{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:V5RIZGUYTOLFPMZZGAY7MLJTHG","short_pith_number":"pith:V5RIZGUY","canonical_record":{"source":{"id":"1808.04699","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-14T14:03:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b1b9f3163be72fe4d00637fa6ada8302429cccbca0a2c8554b18251b10b5857d","abstract_canon_sha256":"f9b4009abc7b0c3e20917a0908523a4f96e683b7ec2dd34a9643b244aa67d61c"},"schema_version":"1.0"},"canonical_sha256":"af628c9a989b9657b3393031f62d3339939bda122902b5b8b38a3665767b1e0a","source":{"kind":"arxiv","id":"1808.04699","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.04699","created_at":"2026-05-18T00:08:11Z"},{"alias_kind":"arxiv_version","alias_value":"1808.04699v1","created_at":"2026-05-18T00:08:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.04699","created_at":"2026-05-18T00:08:11Z"},{"alias_kind":"pith_short_12","alias_value":"V5RIZGUYTOLF","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"V5RIZGUYTOLFPMZZ","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"V5RIZGUY","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:V5RIZGUYTOLFPMZZGAY7MLJTHG","target":"record","payload":{"canonical_record":{"source":{"id":"1808.04699","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-14T14:03:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b1b9f3163be72fe4d00637fa6ada8302429cccbca0a2c8554b18251b10b5857d","abstract_canon_sha256":"f9b4009abc7b0c3e20917a0908523a4f96e683b7ec2dd34a9643b244aa67d61c"},"schema_version":"1.0"},"canonical_sha256":"af628c9a989b9657b3393031f62d3339939bda122902b5b8b38a3665767b1e0a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:11.884084Z","signature_b64":"CO57XcQ1cFJ795klCCe3HD5sy7PbcQdEo2IQMdZzQ8UtHgsHn3yPtViJmv9wiQFWrmiLKif3mXjwCrIRbsXKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af628c9a989b9657b3393031f62d3339939bda122902b5b8b38a3665767b1e0a","last_reissued_at":"2026-05-18T00:08:11.883551Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:11.883551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.04699","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":"2026-05-18T00:08:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vwETGRJgB13yAl3ar94z/gFCO5KOet12mNuRMopaeGwSKh5VJg5mmaYV2VOWNwmbfULTGZLSXShd7ovdwWoYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T12:33:42.631251Z"},"content_sha256":"f594070973f3544f43bb2fb41d6b3e5c643926cda12a6073448a41df6c2e8032","schema_version":"1.0","event_id":"sha256:f594070973f3544f43bb2fb41d6b3e5c643926cda12a6073448a41df6c2e8032"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:V5RIZGUYTOLFPMZZGAY7MLJTHG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Generalization via Scalable Neighborhood Component Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexei A. Efros, Stella X. Yu, Zhirong Wu","submitted_at":"2018-08-14T14:03:47Z","abstract_excerpt":"Current major approaches to visual recognition follow an end-to-end formulation that classifies an input image into one of the pre-determined set of semantic categories. Parametric softmax classifiers are a common choice for such a closed world with fixed categories, especially when big labeled data is available during training. However, this becomes problematic for open-set scenarios where new categories are encountered with very few examples for learning a generalizable parametric classifier. We adopt a non-parametric approach for visual recognition by optimizing feature embeddings instead o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.04699","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":"2026-05-18T00:08:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xpyy9GBNBMSXLP/mMw2EGIhv07banVeHTD+tFO1adgK7I9JlTV70MxwZDdxFHdRmBGUPFtZNtxFJsHaM2NutAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T12:33:42.631628Z"},"content_sha256":"606bf40391d5d88162353c9df3a42ef9c9d84e3b05d8ebca7ff4486b4baca4db","schema_version":"1.0","event_id":"sha256:606bf40391d5d88162353c9df3a42ef9c9d84e3b05d8ebca7ff4486b4baca4db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V5RIZGUYTOLFPMZZGAY7MLJTHG/bundle.json","state_url":"https://pith.science