{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CRCO3R7SSS4MTFLPLXK7ZRAQAL","short_pith_number":"pith:CRCO3R7S","canonical_record":{"source":{"id":"2211.11355","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-21T11:17:07Z","cross_cats_sorted":[],"title_canon_sha256":"aa46268e32e7d6a7dee6b25c533052bb468b35fa2131d0e72090df01dd751a7a","abstract_canon_sha256":"ab8506c0cbcbd50170a9f0a69ee960fe62c2d6bed26360f7f7c93d1610d90b7b"},"schema_version":"1.0"},"canonical_sha256":"1444edc7f294b8c9956f5dd5fcc41002e8ba4ab492034eb62e2e4289ad2aea9b","source":{"kind":"arxiv","id":"2211.11355","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.11355","created_at":"2026-07-05T06:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2211.11355v1","created_at":"2026-07-05T06:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11355","created_at":"2026-07-05T06:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"CRCO3R7SSS4M","created_at":"2026-07-05T06:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"CRCO3R7SSS4MTFLP","created_at":"2026-07-05T06:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"CRCO3R7S","created_at":"2026-07-05T06:04:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CRCO3R7SSS4MTFLPLXK7ZRAQAL","target":"record","payload":{"canonical_record":{"source":{"id":"2211.11355","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-21T11:17:07Z","cross_cats_sorted":[],"title_canon_sha256":"aa46268e32e7d6a7dee6b25c533052bb468b35fa2131d0e72090df01dd751a7a","abstract_canon_sha256":"ab8506c0cbcbd50170a9f0a69ee960fe62c2d6bed26360f7f7c93d1610d90b7b"},"schema_version":"1.0"},"canonical_sha256":"1444edc7f294b8c9956f5dd5fcc41002e8ba4ab492034eb62e2e4289ad2aea9b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:35.392238Z","signature_b64":"G26IDckY0yxzQVyNWS23BzB1V524pf+XDKVOMN1dmm3dZeVI8DhG4DxbJ4ptAP2HdUc56ISGSkBOIfI+UqFNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1444edc7f294b8c9956f5dd5fcc41002e8ba4ab492034eb62e2e4289ad2aea9b","last_reissued_at":"2026-07-05T06:04:35.391779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:35.391779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.11355","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":"2026-07-05T06:04:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gmgHmj1vQVscsotBALGQsqiN7EwOf7M4q3QINkF8RbgoxgeB2NGr34lI7crKLMpzWYY+P8y4vavmWCfIh2HXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T22:12:44.265947Z"},"content_sha256":"ca5b1747f4309046bcd0efa8c1c32b9b4ca9c537a1136cdabc60ef3e7aa1a146","schema_version":"1.0","event_id":"sha256:ca5b1747f4309046bcd0efa8c1c32b9b4ca9c537a1136cdabc60ef3e7aa1a146"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CRCO3R7SSS4MTFLPLXK7ZRAQAL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Blind Knowledge Distillation for Robust Image Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bodo Rosenhahn, Christoph Reinders, Lukas Ehmann, Timo Kaiser","submitted_at":"2022-11-21T11:17:07Z","abstract_excerpt":"Optimizing neural networks with noisy labels is a challenging task, especially if the label set contains real-world noise. Networks tend to generalize to reasonable patterns in the early training stages and overfit to specific details of noisy samples in the latter ones. We introduce Blind Knowledge Distillation - a novel teacher-student approach for learning with noisy labels by masking the ground truth related teacher output to filter out potentially corrupted knowledge and to estimate the tipping point from generalizing to overfitting. Based on this, we enable the estimation of noise in the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11355","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.11355/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T06:04:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p5TXpSPiBFQfLr+QWc7C+sR4KQekXpviejyOyeEEc5GqK6IFSM45xFXjQG+jO+TQOjuNXHMSot3ygDusegmCCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T22:12:44.266337Z"},"content_sha256":"70c7570f8a946de91205e44da73a5513dab42d60cb6e291295fcfca6a68029cb","schema_version":"1.0","event_id":"sha256:70c7570f8a946de91205e44da73a5513dab42d60cb6e291295fcfca6a68029cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CRCO3R7SSS4MTFLPLXK7ZRAQAL/bundle.json","state_url":"https://pith.science