{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:6EHMJWFY4ANYKDMA2E5MJGAII2","short_pith_number":"pith:6EHMJWFY","canonical_record":{"source":{"id":"1511.02683","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-09T14:02:03Z","cross_cats_sorted":[],"title_canon_sha256":"ec4c5dded342d35375e9647cedbcea34c04d9bb85692cb024e639dfd933d08a0","abstract_canon_sha256":"b70634d7c3a5d7badb9107d7e755fcdfd931c930f3eb70d603ab0221a81f2b10"},"schema_version":"1.0"},"canonical_sha256":"f10ec4d8b8e01b850d80d13ac4980846a28cee383def581605fe548d91b70adb","source":{"kind":"arxiv","id":"1511.02683","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.02683","created_at":"2026-05-18T00:08:24Z"},{"alias_kind":"arxiv_version","alias_value":"1511.02683v4","created_at":"2026-05-18T00:08:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.02683","created_at":"2026-05-18T00:08:24Z"},{"alias_kind":"pith_short_12","alias_value":"6EHMJWFY4ANY","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"6EHMJWFY4ANYKDMA","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"6EHMJWFY","created_at":"2026-05-18T12:29:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:6EHMJWFY4ANYKDMA2E5MJGAII2","target":"record","payload":{"canonical_record":{"source":{"id":"1511.02683","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-09T14:02:03Z","cross_cats_sorted":[],"title_canon_sha256":"ec4c5dded342d35375e9647cedbcea34c04d9bb85692cb024e639dfd933d08a0","abstract_canon_sha256":"b70634d7c3a5d7badb9107d7e755fcdfd931c930f3eb70d603ab0221a81f2b10"},"schema_version":"1.0"},"canonical_sha256":"f10ec4d8b8e01b850d80d13ac4980846a28cee383def581605fe548d91b70adb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:24.204645Z","signature_b64":"UvHjv/zQUManhu1TNBsCI4AixySrQ3HI7+3AZGEFe62f/4dMmuSzub17rVn512xVnhyUtxZv7tq/3JWE978BBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f10ec4d8b8e01b850d80d13ac4980846a28cee383def581605fe548d91b70adb","last_reissued_at":"2026-05-18T00:08:24.204109Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:24.204109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.02683","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:08:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tqkuGCYUvnH3Hicf2Crp2qEqqtefj0BaajsUFRf4ZAfTsqGCcGzEc/nZjjY5tSohHDbNNUZ7W2Z18RccqHnFDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:13:44.080996Z"},"content_sha256":"311572319dd83f7c8ec40a697f9a1b4a169d9ede562e1a12eaf23c5dc1ab9e9f","schema_version":"1.0","event_id":"sha256:311572319dd83f7c8ec40a697f9a1b4a169d9ede562e1a12eaf23c5dc1ab9e9f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:6EHMJWFY4ANYKDMA2E5MJGAII2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Light CNN for Deep Face Representation with Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ran He, Tieniu Tan, Xiang Wu, Zhenan Sun","submitted_at":"2015-11-09T14:02:03Z","abstract_excerpt":"The volume of convolutional neural network (CNN) models proposed for face recognition has been continuously growing larger to better fit large amount of training data. When training data are obtained from internet, the labels are likely to be ambiguous and inaccurate. This paper presents a Light CNN framework to learn a compact embedding on the large-scale face data with massive noisy labels. First, we introduce a variation of maxout activation, called Max-Feature-Map (MFM), into each convolutional layer of CNN. Different from maxout activation that uses many feature maps to linearly approxima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.02683","kind":"arxiv","version":4},"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":"2026-05-18T00:08:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H8MIUKQotNxVX1wGbLQRqgz98ib4Mo6nJvuFnHbnCi3uFR2nu0q4YnI52A0z2PugoahQgVZ/p6YT+ZJO2EFCDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:13:44.081349Z"},"content_sha256":"fe80aa76e0db0427e00f8fc5cda180d3443e2b9c93724dab5705ad4e45fcdaad","schema_version":"1.0","event_id":"sha256:fe80aa76e0db0427e00f8fc5cda180d3443e2b9c93724dab5705ad4e45fcdaad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6EHMJWFY4ANYKDMA2E5MJGAII2/bundle.json","state_url":"https://pith.science/pith/6EHMJWFY4ANYKDMA2E5MJGAII2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6EHMJWFY4ANYKDMA2E5MJGAII2/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":"2026-05-31T07:13:44Z","links":{"resolver":"https://pith.science/pith/6EHMJWFY4ANYKDMA2E5MJGAII2","bundle":"https://pith.science/pith/6EHMJWFY4ANYKDMA2E5MJGAII2/bundle.json","state":"https://pith.science/pith/6EHMJWFY4ANYKDMA2E5MJGAII2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6EHMJWFY4ANYKDMA2E5MJGAII2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:6EHMJWFY4ANYKDMA2E5MJGAII2","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":"b70634d7c3a5d7badb9107d7e755fcdfd931c930f3eb70d603ab0221a81f2b10","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-09T14:02:03Z","title_canon_sha256":"ec4c5dded342d35375e9647cedbcea34c04d9bb85692cb024e639dfd933d08a0"},"schema_version":"1.0","source":{"id":"1511.02683","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.02683","created_at":"2026-05-18T00:08:24Z"},{"alias_kind":"arxiv_version","alias_value":"1511.02683v4","created_at":"2026-05-18T00:08:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.02683","created_at":"2026-05-18T00:08:24Z"},{"alias_kind":"pith_short_12","alias_value":"6EHMJWFY4ANY","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"6EHMJWFY4ANYKDMA","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"6EHMJWFY","created_at":"2026-05-18T12:29:07Z"}],"graph_snapshots":[{"event_id":"sha256:fe80aa76e0db0427e00f8fc5cda180d3443e2b9c93724dab5705ad4e45fcdaad","target":"graph","created_at":"2026-05-18T00:08:24Z","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 volume of convolutional neural network (CNN) models proposed for face recognition has been continuously growing larger to better fit large amount of training data. When training data are obtained from internet, the labels are likely to be ambiguous and inaccurate. This paper presents a Light CNN framework to learn a compact embedding on the large-scale face data with massive noisy labels. First, we introduce a variation of maxout activation, called Max-Feature-Map (MFM), into each convolutional layer of CNN. Different from maxout activation that uses many feature maps to linearly approxima","authors_text":"Ran He, Tieniu Tan, Xiang Wu, Zhenan Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-09T14:02:03Z","title":"A Light CNN for Deep Face Representation with Noisy Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.02683","kind":"arxiv","version":4},"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":"sha256:311572319dd83f7c8ec40a697f9a1b4a169d9ede562e1a12eaf23c5dc1ab9e9f","target":"record","created_at":"2026-05-18T00:08:24Z","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":"b70634d7c3a5d7badb9107d7e755fcdfd931c930f3eb70d603ab0221a81f2b10","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-09T14:02:03Z","title_canon_sha256":"ec4c5dded342d35375e9647cedbcea34c04d9bb85692cb024e639dfd933d08a0"},"schema_version":"1.0","source":{"id":"1511.02683","kind":"arxiv","version":4}},"canonical_sha256":"f10ec4d8b8e01b850d80d13ac4980846a28cee383def581605fe548d91b70adb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f10ec4d8b8e01b850d80d13ac4980846a28cee383def581605fe548d91b70adb","first_computed_at":"2026-05-18T00:08:24.204109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:08:24.204109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UvHjv/zQUManhu1TNBsCI4AixySrQ3HI7+3AZGEFe62f/4dMmuSzub17rVn512xVnhyUtxZv7tq/3JWE978BBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:08:24.204645Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.02683","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:311572319dd83f7c8ec40a697f9a1b4a169d9ede562e1a12eaf23c5dc1ab9e9f","sha256:fe80aa76e0db0427e00f8fc5cda180d3443e2b9c93724dab5705ad4e45fcdaad"],"state_sha256":"24b4b0f61efc481dc0c537d0940d57735122d1caee7981fa9467bcf4165d80df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4rbJt7yDIDe8hM41E0NGzzIDs9yGYcl3uriQtkkI+AxddMOpHP4MKdLHTlnNuj+BLmDVGAXFqFnZkoyA4o79CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T07:13:44.083456Z","bundle_sha256":"27ecd96cb92f1345981e051f3f5397f0727d8bd046c083fc28bdfd0b1e5a1999"}}