{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5LFIMW6W457YNZF6XDUY7HNGII","short_pith_number":"pith:5LFIMW6W","canonical_record":{"source":{"id":"2504.01527","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T09:13:18Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"a6de217bf5863770fd6124b34a76dc1763f46d2544f7c2982382c6c89815fc1e","abstract_canon_sha256":"b9fefc201df791e6d7919a37b53c0e2ee5db3c5eed1618cf80d1a4aba5e88965"},"schema_version":"1.0"},"canonical_sha256":"eaca865bd6e77f86e4beb8e98f9da642364b016a1827eb71baa01631932a6152","source":{"kind":"arxiv","id":"2504.01527","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01527","created_at":"2026-06-19T16:11:10Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01527v4","created_at":"2026-06-19T16:11:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01527","created_at":"2026-06-19T16:11:10Z"},{"alias_kind":"pith_short_12","alias_value":"5LFIMW6W457Y","created_at":"2026-06-19T16:11:10Z"},{"alias_kind":"pith_short_16","alias_value":"5LFIMW6W457YNZF6","created_at":"2026-06-19T16:11:10Z"},{"alias_kind":"pith_short_8","alias_value":"5LFIMW6W","created_at":"2026-06-19T16:11:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5LFIMW6W457YNZF6XDUY7HNGII","target":"record","payload":{"canonical_record":{"source":{"id":"2504.01527","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T09:13:18Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"a6de217bf5863770fd6124b34a76dc1763f46d2544f7c2982382c6c89815fc1e","abstract_canon_sha256":"b9fefc201df791e6d7919a37b53c0e2ee5db3c5eed1618cf80d1a4aba5e88965"},"schema_version":"1.0"},"canonical_sha256":"eaca865bd6e77f86e4beb8e98f9da642364b016a1827eb71baa01631932a6152","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:10.473337Z","signature_b64":"hGTkxio1vMRJ0TPvWocc9Ro+vkUjDL+wBxJOfBvY4vmdYmVSwXMPiA+tyjempTPLCAXVIFM0kqTql7TIVYkAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eaca865bd6e77f86e4beb8e98f9da642364b016a1827eb71baa01631932a6152","last_reissued_at":"2026-06-19T16:11:10.472855Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:10.472855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.01527","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:11:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bcxkbAJqZJ33MyJxKum16XMBJquGJvFC1Oiq+7grxImUUuE9dVxE0xePaRWAjYLYPa0wDVsdxilIiB12NlgqAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T20:39:19.231198Z"},"content_sha256":"03a36f4b3bdc32e2e81bc859ab0fc7f52132ce8d8d9f7f966b6092f8bb3b6e4e","schema_version":"1.0","event_id":"sha256:03a36f4b3bdc32e2e81bc859ab0fc7f52132ce8d8d9f7f966b6092f8bb3b6e4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5LFIMW6W457YNZF6XDUY7HNGII","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Nearest Neighbor Interpolation in Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Replacing nearest neighbor interpolation with alternative methods and a mean-based class filter improves performance in medical image segmentation.","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Olivier Rukundo","submitted_at":"2025-04-02T09:13:18Z","abstract_excerpt":"Avoiding the risk of undefined categorical labels using nearest neighbor interpolation overlooks the risk of exacerbating pixel level annotation errors in augmented training data. Additionally, the inherent low pass filtering effects of interpolation algorithms exacerbate the risk of degrading high frequency structural details within annotated regions of interest. To avoid these risks, the author modified convolutional neural networks data transformation functions by incorporating a modified geometric transformation function, removing reliance on nearest neighbor interpolation, and integrating"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experimental evaluation on three medical image segmentation datasets and the XBAT+ datasets demonstrated performance gains across multiple quantitative metrics.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the mean-based class filtering mechanism effectively handles undefined categorical labels without introducing new biases or errors in the augmented data while preserving high-frequency details.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A modified geometric transformation and mean-based class filtering in data augmentation pipelines, paired with an offline interpolation-specific pipeline, yields performance gains on medical image segmentation datasets by avoiding nearest-neighbor label and detail issues.