{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BHOGF3DGCUPLN6W7RBMXZZT5JG","short_pith_number":"pith:BHOGF3DG","canonical_record":{"source":{"id":"2604.20824","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-22T17:49:00Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"d8d7d67437b8958eae7c614d023e275f3c6851726c9edd4e520178e542e6934b","abstract_canon_sha256":"0c662f0868bb436522218cbdc555502301333d9cf7bc180f5be8a8225b07efde"},"schema_version":"1.0"},"canonical_sha256":"09dc62ec66151eb6fadf88597ce67d4987786b9ea5621a1259c27b1786fe4980","source":{"kind":"arxiv","id":"2604.20824","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.20824","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"arxiv_version","alias_value":"2604.20824v2","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.20824","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"pith_short_12","alias_value":"BHOGF3DGCUPL","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"pith_short_16","alias_value":"BHOGF3DGCUPLN6W7","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"pith_short_8","alias_value":"BHOGF3DG","created_at":"2026-06-23T03:13:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BHOGF3DGCUPLN6W7RBMXZZT5JG","target":"record","payload":{"canonical_record":{"source":{"id":"2604.20824","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-22T17:49:00Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"d8d7d67437b8958eae7c614d023e275f3c6851726c9edd4e520178e542e6934b","abstract_canon_sha256":"0c662f0868bb436522218cbdc555502301333d9cf7bc180f5be8a8225b07efde"},"schema_version":"1.0"},"canonical_sha256":"09dc62ec66151eb6fadf88597ce67d4987786b9ea5621a1259c27b1786fe4980","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:57.403406Z","signature_b64":"anhdTUUPHHxuyuFF4cNKs2vSbh6tDvi42IncWhO80nIB1Ac+QISYZXfyTn3B2LPnhl8NoWz5UvNGF0kM9q5iCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09dc62ec66151eb6fadf88597ce67d4987786b9ea5621a1259c27b1786fe4980","last_reissued_at":"2026-06-23T03:13:57.403003Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:57.403003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.20824","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":"2026-06-23T03:13:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eY7uHvDP1tB6fcDfUcmTLjT29ZzHA2Muy/a0E1bjxoR2aR4IZijrUdyprVklQse9LeQ4MYmgS65Z3trFzGwUBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T10:36:30.519546Z"},"content_sha256":"816d6d08719438b7a14fb5114c1ae02b1534fc1a0623aaec3889e95b412ce800","schema_version":"1.0","event_id":"sha256:816d6d08719438b7a14fb5114c1ae02b1534fc1a0623aaec3889e95b412ce800"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BHOGF3DGCUPLN6W7RBMXZZT5JG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stabilizing In-Context Multi-Source Domain Adaptation for Biomedical Images Through Controls","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Negative control samples present in every batch let meta-learning adapt models to new experimental conditions and close the domain gap in biomedical imaging.","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Ana Sanchez-Fernandez, G\\\"unter Klambauer, Thomas Pinetz, Werner Zellinger","submitted_at":"2026-04-22T17:49:00Z","abstract_excerpt":"Biomedical imaging data presents enormous potential for deep learning models to predict invaluable properties, such as diseases and drug effects. However, unavoidable alterations of the technical conditions cause batch effects: variations between groups of samples that are not due to any biological signal of interest. Batch effects greatly hinder the generalization abilities of deep learning models, preventing their practical use in the real world. Unsupervised Domain Adaptation (UDA) methods have been proposed to mitigate batch effects, but they usually assume that the data is comprised of on"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We are the first to show that meta-learning approaches close the domain gap by achieving 0.935 ± 0.018.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Negative control samples are present in every experimental batch by design and serve as stable, unperturbed context for adaptation without introducing their own bias or domain shift.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Meta-learning with in-context control samples closes the domain gap for mechanism-of-action classification, raising accuracy on new batches from 0.862 to 0.935 on the JUMP-CP dataset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Negative control samples present in every batch let meta-learning adapt models to new experimental conditions and close the domain gap in biomedical imaging.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"27da065bcefdd71dbba6e7a6efbb11e210774987dbf49685f48347a5ad4ec060"},"source":{"id":"2604.20824","kind":"arxiv","version":2},"verdict":{"id":"5377c3cf-a3d4-49a0-a07a-5b42823d0dec","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T00:02:51.914285Z","strongest_claim":"We are the first to show that meta-learning approaches close the domain gap by achieving 0.935 ± 0.018.","one_line_summary":"Meta-learning with in-context control samples closes the domain gap for mechanism-of-action classification, raising accuracy on new batches from 0.862 to 0.935 on the JUMP-CP dataset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Negative control samples are present in every experimental batch by design and serve as stable, unperturbed context for adaptation without introducing their own bias or domain shift.","pith_extraction_headline":"Negative control samples present in every batch let meta-learning adapt models to new experimental conditions and close the domain gap in biomedical imaging."