/pith/CRCO3R7SSS4MTFLPLXK7ZRAQAL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CRCO3R7SSS4MTFLPLXK7ZRAQAL/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":"2026-07-08T22:12:44Z","links":{"resolver":"https://pith.science/pith/CRCO3R7SSS4MTFLPLXK7ZRAQAL","bundle":"https://pith.science/pith/CRCO3R7SSS4MTFLPLXK7ZRAQAL/bundle.json","state":"https://pith.science/pith/CRCO3R7SSS4MTFLPLXK7ZRAQAL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CRCO3R7SSS4MTFLPLXK7ZRAQAL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CRCO3R7SSS4MTFLPLXK7ZRAQAL","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":"ab8506c0cbcbd50170a9f0a69ee960fe62c2d6bed26360f7f7c93d1610d90b7b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-21T11:17:07Z","title_canon_sha256":"aa46268e32e7d6a7dee6b25c533052bb468b35fa2131d0e72090df01dd751a7a"},"schema_version":"1.0","source":{"id":"2211.11355","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.11355","created_at":"2026-07-05T06:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2211.11355v1","created_at":"2026-07-05T06:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11355","created_at":"2026-07-05T06:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"CRCO3R7SSS4M","created_at":"2026-07-05T06:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"CRCO3R7SSS4MTFLP","created_at":"2026-07-05T06:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"CRCO3R7S","created_at":"2026-07-05T06:04:35Z"}],"graph_snapshots":[{"event_id":"sha256:70c7570f8a946de91205e44da73a5513dab42d60cb6e291295fcfca6a68029cb","target":"graph","created_at":"2026-07-05T06:04:35Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2211.11355/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimizing neural networks with noisy labels is a challenging task, especially if the label set contains real-world noise. Networks tend to generalize to reasonable patterns in the early training stages and overfit to specific details of noisy samples in the latter ones. We introduce Blind Knowledge Distillation - a novel teacher-student approach for learning with noisy labels by masking the ground truth related teacher output to filter out potentially corrupted knowledge and to estimate the tipping point from generalizing to overfitting. Based on this, we enable the estimation of noise in the","authors_text":"Bodo Rosenhahn, Christoph Reinders, Lukas Ehmann, Timo Kaiser","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-21T11:17:07Z","title":"Blind Knowledge Distillation for Robust Image Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11355","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:ca5b1747f4309046bcd0efa8c1c32b9b4ca9c537a1136cdabc60ef3e7aa1a146","target":"record","created_at":"2026-07-05T06:04:35Z","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":"ab8506c0cbcbd50170a9f0a69ee960fe62c2d6bed26360f7f7c93d1610d90b7b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-21T11:17:07Z","title_canon_sha256":"aa46268e32e7d6a7dee6b25c533052bb468b35fa2131d0e72090df01dd751a7a"},"schema_version":"1.0","source":{"id":"2211.11355","kind":"arxiv","version":1}},"canonical_sha256":"1444edc7f294b8c9956f5dd5fcc41002e8ba4ab492034eb62e2e4289ad2aea9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1444edc7f294b8c9956f5dd5fcc41002e8ba4ab492034eb62e2e4289ad2aea9b","first_computed_at":"2026-07-05T06:04:35.391779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:04:35.391779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G26IDckY0yxzQVyNWS23BzB1V524pf+XDKVOMN1dmm3dZeVI8DhG4DxbJ4ptAP2HdUc56ISGSkBOIfI+UqFNAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:04:35.392238Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.11355","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca5b1747f4309046bcd0efa8c1c32b9b4ca9c537a1136cdabc60ef3e7aa1a146","sha256:70c7570f8a946de91205e44da73a5513dab42d60cb6e291295fcfca6a68029cb"],"state_sha256":"d59ed7b5dd3f3eb1d5b846f3a1fd9ad6e39603b49a8969a6c542298e24269976"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CZhQ96wnkwRcYmJnojbWQAwF85EIkNb81sbkaHZ6zhK8uauaL75KGwRFax8sfCbMRgaSNYHkARbVEcWJOLU4Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T22:12:44.268441Z","bundle_sha256":"68fcf8247466b74185fb6ffe1843260f2d7bae59e05f580c975d71e39d157a16"}}