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Replacing nearest neighbor interpolation with alternative methods and a mean-based class filter improves performance in medical image segmentation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"186305b33a269fecd752fa65684f4941ec2995bafb00ba281c81bb06522a8b17"},"source":{"id":"2504.01527","kind":"arxiv","version":4},"verdict":{"id":"59e24f0b-4475-42f3-aafe-3170fd9166b9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-22T22:08:40.969900Z","strongest_claim":"Experimental evaluation on three medical image segmentation datasets and the XBAT+ datasets demonstrated performance gains across multiple quantitative metrics.","one_line_summary":"A modified geometric transformation and mean-based class filtering in data augmentation pipelines, paired with an offline interpolation-specific pipeline, yields performance gains on medical image segmentation datasets by avoiding nearest-neighbor label and detail issues.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the mean-based class filtering mechanism effectively handles undefined categorical labels without introducing new biases or errors in the augmented data while preserving high-frequency details.","pith_extraction_headline":"Replacing nearest neighbor interpolation with alternative methods and a mean-based class filter improves performance in medical image segmentation."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.01527/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":"59e24f0b-4475-42f3-aafe-3170fd9166b9"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:11:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O9HlKdR93nLyyDjp9/DQkjG0cQ16xlBvq7TQPTUjC9wmlmf0FQJcK82SxFOIq7nhwuye/kGhmZ/E6CoPfQW4Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T20:39:19.231700Z"},"content_sha256":"a48392fe58eb812000eb5c33c34dcc796ab883bb6b9f7f21e6102d9036fa4af3","schema_version":"1.0","event_id":"sha256:a48392fe58eb812000eb5c33c34dcc796ab883bb6b9f7f21e6102d9036fa4af3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5LFIMW6W457YNZF6XDUY7HNGII/bundle.json","state_url":"https://pith.science/pith/5LFIMW6W457YNZF6XDUY7HNGII/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5LFIMW6W457YNZF6XDUY7HNGII/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":"2026-06-28T20:39:19Z","links":{"resolver":"https://pith.science/pith/5LFIMW6W457YNZF6XDUY7HNGII","bundle":"https://pith.science/pith/5LFIMW6W457YNZF6XDUY7HNGII/bundle.json","state":"https://pith.science/pith/5LFIMW6W457YNZF6XDUY7HNGII/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5LFIMW6W457YNZF6XDUY7HNGII/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5LFIMW6W457YNZF6XDUY7HNGII","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":"b9fefc201df791e6d7919a37b53c0e2ee5db3c5eed1618cf80d1a4aba5e88965","cross_cats_sorted":["eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T09:13:18Z","title_canon_sha256":"a6de217bf5863770fd6124b34a76dc1763f46d2544f7c2982382c6c89815fc1e"},"schema_version":"1.0","source":{"id":"2504.01527","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01527","created_at":"2026-06-19T16:11:10Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01527v4","created_at":"2026-06-19T16:11:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01527","created_at":"2026-06-19T16:11:10Z"},{"alias_kind":"pith_short_12","alias_value":"5LFIMW6W457Y","created_at":"2026-06-19T16:11:10Z"},{"alias_kind":"pith_short_16","alias_value":"5LFIMW6W457YNZF6","created_at":"2026-06-19T16:11:10Z"},{"alias_kind":"pith_short_8","alias_value":"5LFIMW6W","created_at":"2026-06-19T16:11:10Z"}],"graph_snapshots":[{"event_id":"sha256:a48392fe58eb812000eb5c33c34dcc796ab883bb6b9f7f21e6102d9036fa4af3","target":"graph","created_at":"2026-06-19T16:11:10Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experimental evaluation on three medical image segmentation datasets and the XBAT+ datasets demonstrated performance gains across multiple quantitative metrics."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the mean-based class filtering mechanism effectively handles undefined categorical labels without introducing new biases or errors in the augmented data while preserving high-frequency details."