{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TRIKW7ENTGD6HOKJNB64VKLKOM","short_pith_number":"pith:TRIKW7EN","canonical_record":{"source":{"id":"2508.17567","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-25T00:33:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a1e3f7ad70518817fa55d3bac98d95ce79ead94ebd06888172099dc14386f5d5","abstract_canon_sha256":"6ce6206fc09ab3eed972fec056a0ef5258f450c91d55500344638c3f903293f3"},"schema_version":"1.0"},"canonical_sha256":"9c50ab7c8d9987e3b949687dcaa96a7329282f763efcefacd8a85cc079188883","source":{"kind":"arxiv","id":"2508.17567","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.17567","created_at":"2026-07-05T11:59:21Z"},{"alias_kind":"arxiv_version","alias_value":"2508.17567v2","created_at":"2026-07-05T11:59:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17567","created_at":"2026-07-05T11:59:21Z"},{"alias_kind":"pith_short_12","alias_value":"TRIKW7ENTGD6","created_at":"2026-07-05T11:59:21Z"},{"alias_kind":"pith_short_16","alias_value":"TRIKW7ENTGD6HOKJ","created_at":"2026-07-05T11:59:21Z"},{"alias_kind":"pith_short_8","alias_value":"TRIKW7EN","created_at":"2026-07-05T11:59:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TRIKW7ENTGD6HOKJNB64VKLKOM","target":"record","payload":{"canonical_record":{"source":{"id":"2508.17567","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-25T00:33:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a1e3f7ad70518817fa55d3bac98d95ce79ead94ebd06888172099dc14386f5d5","abstract_canon_sha256":"6ce6206fc09ab3eed972fec056a0ef5258f450c91d55500344638c3f903293f3"},"schema_version":"1.0"},"canonical_sha256":"9c50ab7c8d9987e3b949687dcaa96a7329282f763efcefacd8a85cc079188883","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:21.177737Z","signature_b64":"2BJ0QS6cz9ULxSUTl1rI205hQfqvfcHuANNJLNPNB2Rwlpyh9kDD5b+L5h1ZlIAmaVoiNbMY+8BK6kqO0VjODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c50ab7c8d9987e3b949687dcaa96a7329282f763efcefacd8a85cc079188883","last_reissued_at":"2026-07-05T11:59:21.177145Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:21.177145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.17567","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":"2026-07-05T11:59:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UcaGBedj80mwAzsZ+VlfC1xN/4ZbHwlFrHEy9FE5iHx75Y9XKhMyAkFDnYCeZFct1LbMJCSdy+5p+wqw0iQmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:26:39.526311Z"},"content_sha256":"33518b0a5c5d9a39fae3dde458f28a8a04a2845673bb07709a78e9a80f94a943","schema_version":"1.0","event_id":"sha256:33518b0a5c5d9a39fae3dde458f28a8a04a2845673bb07709a78e9a80f94a943"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TRIKW7ENTGD6HOKJNB64VKLKOM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Optimal Convolutional Transfer Learning Architectures for Breast Lesion Classification and ACL Tear Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aditri Bhagirath, Daniel Frees, Moritz Bolling","submitted_at":"2025-08-25T00:33:43Z","abstract_excerpt":"Modern computer vision models have proven to be highly useful for medical imaging classification and segmentation tasks, but the scarcity of medical imaging data often limits the efficacy of models trained from scratch. Transfer learning has emerged as a pivotal solution to this, enabling the fine-tuning of high-performance models on small data. Mei et al. (2022) found that pre-training CNNs on a large dataset of radiologist-labeled images (RadImageNet) enhanced model performance on downstream tasks compared to ImageNet pretraining. The present work extends Mei et al. (2022) by conducting a co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17567","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.17567/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":"2026-07-05T11:59:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cicd1CuKfc1mZLZf068IIZd8xqW7FozZzpPQoTr4ueoyLTCKRmA6aTEwooouCFUHpMlxwfojOkoEgyPWiwraDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:26:39.527258Z"},"content_sha256":"ebd24edd4fde026ae67f12faf5b49edb9551cc9bf79826c3882d9210816fe329","schema_version":"1.0","event_id":"sha256:ebd24edd4fde026ae67f12faf5b49edb9551cc9bf79826c3882d9210816fe329"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TRIKW7ENTGD6HOKJNB64VKLKOM/bundle.json","state_url":"https://pith.science