{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:2CXUM4D2SR46WETUUOKWHUKB3N","short_pith_number":"pith:2CXUM4D2","canonical_record":{"source":{"id":"1905.12931","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2019-05-30T09:47:11Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"77438516956aee49458436b799af014fba517d373a399cab05bf2859fa72980b","abstract_canon_sha256":"4e540467b528441e10823d5861a092e10f85eb23af30c9b09e4932e5490da1a8"},"schema_version":"1.0"},"canonical_sha256":"d0af46707a9479eb1274a39563d141db79bb79c19652ae0759ca8a1327fb142b","source":{"kind":"arxiv","id":"1905.12931","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.12931","created_at":"2026-05-17T23:40:17Z"},{"alias_kind":"arxiv_version","alias_value":"1905.12931v2","created_at":"2026-05-17T23:40:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12931","created_at":"2026-05-17T23:40:17Z"},{"alias_kind":"pith_short_12","alias_value":"2CXUM4D2SR46","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2CXUM4D2SR46WETU","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2CXUM4D2","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:2CXUM4D2SR46WETUUOKWHUKB3N","target":"record","payload":{"canonical_record":{"source":{"id":"1905.12931","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2019-05-30T09:47:11Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"77438516956aee49458436b799af014fba517d373a399cab05bf2859fa72980b","abstract_canon_sha256":"4e540467b528441e10823d5861a092e10f85eb23af30c9b09e4932e5490da1a8"},"schema_version":"1.0"},"canonical_sha256":"d0af46707a9479eb1274a39563d141db79bb79c19652ae0759ca8a1327fb142b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:17.102685Z","signature_b64":"/YV3k+sfJPVsy0vs8mnatIzQ76dXotpHLfLGCW2IRen4LhCNDQmD0lD7wQtn9zMI+6ZlkLuVr4PG7vx4tFxVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0af46707a9479eb1274a39563d141db79bb79c19652ae0759ca8a1327fb142b","last_reissued_at":"2026-05-17T23:40:17.100890Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:17.100890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.12931","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:40:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FvGhiwgIxO09Kli3aTWri3IeWUHfImu1rJg2qRWk19vJBy1dwZGusXVfADPfCoQkBsiyjIMGT7A91SrLTTz5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T16:37:31.684852Z"},"content_sha256":"f5f89dffb3e7dc870847904f14ba163c211f9f742942ec39c82ca9c6f399a3af","schema_version":"1.0","event_id":"sha256:f5f89dffb3e7dc870847904f14ba163c211f9f742942ec39c82ca9c6f399a3af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:2CXUM4D2SR46WETUUOKWHUKB3N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Weakly supervised training of pixel resolution segmentation models on whole slide images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"eess.IV","authors_text":"Nicolas Pinchaud","submitted_at":"2019-05-30T09:47:11Z","abstract_excerpt":"We present a novel approach to train pixel resolution segmentation models on whole slide images in a weakly supervised setup. The model is trained to classify patches extracted from slides. This leads the training to be made under noisy labeled data. We solve the problem with two complementary strategies. First, the patches are sampled online using the model's knowledge by focusing on regions where the model's confidence is higher. Second, we propose an extension of the KL divergence that is robust to noisy labels. Our preliminary experiment on CAMELYON 16 data set show promising results. The "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12931","kind":"arxiv","version":2},"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":"2026-05-17T23:40:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kuA33R+94O/GtTVzNBLW5xAmTy8qO+fLOx9vVRSW6uAhNsfwKmAdFmVQPdJEegakoVQuP7lZUh6TVS4JbJBMDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T16:37:31.685195Z"},"content_sha256":"4c492a0025b127760bffa4cc7908d0249892b061d0aee6e6a7c355ddb4913b1b","schema_version":"1.0","event_id":"sha256:4c492a0025b127760bffa4cc7908d0249892b061d0aee6e6a7c355ddb4913b1b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2CXUM4D2SR46WETUUOKWHUKB3N/bundle.json","state_url":"https://pith.science/pith/2CXUM4D2SR46WETUUOKWHUKB3N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2CXUM4D2SR46WETUUOKWHUKB3N/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":"2026-06-03T16:37:31Z","links":{"resolver":"https://pith.science/pith/2CXUM4D2SR46WETUUOKWHUKB3N","bundle":"https://pith.science/pith/2CXUM4D2SR46WETUUOKWHUKB3N/bundle.json","state":"https://pith.science/pith/2CXUM4D2SR46WETUUOKWHUKB3N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2CXUM4D2SR46WETUUOKWHUKB3N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:2CXUM4D2SR46WETUUOKWHUKB3N","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":"4e540467b528441e10823d5861a092e10f85eb23af30c9b09e4932e5490da1a8","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2019-05-30T09:47:11Z","title_canon_sha256":"77438516956aee49458436b799af014fba517d373a399cab05bf2859fa72980b"},"schema_version":"1.0","source":{"id":"1905.12931","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.12931","created_at":"2026-05-17T23:40:17Z"},{"alias_kind":"arxiv_version","alias_value":"1905.12931v2","created_at":"2026-05-17T23:40:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12931","created_at":"2026-05-17T23:40:17Z"},{"alias_kind":"pith_short_12","alias_value":"2CXUM4D2SR46","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2CXUM4D2SR46WETU","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2CXUM4D2","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:4c492a0025b127760bffa4cc7908d0249892b061d0aee6e6a7c355ddb4913b1b","target":"graph","created_at":"2026-05-17T23:40:17Z","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":"We present a novel approach to train pixel resolution segmentation models on whole slide images in a weakly supervised setup. The model is trained to classify patches extracted from slides. This leads the training to be made under noisy labeled data. We solve the problem with two complementary strategies. First, the patches are sampled online using the model's knowledge by focusing on regions where the model's confidence is higher. Second, we propose an extension of the KL divergence that is robust to noisy labels. Our preliminary experiment on CAMELYON 16 data set show promising results. The ","authors_text":"Nicolas Pinchaud","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2019-05-30T09:47:11Z","title":"Weakly supervised training of pixel resolution segmentation models on whole slide images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12931","kind":"arxiv","version":2},"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:f5f89dffb3e7dc870847904f14ba163c211f9f742942ec39c82ca9c6f399a3af","target":"record","created_at":"2026-05-17T23:40:17Z","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":"4e540467b528441e10823d5861a092e10f85eb23af30c9b09e4932e5490da1a8","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2019-05-30T09:47:11Z","title_canon_sha256":"77438516956aee49458436b799af014fba517d373a399cab05bf2859fa72980b"},"schema_version":"1.0","source":{"id":"1905.12931","kind":"arxiv","version":2}},"canonical_sha256":"d0af46707a9479eb1274a39563d141db79bb79c19652ae0759ca8a1327fb142b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0af46707a9479eb1274a39563d141db79bb79c19652ae0759ca8a1327fb142b","first_computed_at":"2026-05-17T23:40:17.100890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:17.100890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/YV3k+sfJPVsy0vs8mnatIzQ76dXotpHLfLGCW2IRen4LhCNDQmD0lD7wQtn9zMI+6ZlkLuVr4PG7vx4tFxVBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:17.102685Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.12931","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5f89dffb3e7dc870847904f14ba163c211f9f742942ec39c82ca9c6f399a3af","sha256:4c492a0025b127760bffa4cc7908d0249892b061d0aee6e6a7c355ddb4913b1b"],"state_sha256":"0e4dadb6f730e14ff6f73f2adcf157a3a6db3de7d689765a12f468ced03ec808"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vycBEpJK3laxJYjE7knPgG+YvZT2JZv2TVS6ixU6LEifc+Aa0ngwchJggeZmsNC3oomT5lETG/Fj8ugi1xp6Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T16:37:31.687085Z","bundle_sha256":"858fc3c70d47d418cb133c0cafdb836ed6c39cf3c1a99c2c590b0b4ecfbee0a2"}}