{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:3VZFU4ANQQS7EBPHCATJF6TV2B","short_pith_number":"pith:3VZFU4AN","canonical_record":{"source":{"id":"1805.04628","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-12T00:51:54Z","cross_cats_sorted":[],"title_canon_sha256":"480c60422b220b8f0fcc09625f88277c44a58a27a1978d54811484bbfe4df9a2","abstract_canon_sha256":"a4804408043d80fac1a22341f6de2297fbec4dc3a39fa8519186247e62cc2aa4"},"schema_version":"1.0"},"canonical_sha256":"dd725a700d8425f205e7102692fa75d05c16b4cd6125f7111fb238c5988198b3","source":{"kind":"arxiv","id":"1805.04628","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.04628","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"arxiv_version","alias_value":"1805.04628v2","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.04628","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"pith_short_12","alias_value":"3VZFU4ANQQS7","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"3VZFU4ANQQS7EBPH","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"3VZFU4AN","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:3VZFU4ANQQS7EBPHCATJF6TV2B","target":"record","payload":{"canonical_record":{"source":{"id":"1805.04628","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-12T00:51:54Z","cross_cats_sorted":[],"title_canon_sha256":"480c60422b220b8f0fcc09625f88277c44a58a27a1978d54811484bbfe4df9a2","abstract_canon_sha256":"a4804408043d80fac1a22341f6de2297fbec4dc3a39fa8519186247e62cc2aa4"},"schema_version":"1.0"},"canonical_sha256":"dd725a700d8425f205e7102692fa75d05c16b4cd6125f7111fb238c5988198b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:54.570647Z","signature_b64":"muFWVdlWSVWDVulrzwmwkweeVd/d8B+QbO8ql3pNgGfLZdgJcbJf5e19YwfpkXNGABobHtjso5anReaCk0FaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd725a700d8425f205e7102692fa75d05c16b4cd6125f7111fb238c5988198b3","last_reissued_at":"2026-05-17T23:51:54.570159Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:54.570159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.04628","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":"2026-05-17T23:51:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X/usooUHiFu7EPCwrCGhyG30FyqNJFn6qX50fOL06SShDLxVYgPPzgurWSImNLOP7vICt6W/7SuU0MvmfPX8CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:05:57.509180Z"},"content_sha256":"2204510abf57f673ec339d070b11643100c9b3741d364df2f29ce8508a1974ea","schema_version":"1.0","event_id":"sha256:2204510abf57f673ec339d070b11643100c9b3741d364df2f29ce8508a1974ea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:3VZFU4ANQQS7EBPHCATJF6TV2B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Constrained-CNN losses for weakly supervised segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric Granger, Hoel Kervadec, Ismail Ben Ayed, Jose Dolz, Meng Tang, Yuri Boykov","submitted_at":"2018-05-12T00:51:54Z","abstract_excerpt":"Weakly-supervised learning based on, e.g., partially labelled images or image-tags, is currently attracting significant attention in CNN segmentation as it can mitigate the need for full and laborious pixel/voxel annotations. Enforcing high-order (global) inequality constraints on the network output (for instance, to constrain the size of the target region) can leverage unlabeled data, guiding the training process with domain-specific knowledge. Inequality constraints are very flexible because they do not assume exact prior knowledge. However, constrained Lagrangian dual optimization has been "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.04628","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":"2026-05-17T23:51:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"im+hgseCV/4BqLd1UTKBEdvcvlYHeETAWVx0hl515lUXjsPbqqpbFoATMvHPOqH/o3HjpuvsEOhdquHkKi9DCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:05:57.509539Z"},"content_sha256":"942772169010b93516bad346d88275d6baa9975cd508d8be7224a0e027be4b96","schema_version":"1.0","event_id":"sha256:942772169010b93516bad346d88275d6baa9975cd508d8be7224a0e027be4b96"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3VZFU4ANQQS7EBPHCATJF6TV2B/bundle.json","state_url":"https://pith.science