{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:OMMQ3QBWBNPZ7GW4LLAFAEVFAB","short_pith_number":"pith:OMMQ3QBW","canonical_record":{"source":{"id":"2112.13885","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2021-12-27T20:06:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7bf35860a3eea755b93a0a233a3c36e8a9f7f2dafdc04ddbb38230c9707ac14e","abstract_canon_sha256":"1de60e94e894b87d95d33deb965496efa45d52c5eb59bc68541ff131ca42d5c0"},"schema_version":"1.0"},"canonical_sha256":"73190dc0360b5f9f9adc5ac05012a5004c3dc473bd1fe69801f09ea5d65bb24d","source":{"kind":"arxiv","id":"2112.13885","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.13885","created_at":"2026-07-05T03:43:59Z"},{"alias_kind":"arxiv_version","alias_value":"2112.13885v1","created_at":"2026-07-05T03:43:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.13885","created_at":"2026-07-05T03:43:59Z"},{"alias_kind":"pith_short_12","alias_value":"OMMQ3QBWBNPZ","created_at":"2026-07-05T03:43:59Z"},{"alias_kind":"pith_short_16","alias_value":"OMMQ3QBWBNPZ7GW4","created_at":"2026-07-05T03:43:59Z"},{"alias_kind":"pith_short_8","alias_value":"OMMQ3QBW","created_at":"2026-07-05T03:43:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:OMMQ3QBWBNPZ7GW4LLAFAEVFAB","target":"record","payload":{"canonical_record":{"source":{"id":"2112.13885","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2021-12-27T20:06:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7bf35860a3eea755b93a0a233a3c36e8a9f7f2dafdc04ddbb38230c9707ac14e","abstract_canon_sha256":"1de60e94e894b87d95d33deb965496efa45d52c5eb59bc68541ff131ca42d5c0"},"schema_version":"1.0"},"canonical_sha256":"73190dc0360b5f9f9adc5ac05012a5004c3dc473bd1fe69801f09ea5d65bb24d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:59.971598Z","signature_b64":"n8M2WWQA5km7g51T1JEDH3hYzilqZ0ijP2nUrO96VMxYraYJ3Ln6OZHmARP+GEo9RaOubNIXkG3G3HYttuFHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73190dc0360b5f9f9adc5ac05012a5004c3dc473bd1fe69801f09ea5d65bb24d","last_reissued_at":"2026-07-05T03:43:59.971269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:59.971269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.13885","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":"2026-07-05T03:43:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8BIpNbRS6xXTP6H5eNNOr0oeBu1/e/i/n3Y8H7/RnjV6PMPn2sgPVOHjbsib5frx2i5UW3RxVGh37xBWiJWvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:29:18.789284Z"},"content_sha256":"da1478406489c00a8c288d0676b1495f7914d659fb25541113918131671fc302","schema_version":"1.0","event_id":"sha256:da1478406489c00a8c288d0676b1495f7914d659fb25541113918131671fc302"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:OMMQ3QBWBNPZ7GW4LLAFAEVFAB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MedShift: identifying shift data for medical dataset curation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Hari Trivedi, Imon Banerjee, Judy Wawira Gichoya, Saptarshi Purkayastha, Xiaoyuan Guo","submitted_at":"2021-12-27T20:06:23Z","abstract_excerpt":"To curate a high-quality dataset, identifying data variance between the internal and external sources is a fundamental and crucial step. However, methods to detect shift or variance in data have not been significantly researched. Challenges to this are the lack of effective approaches to learn dense representation of a dataset and difficulties of sharing private data across medical institutions. To overcome the problems, we propose a unified pipeline called MedShift to detect the top-level shift samples and thus facilitate the medical curation. Given an internal dataset A as the base source, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.13885","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/2112.13885/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":"2026-07-05T03:43:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jyvg0/rbBDtA5NRqc8tskogISgQ8WwVZSPLSXI+wUZ8mupT4dK/kuskWeWOnjoxJG4LhdlXeM0hpyRZQdHzADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:29:18.789690Z"},"content_sha256":"82e29f583187c7910e715cdfd25a29908a91fadd84b40e06aaff4b855469f1ae","schema_version":"1.0","event_id":"sha256:82e29f583187c7910e715cdfd25a29908a91fadd84b40e06aaff4b855469f1ae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OMMQ3QBWBNPZ7GW4LLAFAEVFAB/bundle.json","state_url":"https://pith.science