{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7RJGSCNFPTLMHAKOFABMH5JA2U","short_pith_number":"pith:7RJGSCNF","canonical_record":{"source":{"id":"1802.07595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-21T14:54:43Z","cross_cats_sorted":[],"title_canon_sha256":"3aee514bd0ae7bd98305ca9f0857c396a6c697eedc073139f48c317cfcddf391","abstract_canon_sha256":"52d30d36cb953769b326972d6ee385e105a1dfa34417ca90b0b2beb10de2f530"},"schema_version":"1.0"},"canonical_sha256":"fc526909a57cd6c3814e2802c3f520d50fb283c39ca0dbe4dff6cfe92b39a228","source":{"kind":"arxiv","id":"1802.07595","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07595","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07595v1","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07595","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"7RJGSCNFPTLM","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7RJGSCNFPTLMHAKO","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7RJGSCNF","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7RJGSCNFPTLMHAKOFABMH5JA2U","target":"record","payload":{"canonical_record":{"source":{"id":"1802.07595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-21T14:54:43Z","cross_cats_sorted":[],"title_canon_sha256":"3aee514bd0ae7bd98305ca9f0857c396a6c697eedc073139f48c317cfcddf391","abstract_canon_sha256":"52d30d36cb953769b326972d6ee385e105a1dfa34417ca90b0b2beb10de2f530"},"schema_version":"1.0"},"canonical_sha256":"fc526909a57cd6c3814e2802c3f520d50fb283c39ca0dbe4dff6cfe92b39a228","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:49.838815Z","signature_b64":"RG+B+Xe6N8fISwXZxfi1pjWVBc1hAX4KRgoEKrOhG98vToO/C2T7T8indmvNjRZUlXry0ZlZg4DB9/7tMdQeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc526909a57cd6c3814e2802c3f520d50fb283c39ca0dbe4dff6cfe92b39a228","last_reissued_at":"2026-05-18T00:22:49.838343Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:49.838343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.07595","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":"2026-05-18T00:22:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lAMPSjuV8g6oZHh91S9zU+28re+QVVu0moR3jYLL5530ZjCdVyaR4v6l7PtUDulXjUvQJ+/fjSJtND7jgZrICA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T06:17:19.528933Z"},"content_sha256":"a16e26e6d4284c077181cea6ef18f0944e94993eb2cf7d35038bf1be7fda27a8","schema_version":"1.0","event_id":"sha256:a16e26e6d4284c077181cea6ef18f0944e94993eb2cf7d35038bf1be7fda27a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7RJGSCNFPTLMHAKOFABMH5JA2U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Smooth Loss Functions for Deep Top-k Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew Zisserman, Leonard Berrada, M. Pawan Kumar","submitted_at":"2018-02-21T14:54:43Z","abstract_excerpt":"The top-k error is a common measure of performance in machine learning and computer vision. In practice, top-k classification is typically performed with deep neural networks trained with the cross-entropy loss. Theoretical results indeed suggest that cross-entropy is an optimal learning objective for such a task in the limit of infinite data. In the context of limited and noisy data however, the use of a loss function that is specifically designed for top-k classification can bring significant improvements. Our empirical evidence suggests that the loss function must be smooth and have non-spa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07595","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":"2026-05-18T00:22:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V4uty7E/6zOPs7afmYijjOvrJrJMpJuhmHixQ+DvIi2q7SnzkQ/TOgFQADiOifgs8zd51GpEYKKshn5aOoPXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T06:17:19.529279Z"},"content_sha256":"46f57f83d08e7e294f54144f5ae08c7ebacd0d38397aa04e72aaae0766574c8f","schema_version":"1.0","event_id":"sha256:46f57f83d08e7e294f54144f5ae08c7ebacd0d38397aa04e72aaae0766574c8f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7RJGSCNFPTLMHAKOFABMH5JA2U/bundle.json","state_url":"https://pith.science/pith/7RJGSCNFPTLMHAKOFABMH5JA2U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7RJGSCNFPTLMHAKOFABMH5JA2U/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":"2026-06-01T06:17:19Z","links":{"resolver":"https://pith.science/pith/7RJGSCNFPTLMHAKOFABMH5JA2U","bundle":"https://pith.science/pith/7RJGSCNFPTLMHAKOFABMH5JA2U/bundle.json","state":"https://pith.science/pith/7RJGSCNFPTLMHAKOFABMH5JA2U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7RJGSCNFPTLMHAKOFABMH5JA2U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7RJGSCNFPTLMHAKOFABMH5JA2U","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":"52d30d36cb953769b326972d6ee385e105a1dfa34417ca90b0b2beb10de2f530","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-21T14:54:43Z","title_canon_sha256":"3aee514bd0ae7bd98305ca9f0857c396a6c697eedc073139f48c317cfcddf391"},"schema_version":"1.0","source":{"id":"1802.07595","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07595","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07595v1","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07595","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"7RJGSCNFPTLM","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7RJGSCNFPTLMHAKO","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7RJGSCNF","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:46f57f83d08e7e294f54144f5ae08c7ebacd0d38397aa04e72aaae0766574c8f","target":"graph","created_at":"2026-05-18T00:22:49Z","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":"The top-k error is a common measure of performance in machine learning and computer vision. In practice, top-k classification is typically performed with deep neural networks trained with the cross-entropy loss. Theoretical results indeed suggest that cross-entropy is an optimal learning objective for such a task in the limit of infinite data. In the context of limited and noisy data however, the use of a loss function that is specifically designed for top-k classification can bring significant improvements. Our empirical evidence suggests that the loss function must be smooth and have non-spa","authors_text":"Andrew Zisserman, Leonard Berrada, M. Pawan Kumar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-21T14:54:43Z","title":"Smooth Loss Functions for Deep Top-k Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07595","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:a16e26e6d4284c077181cea6ef18f0944e94993eb2cf7d35038bf1be7fda27a8","target":"record","created_at":"2026-05-18T00:22:49Z","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":"52d30d36cb953769b326972d6ee385e105a1dfa34417ca90b0b2beb10de2f530","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-21T14:54:43Z","title_canon_sha256":"3aee514bd0ae7bd98305ca9f0857c396a6c697eedc073139f48c317cfcddf391"},"schema_version":"1.0","source":{"id":"1802.07595","kind":"arxiv","version":1}},"canonical_sha256":"fc526909a57cd6c3814e2802c3f520d50fb283c39ca0dbe4dff6cfe92b39a228","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc526909a57cd6c3814e2802c3f520d50fb283c39ca0dbe4dff6cfe92b39a228","first_computed_at":"2026-05-18T00:22:49.838343Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:49.838343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RG+B+Xe6N8fISwXZxfi1pjWVBc1hAX4KRgoEKrOhG98vToO/C2T7T8indmvNjRZUlXry0ZlZg4DB9/7tMdQeBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:49.838815Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.07595","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a16e26e6d4284c077181cea6ef18f0944e94993eb2cf7d35038bf1be7fda27a8","sha256:46f57f83d08e7e294f54144f5ae08c7ebacd0d38397aa04e72aaae0766574c8f"],"state_sha256":"5d7317940efa400d7aed662145530381048e1af81d1d061597ee18a1001e3c7a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x59fQEX1ydF4dj44Gn654IyXvXyF9s73zJdU41rAXEi6wsC0lfi9lGEdABKX32oHfN+PCbH2wHHOjY+AwMRtBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T06:17:19.531188Z","bundle_sha256":"5b8cf28ec382095310ebe49fd28a6f894acf2bd5e16367382b84e1c21d151085"}}