/pith/3VZFU4ANQQS7EBPHCATJF6TV2B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3VZFU4ANQQS7EBPHCATJF6TV2B/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":"2026-05-28T20:05:57Z","links":{"resolver":"https://pith.science/pith/3VZFU4ANQQS7EBPHCATJF6TV2B","bundle":"https://pith.science/pith/3VZFU4ANQQS7EBPHCATJF6TV2B/bundle.json","state":"https://pith.science/pith/3VZFU4ANQQS7EBPHCATJF6TV2B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3VZFU4ANQQS7EBPHCATJF6TV2B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:3VZFU4ANQQS7EBPHCATJF6TV2B","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":"a4804408043d80fac1a22341f6de2297fbec4dc3a39fa8519186247e62cc2aa4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-12T00:51:54Z","title_canon_sha256":"480c60422b220b8f0fcc09625f88277c44a58a27a1978d54811484bbfe4df9a2"},"schema_version":"1.0","source":{"id":"1805.04628","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.04628","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"arxiv_version","alias_value":"1805.04628v2","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.04628","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"pith_short_12","alias_value":"3VZFU4ANQQS7","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"3VZFU4ANQQS7EBPH","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"3VZFU4AN","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:942772169010b93516bad346d88275d6baa9975cd508d8be7224a0e027be4b96","target":"graph","created_at":"2026-05-17T23:51:54Z","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":"Weakly-supervised learning based on, e.g., partially labelled images or image-tags, is currently attracting significant attention in CNN segmentation as it can mitigate the need for full and laborious pixel/voxel annotations. Enforcing high-order (global) inequality constraints on the network output (for instance, to constrain the size of the target region) can leverage unlabeled data, guiding the training process with domain-specific knowledge. Inequality constraints are very flexible because they do not assume exact prior knowledge. However, constrained Lagrangian dual optimization has been ","authors_text":"Eric Granger, Hoel Kervadec, Ismail Ben Ayed, Jose Dolz, Meng Tang, Yuri Boykov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-12T00:51:54Z","title":"Constrained-CNN losses for weakly supervised segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.04628","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":"sha256:2204510abf57f673ec339d070b11643100c9b3741d364df2f29ce8508a1974ea","target":"record","created_at":"2026-05-17T23:51:54Z","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":"a4804408043d80fac1a22341f6de2297fbec4dc3a39fa8519186247e62cc2aa4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-12T00:51:54Z","title_canon_sha256":"480c60422b220b8f0fcc09625f88277c44a58a27a1978d54811484bbfe4df9a2"},"schema_version":"1.0","source":{"id":"1805.04628","kind":"arxiv","version":2}},"canonical_sha256":"dd725a700d8425f205e7102692fa75d05c16b4cd6125f7111fb238c5988198b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd725a700d8425f205e7102692fa75d05c16b4cd6125f7111fb238c5988198b3","first_computed_at":"2026-05-17T23:51:54.570159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:54.570159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"muFWVdlWSVWDVulrzwmwkweeVd/d8B+QbO8ql3pNgGfLZdgJcbJf5e19YwfpkXNGABobHtjso5anReaCk0FaAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:54.570647Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.04628","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2204510abf57f673ec339d070b11643100c9b3741d364df2f29ce8508a1974ea","sha256:942772169010b93516bad346d88275d6baa9975cd508d8be7224a0e027be4b96"],"state_sha256":"291b8554e873a4e3511623dc607c0f9bdc317e15e33679bb05f6dce22c63aed8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ru6mCn3VHAHG/7MI4+aelQsRcsMyF8tpkB0OTH8vh+fI5EumOJfLt6Q+jX+nkNvy3IvQAUpaF1F4vJQxrLxLCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T20:05:57.511754Z","bundle_sha256":"c9664198e247aa498c06e714642305879e55e7113d8033159ac336f5ee4ddf01"}}