/pith/OMMQ3QBWBNPZ7GW4LLAFAEVFAB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OMMQ3QBWBNPZ7GW4LLAFAEVFAB/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":"2026-07-07T08:29:18Z","links":{"resolver":"https://pith.science/pith/OMMQ3QBWBNPZ7GW4LLAFAEVFAB","bundle":"https://pith.science/pith/OMMQ3QBWBNPZ7GW4LLAFAEVFAB/bundle.json","state":"https://pith.science/pith/OMMQ3QBWBNPZ7GW4LLAFAEVFAB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OMMQ3QBWBNPZ7GW4LLAFAEVFAB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:OMMQ3QBWBNPZ7GW4LLAFAEVFAB","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":"1de60e94e894b87d95d33deb965496efa45d52c5eb59bc68541ff131ca42d5c0","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2021-12-27T20:06:23Z","title_canon_sha256":"7bf35860a3eea755b93a0a233a3c36e8a9f7f2dafdc04ddbb38230c9707ac14e"},"schema_version":"1.0","source":{"id":"2112.13885","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.13885","created_at":"2026-07-05T03:43:59Z"},{"alias_kind":"arxiv_version","alias_value":"2112.13885v1","created_at":"2026-07-05T03:43:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.13885","created_at":"2026-07-05T03:43:59Z"},{"alias_kind":"pith_short_12","alias_value":"OMMQ3QBWBNPZ","created_at":"2026-07-05T03:43:59Z"},{"alias_kind":"pith_short_16","alias_value":"OMMQ3QBWBNPZ7GW4","created_at":"2026-07-05T03:43:59Z"},{"alias_kind":"pith_short_8","alias_value":"OMMQ3QBW","created_at":"2026-07-05T03:43:59Z"}],"graph_snapshots":[{"event_id":"sha256:82e29f583187c7910e715cdfd25a29908a91fadd84b40e06aaff4b855469f1ae","target":"graph","created_at":"2026-07-05T03:43:59Z","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/2112.13885/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To curate a high-quality dataset, identifying data variance between the internal and external sources is a fundamental and crucial step. However, methods to detect shift or variance in data have not been significantly researched. Challenges to this are the lack of effective approaches to learn dense representation of a dataset and difficulties of sharing private data across medical institutions. To overcome the problems, we propose a unified pipeline called MedShift to detect the top-level shift samples and thus facilitate the medical curation. Given an internal dataset A as the base source, w","authors_text":"Hari Trivedi, Imon Banerjee, Judy Wawira Gichoya, Saptarshi Purkayastha, Xiaoyuan Guo","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2021-12-27T20:06:23Z","title":"MedShift: identifying shift data for medical dataset curation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.13885","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:da1478406489c00a8c288d0676b1495f7914d659fb25541113918131671fc302","target":"record","created_at":"2026-07-05T03:43:59Z","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":"1de60e94e894b87d95d33deb965496efa45d52c5eb59bc68541ff131ca42d5c0","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2021-12-27T20:06:23Z","title_canon_sha256":"7bf35860a3eea755b93a0a233a3c36e8a9f7f2dafdc04ddbb38230c9707ac14e"},"schema_version":"1.0","source":{"id":"2112.13885","kind":"arxiv","version":1}},"canonical_sha256":"73190dc0360b5f9f9adc5ac05012a5004c3dc473bd1fe69801f09ea5d65bb24d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73190dc0360b5f9f9adc5ac05012a5004c3dc473bd1fe69801f09ea5d65bb24d","first_computed_at":"2026-07-05T03:43:59.971269Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:43:59.971269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n8M2WWQA5km7g51T1JEDH3hYzilqZ0ijP2nUrO96VMxYraYJ3Ln6OZHmARP+GEo9RaOubNIXkG3G3HYttuFHDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:43:59.971598Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.13885","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da1478406489c00a8c288d0676b1495f7914d659fb25541113918131671fc302","sha256:82e29f583187c7910e715cdfd25a29908a91fadd84b40e06aaff4b855469f1ae"],"state_sha256":"f4d2cbac679d33373ae2999f9faa8db3d02f190cf21dc7e240837dc2ec39b67c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eAGgFHXjM+QYcNyBCPAUCp/gET0AVK84Uxfpz9CXiPoPF2g4aYLEQvS6czwzol8OOSpRD64UvihCyr3bb2OYDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:29:18.791671Z","bundle_sha256":"57dace51e4fd03ec5477a54bb5b052f1d3994eec745543186289ea8b6cf64a8d"}}