85ccd4c1b400a02861f433c0053434029532a27d8c4cfbc","schema_version":"1.0","event_id":"sha256:f5f5b64bf1de723fd85ccd4c1b400a02861f433c0053434029532a27d8c4cfbc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:6SAG7JKGJ7UHOV4HR76QUUQCIT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spatially-sparse convolutional neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CV","authors_text":"Benjamin Graham","submitted_at":"2014-09-22T02:39:27Z","abstract_excerpt":"Convolutional neural networks (CNNs) perform well on problems such as handwriting recognition and image classification. However, the performance of the networks is often limited by budget and time constraints, particularly when trying to train deep networks.\n  Motivated by the problem of online handwriting recognition, we developed a CNN for processing spatially-sparse inputs; a character drawn with a one-pixel wide pen on a high resolution grid looks like a sparse matrix. Taking advantage of the sparsity allowed us more efficiently to train and test large, deep CNNs. On the CASIA-OLHWDB1.1 da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.6070","kind":"arxiv","version":1},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:42:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v9pJNZt0oAcM97ENKMZze+3HtL+xGReJz5MW4Y6I9c/4WNYv370zjBgfK5kD2bixEagVsAx0DGWzsOlJBP6sCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T20:15:29.529678Z"},"content_sha256":"b9d50bfe4098823078b52345db17731051c14ee37ea44c901fa65a54f4051eee","schema_version":"1.0","event_id":"sha256:b9d50bfe4098823078b52345db17731051c14ee37ea44c901fa65a54f4051eee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6SAG7JKGJ7UHOV4HR76QUUQCIT/bundle.json","state_url":"https://pith.science/pith/6SAG7JKGJ7UHOV4HR76QUUQCIT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6SAG7JKGJ7UHOV4HR76QUUQCIT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T20:15:29Z","links":{"resolver":"https://pith.science/pith/6SAG7JKGJ7UHOV4HR76QUUQCIT","bundle":"https://pith.science/pith/6SAG7JKGJ7UHOV4HR76QUUQCIT/bundle.json","state":"https://pith.science/pith/6SAG7JKGJ7UHOV4HR76QUUQCIT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6SAG7JKGJ7UHOV4HR76QUUQCIT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:6SAG7JKGJ7UHOV4HR76QUUQCIT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b4b599cda3a1a4d07ed314ef9323b6ecc3f492b2fe8bc9cfcf9320012ae14f5a","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-09-22T02:39:27Z","title_canon_sha256":"5db91fbbac5bcb86537d6d9ad0705a89ec6b69041308f8315d09f564ac094abf"},"schema_version":"1.0","source":{"id":"1409.6070","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1409.6070","created_at":"2026-05-18T02:42:13Z"},{"alias_kind":"arxiv_version","alias_value":"1409.6070v1","created_at":"2026-05-18T02:42:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.6070","created_at":"2026-05-18T02:42:13Z"},{"alias_kind":"pith_short_12","alias_value":"6SAG7JKGJ7UH","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"6SAG7JKGJ7UHOV4H","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"6SAG7JKG","created_at":"2026-05-18T12:28:16Z"}],"graph_snapshots":[{"event_id":"sha256:b9d50bfe4098823078b52345db17731051c14ee37ea44c901fa65a54f4051eee","target":"graph","created_at":"2026-05-18T02:42:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Convolutional neural networks (CNNs) perform well on problems such as handwriting recognition and image classification. However, the performance of the networks is often limited by budget and time constraints, particularly when trying to train deep networks.\n  Motivated by the problem of online handwriting recognition, we developed a CNN for processing spatially-sparse inputs; a character drawn with a one-pixel wide pen on a high resolution grid looks like a sparse matrix. Taking advantage of the sparsity allowed us more efficiently to train and test large, deep CNNs. On the CASIA-OLHWDB1.1 da","authors_text":"Benjamin Graham","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-09-22T02:39:27Z","title":"Spatially-sparse convolutional neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.6070","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f5f5b64bf1de723fd85ccd4c1b400a02861f433c0053434029532a27d8c4cfbc","target":"record","created_at":"2026-05-18T02:42:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b4b599cda3a1a4d07ed314ef9323b6ecc3f492b2fe8bc9cfcf9320012ae14f5a","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-09-22T02:39:27Z","title_canon_sha256":"5db91fbbac5bcb86537d6d9ad0705a89ec6b69041308f8315d09f564ac094abf"},"schema_version":"1.0","source":{"id":"1409.6070","kind":"arxiv","version":1}},"canonical_sha256":"f4806fa5464fe87757878ffd0a520244df91ee72d78e7ca69b77400bfbb3cd85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4806fa5464fe87757878ffd0a520244df91ee72d78e7ca69b77400bfbb3cd85","first_computed_at":"2026-05-18T02:42:13.820134Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:42:13.820134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ng7iFGFb9v3tN4VkJX6UtjTd5VaIX5ndsWfoMG1gJb4aUdPjIR1ylDLZb9flTVXXt7Cmlk9Ytg9q/Cjqu6IqAA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:42:13.820513Z","signed_message":"canonical_sha256_bytes"},"source_id":"1409.6070","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5f5b64bf1de723fd85ccd4c1b400a02861f433c0053434029532a27d8c4cfbc","sha256:b9d50bfe4098823078b52345db17731051c14ee37ea44c901fa65a54f4051eee"],"state_sha256":"bd1973433c7508232805bc86fb5cfada72cd4f1f6c62f961a86f70d299034cbb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5WTiZwLzsGXs1IgNAOeNIQE5z9Qa7YiFugyiQgZU8GU/xP0fSXB3TWQSRuEfDs6h95zDlIhHnpLjZbp3h/9pAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T20:15:29.533044Z","bundle_sha256":"359c4d4cda6f090e4608a942577b58d8986ec24c5a64852d3c804c7503016b7d"}}