{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:XSYH43G75S6PZJ6FLDP5K6ZGOU","short_pith_number":"pith:XSYH43G7","canonical_record":{"source":{"id":"1706.05721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-18T20:35:27Z","cross_cats_sorted":[],"title_canon_sha256":"61e5ef8eb8648edc482481cc9e25d6263291522046980c92bc4c3b2a95548956","abstract_canon_sha256":"685d8da8e2354ff5fb0e9f18f9ae139cdd62071b2a77c63dfbcb829c6d5ea62a"},"schema_version":"1.0"},"canonical_sha256":"bcb07e6cdfecbcfca7c558dfd57b26750e20262482b621e1bdcd2c286f638226","source":{"kind":"arxiv","id":"1706.05721","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.05721","created_at":"2026-05-18T00:42:09Z"},{"alias_kind":"arxiv_version","alias_value":"1706.05721v1","created_at":"2026-05-18T00:42:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.05721","created_at":"2026-05-18T00:42:09Z"},{"alias_kind":"pith_short_12","alias_value":"XSYH43G75S6P","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"XSYH43G75S6PZJ6F","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"XSYH43G7","created_at":"2026-05-18T12:31:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:XSYH43G75S6PZJ6FLDP5K6ZGOU","target":"record","payload":{"canonical_record":{"source":{"id":"1706.05721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-18T20:35:27Z","cross_cats_sorted":[],"title_canon_sha256":"61e5ef8eb8648edc482481cc9e25d6263291522046980c92bc4c3b2a95548956","abstract_canon_sha256":"685d8da8e2354ff5fb0e9f18f9ae139cdd62071b2a77c63dfbcb829c6d5ea62a"},"schema_version":"1.0"},"canonical_sha256":"bcb07e6cdfecbcfca7c558dfd57b26750e20262482b621e1bdcd2c286f638226","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:09.105764Z","signature_b64":"FAa/VBp661mQsNgz5gv2x6LL69DvVCwE4zKhECb3aGxct3fCr4TIFZy86vxeTViG10btYv1w4GO7OSsuBil9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcb07e6cdfecbcfca7c558dfd57b26750e20262482b621e1bdcd2c286f638226","last_reissued_at":"2026-05-18T00:42:09.105269Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:09.105269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.05721","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":"2026-05-18T00:42:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fmho8FnMgsFENbgIysVj89OvNzya/OU2/fKqbf+q2iIPxMyWI/8Qp7iEpSwumjZn8q+zUd0kizoJVKcLeLztAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:43:05.529035Z"},"content_sha256":"1e45d546e7d414cdfbf77dffe8dedec54cfd4f1b0fa071e4af4cfc82d8eb2862","schema_version":"1.0","event_id":"sha256:1e45d546e7d414cdfbf77dffe8dedec54cfd4f1b0fa071e4af4cfc82d8eb2862"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:XSYH43G75S6PZJ6FLDP5K6ZGOU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tversky loss function for image segmentation using 3D fully convolutional deep networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Gholipour, Deniz Erdogmus, Seyed Sadegh Mohseni Salehi","submitted_at":"2017-06-18T20:35:27Z","abstract_excerpt":"Fully convolutional deep neural networks carry out excellent potential for fast and accurate image segmentation. One of the main challenges in training these networks is data imbalance, which is particularly problematic in medical imaging applications such as lesion segmentation where the number of lesion voxels is often much lower than the number of non-lesion voxels. Training with unbalanced data can lead to predictions that are severely biased towards high precision but low recall (sensitivity), which is undesired especially in medical applications where false negatives are much less tolera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.05721","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":"2026-05-18T00:42:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hLK4Oh+of5MVCJkgCVKmblWx7AVgRPq7eQzYozT9QLKTJfgl9fXlMqrxDfqFXG0PReTu5jKNNEfpkwx2wkp8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:43:05.529723Z"},"content_sha256":"8f694a171d37ad413077b7be664435a45caf82c8a356477c64b16cd300acf88f","schema_version":"1.0","event_id":"sha256:8f694a171d37ad413077b7be664435a45caf82c8a356477c64b16cd300acf88f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XSYH43G75S6PZJ6FLDP5K6ZGOU/bundle.json","state_url":"https://pith.science/pith/XSYH43G75S6PZJ6FLDP5K6ZGOU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XSYH43G75S6PZJ6FLDP5K6ZGOU/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":"2026-05-26T10:43:05Z","links":{"resolver":"https://pith.science/pith/XSYH43G75S6PZJ6FLDP5K6ZGOU","bundle":"https://pith.science/pith/XSYH43G75S6PZJ6FLDP5K6ZGOU/bundle.json","state":"https://pith.science/pith/XSYH43G75S6PZJ6FLDP5K6ZGOU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XSYH43G75S6PZJ6FLDP5K6ZGOU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:XSYH43G75S6PZJ6FLDP5K6ZGOU","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":"685d8da8e2354ff5fb0e9f18f9ae139cdd62071b2a77c63dfbcb829c6d5ea62a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-18T20:35:27Z","title_canon_sha256":"61e5ef8eb8648edc482481cc9e25d6263291522046980c92bc4c3b2a95548956"},"schema_version":"1.0","source":{"id":"1706.05721","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.05721","created_at":"2026-05-18T00:42:09Z"},{"alias_kind":"arxiv_version","alias_value":"1706.05721v1","created_at":"2026-05-18T00:42:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.05721","created_at":"2026-05-18T00:42:09Z"},{"alias_kind":"pith_short_12","alias_value":"XSYH43G75S6P","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"XSYH43G75S6PZJ6F","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"XSYH43G7","created_at":"2026-05-18T12:31:56Z"}],"graph_snapshots":[{"event_id":"sha256:8f694a171d37ad413077b7be664435a45caf82c8a356477c64b16cd300acf88f","target":"graph","created_at":"2026-05-18T00:42:09Z","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":"Fully convolutional deep neural networks carry out excellent potential for fast and accurate image segmentation. One of the main challenges in training these networks is data imbalance, which is particularly problematic in medical imaging applications such as lesion segmentation where the number of lesion voxels is often much lower than the number of non-lesion voxels. Training with unbalanced data can lead to predictions that are severely biased towards high precision but low recall (sensitivity), which is undesired especially in medical applications where false negatives are much less tolera","authors_text":"Ali Gholipour, Deniz Erdogmus, Seyed Sadegh Mohseni Salehi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-18T20:35:27Z","title":"Tversky loss function for image segmentation using 3D fully convolutional deep networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.05721","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":"sha256:1e45d546e7d414cdfbf77dffe8dedec54cfd4f1b0fa071e4af4cfc82d8eb2862","target":"record","created_at":"2026-05-18T00:42:09Z","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":"685d8da8e2354ff5fb0e9f18f9ae139cdd62071b2a77c63dfbcb829c6d5ea62a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-18T20:35:27Z","title_canon_sha256":"61e5ef8eb8648edc482481cc9e25d6263291522046980c92bc4c3b2a95548956"},"schema_version":"1.0","source":{"id":"1706.05721","kind":"arxiv","version":1}},"canonical_sha256":"bcb07e6cdfecbcfca7c558dfd57b26750e20262482b621e1bdcd2c286f638226","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcb07e6cdfecbcfca7c558dfd57b26750e20262482b621e1bdcd2c286f638226","first_computed_at":"2026-05-18T00:42:09.105269Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:09.105269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FAa/VBp661mQsNgz5gv2x6LL69DvVCwE4zKhECb3aGxct3fCr4TIFZy86vxeTViG10btYv1w4GO7OSsuBil9Cw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:09.105764Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.05721","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e45d546e7d414cdfbf77dffe8dedec54cfd4f1b0fa071e4af4cfc82d8eb2862","sha256:8f694a171d37ad413077b7be664435a45caf82c8a356477c64b16cd300acf88f"],"state_sha256":"3f0cc78665471a0872910e7bccae0b1582192b8d4eaebef99468d62af5887598"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6//pnBNrJh5m72QAhJez0JHdCTUJWUzBT9Yjl3VXmEOSQo/yYofsYGyg8B/ePSNrMkLzbw/EpyafXYx8PiwqDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T10:43:05.533283Z","bundle_sha256":"01910d2a2215036d20004a57a5f62ce808997710eb7fde7e024759a8d0165d20"}}