{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:Z4AXXDO7VI4MVKNENV2335VREW","short_pith_number":"pith:Z4AXXDO7","canonical_record":{"source":{"id":"1804.01346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-04T11:18:21Z","cross_cats_sorted":[],"title_canon_sha256":"9f149954de0f1ddab2655d29f94ff9df156c9f72ce07d69d72d1c92240435baf","abstract_canon_sha256":"7a6b05c86a599b97d6541ea71a4569a940f095b3dbdd96e7eb5af0633f331f98"},"schema_version":"1.0"},"canonical_sha256":"cf017b8ddfaa38caa9a46d75bdf6b125979fd57f5850499ab1b599e50f5dd083","source":{"kind":"arxiv","id":"1804.01346","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.01346","created_at":"2026-05-18T00:19:15Z"},{"alias_kind":"arxiv_version","alias_value":"1804.01346v1","created_at":"2026-05-18T00:19:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01346","created_at":"2026-05-18T00:19:15Z"},{"alias_kind":"pith_short_12","alias_value":"Z4AXXDO7VI4M","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Z4AXXDO7VI4MVKNE","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Z4AXXDO7","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:Z4AXXDO7VI4MVKNENV2335VREW","target":"record","payload":{"canonical_record":{"source":{"id":"1804.01346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-04T11:18:21Z","cross_cats_sorted":[],"title_canon_sha256":"9f149954de0f1ddab2655d29f94ff9df156c9f72ce07d69d72d1c92240435baf","abstract_canon_sha256":"7a6b05c86a599b97d6541ea71a4569a940f095b3dbdd96e7eb5af0633f331f98"},"schema_version":"1.0"},"canonical_sha256":"cf017b8ddfaa38caa9a46d75bdf6b125979fd57f5850499ab1b599e50f5dd083","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:15.342487Z","signature_b64":"E6w5f/3HbAe0HGyKr7QcRSSYqa70gx9s4WaY2QbpAR9KaV/Jk8Af2BiZeiLbEfy+9WRHRp0elb8Ucaqx5WAFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf017b8ddfaa38caa9a46d75bdf6b125979fd57f5850499ab1b599e50f5dd083","last_reissued_at":"2026-05-18T00:19:15.341901Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:15.341901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.01346","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":"2026-05-18T00:19:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QoRGF6Y/IolHPTHsGR3LItJM6fWjg6ONrSUSDxPL12UXstaBNky09PvgdIKraLhpVMisuIhh1mCMnKFE8If4BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T23:41:02.692155Z"},"content_sha256":"9fab9f8880c3b043e186fdcfbf979593b8aac3e8ccc09bd8a4511f15cd1b2d80","schema_version":"1.0","event_id":"sha256:9fab9f8880c3b043e186fdcfbf979593b8aac3e8ccc09bd8a4511f15cd1b2d80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:Z4AXXDO7VI4MVKNENV2335VREW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Normalized Cut Loss for Weakly-supervised CNN Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelaziz Djelouah, Christopher Schroers, Federico Perazzi, Meng Tang, Yuri Boykov","submitted_at":"2018-04-04T11:18:21Z","abstract_excerpt":"Most recent semantic segmentation methods train deep convolutional neural networks with fully annotated masks requiring pixel-accuracy for good quality training. Common weakly-supervised approaches generate full masks from partial input (e.g. scribbles or seeds) using standard interactive segmentation methods as preprocessing. But, errors in such masks result in poorer training since standard loss functions (e.g. cross-entropy) do not distinguish seeds from potentially mislabeled other pixels. Inspired by the general ideas in semi-supervised learning, we address these problems via a new princi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01346","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":"2026-05-18T00:19:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IZm54ayXUhbu6ufVqRrSiYF8CdgcfrfV/EtqebqXr8F5vBUiBwS/IJq2C+J7F4Gzbj9eOss+Ikb9BdT7bC0mBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T23:41:02.692891Z"},"content_sha256":"0bfa82870bbd87ab10f45d95b79f86bdf84c253d40606e1c4f01377cc15d9ac2","schema_version":"1.0","event_id":"sha256:0bfa82870bbd87ab10f45d95b79f86bdf84c253d40606e1c4f01377cc15d9ac2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z4AXXDO7VI4MVKNENV2335VREW/bundle.json","state_url":"https://pith.science/pith