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A modified geometric transformation and mean-based class filtering in data augmentation pipelines, paired with an offline interpolation-specific pipeline, yields performance gains on medical image segmentation datasets by avoiding nearest-neighbor label and detail issues."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Replacing nearest neighbor interpolation with alternative methods and a mean-based class filter improves performance in medical image segmentation."}],"snapshot_sha256":"186305b33a269fecd752fa65684f4941ec2995bafb00ba281c81bb06522a8b17"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.01527/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Avoiding the risk of undefined categorical labels using nearest neighbor interpolation overlooks the risk of exacerbating pixel level annotation errors in augmented training data. Additionally, the inherent low pass filtering effects of interpolation algorithms exacerbate the risk of degrading high frequency structural details within annotated regions of interest. To avoid these risks, the author modified convolutional neural networks data transformation functions by incorporating a modified geometric transformation function, removing reliance on nearest neighbor interpolation, and integrating","authors_text":"Olivier Rukundo","cross_cats":["eess.IV"],"headline":"Replacing nearest neighbor interpolation with alternative methods and a mean-based class filter improves performance in medical image segmentation.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T09:13:18Z","title":"Beyond Nearest Neighbor Interpolation in Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01527","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-22T22:08:40.969900Z","id":"59e24f0b-4475-42f3-aafe-3170fd9166b9","model_set":{"reader":"grok-4.3"},"one_line_summary":"A modified geometric transformation and mean-based class filtering in data augmentation pipelines, paired with an offline interpolation-specific pipeline, yields performance gains on medical image segmentation datasets by avoiding nearest-neighbor label and detail issues.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Replacing nearest neighbor interpolation with alternative methods and a mean-based class filter improves performance in medical image segmentation.","strongest_claim":"Experimental evaluation on three medical image segmentation datasets and the XBAT+ datasets demonstrated performance gains across multiple quantitative metrics.","weakest_assumption":"That the mean-based class filtering mechanism effectively handles undefined categorical labels without introducing new biases or errors in the augmented data while preserving high-frequency details."}},"verdict_id":"59e24f0b-4475-42f3-aafe-3170fd9166b9"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:03a36f4b3bdc32e2e81bc859ab0fc7f52132ce8d8d9f7f966b6092f8bb3b6e4e","target":"record","created_at":"2026-06-19T16:11:10Z","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":"b9fefc201df791e6d7919a37b53c0e2ee5db3c5eed1618cf80d1a4aba5e88965","cross_cats_sorted":["eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T09:13:18Z","title_canon_sha256":"a6de217bf5863770fd6124b34a76dc1763f46d2544f7c2982382c6c89815fc1e"},"schema_version":"1.0","source":{"id":"2504.01527","kind":"arxiv","version":4}},"canonical_sha256":"eaca865bd6e77f86e4beb8e98f9da642364b016a1827eb71baa01631932a6152","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eaca865bd6e77f86e4beb8e98f9da642364b016a1827eb71baa01631932a6152","first_computed_at":"2026-06-19T16:11:10.472855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:10.472855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hGTkxio1vMRJ0TPvWocc9Ro+vkUjDL+wBxJOfBvY4vmdYmVSwXMPiA+tyjempTPLCAXVIFM0kqTql7TIVYkAAg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:10.473337Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.01527","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03a36f4b3bdc32e2e81bc859ab0fc7f52132ce8d8d9f7f966b6092f8bb3b6e4e","sha256:a48392fe58eb812000eb5c33c34dcc796ab883bb6b9f7f21e6102d9036fa4af3"],"state_sha256":"8ebc045d5327785add740e1a72a168ff73ad9158f8330a7947113cae8ed6c414"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"blcm6pGiTE+5GjN0m715g1ELc14LqzcmYqmf+ArNvxaq73R+ZUyaQKKvNfxG0qwv7HciircJxRVYHRJR+FIUBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T20:39:19.233858Z","bundle_sha256":"51e25f37db556bf3e09b98f5d60945c46ac4f58f18085f1e90ac28e8ba65a4c6"}}