/pith/V5RIZGUYTOLFPMZZGAY7MLJTHG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V5RIZGUYTOLFPMZZGAY7MLJTHG/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":"2026-06-04T12:33:42Z","links":{"resolver":"https://pith.science/pith/V5RIZGUYTOLFPMZZGAY7MLJTHG","bundle":"https://pith.science/pith/V5RIZGUYTOLFPMZZGAY7MLJTHG/bundle.json","state":"https://pith.science/pith/V5RIZGUYTOLFPMZZGAY7MLJTHG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V5RIZGUYTOLFPMZZGAY7MLJTHG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:V5RIZGUYTOLFPMZZGAY7MLJTHG","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":"f9b4009abc7b0c3e20917a0908523a4f96e683b7ec2dd34a9643b244aa67d61c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-14T14:03:47Z","title_canon_sha256":"b1b9f3163be72fe4d00637fa6ada8302429cccbca0a2c8554b18251b10b5857d"},"schema_version":"1.0","source":{"id":"1808.04699","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.04699","created_at":"2026-05-18T00:08:11Z"},{"alias_kind":"arxiv_version","alias_value":"1808.04699v1","created_at":"2026-05-18T00:08:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.04699","created_at":"2026-05-18T00:08:11Z"},{"alias_kind":"pith_short_12","alias_value":"V5RIZGUYTOLF","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"V5RIZGUYTOLFPMZZ","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"V5RIZGUY","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:606bf40391d5d88162353c9df3a42ef9c9d84e3b05d8ebca7ff4486b4baca4db","target":"graph","created_at":"2026-05-18T00:08:11Z","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":"Current major approaches to visual recognition follow an end-to-end formulation that classifies an input image into one of the pre-determined set of semantic categories. Parametric softmax classifiers are a common choice for such a closed world with fixed categories, especially when big labeled data is available during training. However, this becomes problematic for open-set scenarios where new categories are encountered with very few examples for learning a generalizable parametric classifier. We adopt a non-parametric approach for visual recognition by optimizing feature embeddings instead o","authors_text":"Alexei A. Efros, Stella X. Yu, Zhirong Wu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-14T14:03:47Z","title":"Improving Generalization via Scalable Neighborhood Component Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.04699","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:f594070973f3544f43bb2fb41d6b3e5c643926cda12a6073448a41df6c2e8032","target":"record","created_at":"2026-05-18T00:08:11Z","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":"f9b4009abc7b0c3e20917a0908523a4f96e683b7ec2dd34a9643b244aa67d61c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-14T14:03:47Z","title_canon_sha256":"b1b9f3163be72fe4d00637fa6ada8302429cccbca0a2c8554b18251b10b5857d"},"schema_version":"1.0","source":{"id":"1808.04699","kind":"arxiv","version":1}},"canonical_sha256":"af628c9a989b9657b3393031f62d3339939bda122902b5b8b38a3665767b1e0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af628c9a989b9657b3393031f62d3339939bda122902b5b8b38a3665767b1e0a","first_computed_at":"2026-05-18T00:08:11.883551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:08:11.883551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CO57XcQ1cFJ795klCCe3HD5sy7PbcQdEo2IQMdZzQ8UtHgsHn3yPtViJmv9wiQFWrmiLKif3mXjwCrIRbsXKDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:08:11.884084Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.04699","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f594070973f3544f43bb2fb41d6b3e5c643926cda12a6073448a41df6c2e8032","sha256:606bf40391d5d88162353c9df3a42ef9c9d84e3b05d8ebca7ff4486b4baca4db"],"state_sha256":"1b1f307ed113392823a50ee4b4f404a91939ce0bf3ab6612980cbdc598a9fd4c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gyfu1kZvNt1yJsy2r+g/NgdSJFlj3mZmoNxMlr6ffaggHoxBL5btZtM+K8s6TBQigPx2CV0Tewhxq/uVVfMODg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T12:33:42.633714Z","bundle_sha256":"13836903a65189122d60aac090051949d2c6e283281f4e30c37ec99ecafecbe6"}}