/pith/TRIKW7ENTGD6HOKJNB64VKLKOM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TRIKW7ENTGD6HOKJNB64VKLKOM/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":"2026-08-09T03:26:39Z","links":{"resolver":"https://pith.science/pith/TRIKW7ENTGD6HOKJNB64VKLKOM","bundle":"https://pith.science/pith/TRIKW7ENTGD6HOKJNB64VKLKOM/bundle.json","state":"https://pith.science/pith/TRIKW7ENTGD6HOKJNB64VKLKOM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TRIKW7ENTGD6HOKJNB64VKLKOM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TRIKW7ENTGD6HOKJNB64VKLKOM","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":"6ce6206fc09ab3eed972fec056a0ef5258f450c91d55500344638c3f903293f3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-25T00:33:43Z","title_canon_sha256":"a1e3f7ad70518817fa55d3bac98d95ce79ead94ebd06888172099dc14386f5d5"},"schema_version":"1.0","source":{"id":"2508.17567","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.17567","created_at":"2026-07-05T11:59:21Z"},{"alias_kind":"arxiv_version","alias_value":"2508.17567v2","created_at":"2026-07-05T11:59:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17567","created_at":"2026-07-05T11:59:21Z"},{"alias_kind":"pith_short_12","alias_value":"TRIKW7ENTGD6","created_at":"2026-07-05T11:59:21Z"},{"alias_kind":"pith_short_16","alias_value":"TRIKW7ENTGD6HOKJ","created_at":"2026-07-05T11:59:21Z"},{"alias_kind":"pith_short_8","alias_value":"TRIKW7EN","created_at":"2026-07-05T11:59:21Z"}],"graph_snapshots":[{"event_id":"sha256:ebd24edd4fde026ae67f12faf5b49edb9551cc9bf79826c3882d9210816fe329","target":"graph","created_at":"2026-07-05T11:59:21Z","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/2508.17567/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern computer vision models have proven to be highly useful for medical imaging classification and segmentation tasks, but the scarcity of medical imaging data often limits the efficacy of models trained from scratch. Transfer learning has emerged as a pivotal solution to this, enabling the fine-tuning of high-performance models on small data. Mei et al. (2022) found that pre-training CNNs on a large dataset of radiologist-labeled images (RadImageNet) enhanced model performance on downstream tasks compared to ImageNet pretraining. The present work extends Mei et al. (2022) by conducting a co","authors_text":"Aditri Bhagirath, Daniel Frees, Moritz Bolling","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-25T00:33:43Z","title":"Towards Optimal Convolutional Transfer Learning Architectures for Breast Lesion Classification and ACL Tear Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17567","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":"sha256:33518b0a5c5d9a39fae3dde458f28a8a04a2845673bb07709a78e9a80f94a943","target":"record","created_at":"2026-07-05T11:59:21Z","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":"6ce6206fc09ab3eed972fec056a0ef5258f450c91d55500344638c3f903293f3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-25T00:33:43Z","title_canon_sha256":"a1e3f7ad70518817fa55d3bac98d95ce79ead94ebd06888172099dc14386f5d5"},"schema_version":"1.0","source":{"id":"2508.17567","kind":"arxiv","version":2}},"canonical_sha256":"9c50ab7c8d9987e3b949687dcaa96a7329282f763efcefacd8a85cc079188883","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c50ab7c8d9987e3b949687dcaa96a7329282f763efcefacd8a85cc079188883","first_computed_at":"2026-07-05T11:59:21.177145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:21.177145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2BJ0QS6cz9ULxSUTl1rI205hQfqvfcHuANNJLNPNB2Rwlpyh9kDD5b+L5h1ZlIAmaVoiNbMY+8BK6kqO0VjODg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:21.177737Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.17567","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33518b0a5c5d9a39fae3dde458f28a8a04a2845673bb07709a78e9a80f94a943","sha256:ebd24edd4fde026ae67f12faf5b49edb9551cc9bf79826c3882d9210816fe329"],"state_sha256":"d1f40ab75138aad5c745c4ef3d007df749714a0d2f324cf5be4941bbb9434af8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BUarQgUfQ740kT5XrrvvOp3r3C+ULibcw7hGkQrmkTj8tXG6fLjsuEijgYK8nDIpBeNh3BogH7hW2+9ppN7RBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:26:39.532707Z","bundle_sha256":"3b7dcc76a7451a013b4543630242e1dde331e7965b4b3a248c8a5643d64dc71b"}}