/Z4AXXDO7VI4MVKNENV2335VREW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z4AXXDO7VI4MVKNENV2335VREW/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":"2026-05-31T23:41:02Z","links":{"resolver":"https://pith.science/pith/Z4AXXDO7VI4MVKNENV2335VREW","bundle":"https://pith.science/pith/Z4AXXDO7VI4MVKNENV2335VREW/bundle.json","state":"https://pith.science/pith/Z4AXXDO7VI4MVKNENV2335VREW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z4AXXDO7VI4MVKNENV2335VREW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Z4AXXDO7VI4MVKNENV2335VREW","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":"7a6b05c86a599b97d6541ea71a4569a940f095b3dbdd96e7eb5af0633f331f98","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-04T11:18:21Z","title_canon_sha256":"9f149954de0f1ddab2655d29f94ff9df156c9f72ce07d69d72d1c92240435baf"},"schema_version":"1.0","source":{"id":"1804.01346","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.01346","created_at":"2026-05-18T00:19:15Z"},{"alias_kind":"arxiv_version","alias_value":"1804.01346v1","created_at":"2026-05-18T00:19:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01346","created_at":"2026-05-18T00:19:15Z"},{"alias_kind":"pith_short_12","alias_value":"Z4AXXDO7VI4M","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Z4AXXDO7VI4MVKNE","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Z4AXXDO7","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:0bfa82870bbd87ab10f45d95b79f86bdf84c253d40606e1c4f01377cc15d9ac2","target":"graph","created_at":"2026-05-18T00:19:15Z","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":"Most recent semantic segmentation methods train deep convolutional neural networks with fully annotated masks requiring pixel-accuracy for good quality training. Common weakly-supervised approaches generate full masks from partial input (e.g. scribbles or seeds) using standard interactive segmentation methods as preprocessing. But, errors in such masks result in poorer training since standard loss functions (e.g. cross-entropy) do not distinguish seeds from potentially mislabeled other pixels. Inspired by the general ideas in semi-supervised learning, we address these problems via a new princi","authors_text":"Abdelaziz Djelouah, Christopher Schroers, Federico Perazzi, Meng Tang, Yuri Boykov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-04T11:18:21Z","title":"Normalized Cut Loss for Weakly-supervised CNN Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01346","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":"sha256:9fab9f8880c3b043e186fdcfbf979593b8aac3e8ccc09bd8a4511f15cd1b2d80","target":"record","created_at":"2026-05-18T00:19:15Z","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":"7a6b05c86a599b97d6541ea71a4569a940f095b3dbdd96e7eb5af0633f331f98","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-04T11:18:21Z","title_canon_sha256":"9f149954de0f1ddab2655d29f94ff9df156c9f72ce07d69d72d1c92240435baf"},"schema_version":"1.0","source":{"id":"1804.01346","kind":"arxiv","version":1}},"canonical_sha256":"cf017b8ddfaa38caa9a46d75bdf6b125979fd57f5850499ab1b599e50f5dd083","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf017b8ddfaa38caa9a46d75bdf6b125979fd57f5850499ab1b599e50f5dd083","first_computed_at":"2026-05-18T00:19:15.341901Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:15.341901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E6w5f/3HbAe0HGyKr7QcRSSYqa70gx9s4WaY2QbpAR9KaV/Jk8Af2BiZeiLbEfy+9WRHRp0elb8Ucaqx5WAFBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:15.342487Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.01346","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fab9f8880c3b043e186fdcfbf979593b8aac3e8ccc09bd8a4511f15cd1b2d80","sha256:0bfa82870bbd87ab10f45d95b79f86bdf84c253d40606e1c4f01377cc15d9ac2"],"state_sha256":"fe5cf17b541c6533a627cc9edbac2278b6ec6d8a5aae02fda3e8f85b70431281"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"27tdTPLf8A7ioclYh+XufSBHSXOAGD2qd6Qp4IL/Lb90YGdNXWe8/6H4bI0Qfmj58j1Wj/5Dc5pPaOmvvRkKCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T23:41:02.697026Z","bundle_sha256":"941951c1e024f05f21c197703cd12d368ec08678257abbe7dfdfc9a2eb63599b"}}