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.20824/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T13:40:35.164642Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T01:33:12.248542Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"fb65f93925335e6766311385e2a5bc1834b3dd443c1485636fa00973634334cd"},"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":"5377c3cf-a3d4-49a0-a07a-5b42823d0dec"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T03:13:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"91eAoqgBXsRWVXodO8wECNNJheX1gzSb5qjJNlPJTdkD1peH5K/T5K7bFxvLqJV/2+ypmBiBmzSiFAH4cEXyBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T10:36:30.520024Z"},"content_sha256":"5ec3da9790a860a056f2e48edccfca2a37d46ee63374761a8dac8ae330f47747","schema_version":"1.0","event_id":"sha256:5ec3da9790a860a056f2e48edccfca2a37d46ee63374761a8dac8ae330f47747"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BHOGF3DGCUPLN6W7RBMXZZT5JG/bundle.json","state_url":"https://pith.science/pith/BHOGF3DGCUPLN6W7RBMXZZT5JG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BHOGF3DGCUPLN6W7RBMXZZT5JG/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":"2026-07-05T10:36:30Z","links":{"resolver":"https://pith.science/pith/BHOGF3DGCUPLN6W7RBMXZZT5JG","bundle":"https://pith.science/pith/BHOGF3DGCUPLN6W7RBMXZZT5JG/bundle.json","state":"https://pith.science/pith/BHOGF3DGCUPLN6W7RBMXZZT5JG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BHOGF3DGCUPLN6W7RBMXZZT5JG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BHOGF3DGCUPLN6W7RBMXZZT5JG","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":"0c662f0868bb436522218cbdc555502301333d9cf7bc180f5be8a8225b07efde","cross_cats_sorted":["q-bio.QM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-22T17:49:00Z","title_canon_sha256":"d8d7d67437b8958eae7c614d023e275f3c6851726c9edd4e520178e542e6934b"},"schema_version":"1.0","source":{"id":"2604.20824","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.20824","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"arxiv_version","alias_value":"2604.20824v2","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.20824","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"pith_short_12","alias_value":"BHOGF3DGCUPL","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"pith_short_16","alias_value":"BHOGF3DGCUPLN6W7","created_at":"2026-06-23T03:13:57Z"},{"alias_kind":"pith_short_8","alias_value":"BHOGF3DG","created_at":"2026-06-23T03:13:57Z"}],"graph_snapshots":[{"event_id":"sha256:5ec3da9790a860a056f2e48edccfca2a37d46ee63374761a8dac8ae330f47747","target":"graph","created_at":"2026-06-23T03:13:57Z","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":"We are the first to show that meta-learning approaches close the domain gap by achieving 0.935 ± 0.018."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"Negative control samples are present in every experimental batch by design and serve as stable, unperturbed context for adaptation without introducing their own bias or domain shift."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Meta-learning with in-context control samples closes the domain gap for mechanism-of-action classification, raising accuracy on new batches from 0.862 to 0.935 on the JUMP-CP dataset."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Negative control samples present in every batch let meta-learning adapt models to new experimental conditions and close the domain gap in biomedical imaging."}],"snapshot_sha256":"27da065bcefdd71dbba6e7a6efbb11e210774987dbf49685f48347a5ad4ec060"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-21T13:40:35.164642Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-20T01:33:12.248542Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.20824/integrity.json","findings":[],"snapshot_sha256":"fb65f93925335e6766311385e2a5bc1834b3dd443c1485636fa00973634334cd","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Biomedical imaging data presents enormous potential for deep learning models to predict invaluable properties, such as diseases and drug effects. However, unavoidable alterations of the technical conditions cause batch effects: variations between groups of samples that are not due to any biological signal of interest. Batch effects greatly hinder the generalization abilities of deep learning models, preventing their practical use in the real world. Unsupervised Domain Adaptation (UDA) methods have been proposed to mitigate batch effects, but they usually assume that the data is comprised of on","authors_text":"Ana Sanchez-Fernandez, G\\\"unter Klambauer, Thomas Pinetz, Werner Zellinger","cross_cats":["q-bio.QM"],"headline":"Negative control samples present in every batch let meta-learning adapt models to new experimental conditions and close the domain gap in biomedical imaging.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-22T17:49:00Z","title":"Stabilizing In-Context Multi-Source Domain Adaptation for Biomedical Images Through Controls"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.20824","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T00:02:51.914285Z","id":"5377c3cf-a3d4-49a0-a07a-5b42823d0dec","model_set":{"reader":"grok-4.3"},"one_line_summary":"Meta-learning with in-context control samples closes the domain gap for mechanism-of-action classification, raising accuracy on new batches from 0.862 to 0.935 on the JUMP-CP dataset.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Negative control samples present in every batch let meta-learning adapt models to new experimental conditions and close the domain gap in biomedical imaging.","strongest_claim":"We are the first to show that meta-learning approaches close the domain gap by achieving 0.935 ± 0.018.","weakest_assumption":"Negative control samples are present in every experimental batch by design and serve as stable, unperturbed context for adaptation without introducing their own bias or domain shift."}},"verdict_id":"5377c3cf-a3d4-49a0-a07a-5b42823d0dec"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:816d6d08719438b7a14fb5114c1ae02b1534fc1a0623aaec3889e95b412ce800","target":"record","created_at":"2026-06-23T03:13:57Z","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":"0c662f0868bb436522218cbdc555502301333d9cf7bc180f5be8a8225b07efde","cross_cats_sorted":["q-bio.QM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-22T17:49:00Z","title_canon_sha256":"d8d7d67437b8958eae7c614d023e275f3c6851726c9edd4e520178e542e6934b"},"schema_version":"1.0","source":{"id":"2604.20824","kind":"arxiv","version":2}},"canonical_sha256":"09dc62ec66151eb6fadf88597ce67d4987786b9ea5621a1259c27b1786fe4980","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09dc62ec66151eb6fadf88597ce67d4987786b9ea5621a1259c27b1786fe4980","first_computed_at":"2026-06-23T03:13:57.403003Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:13:57.403003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"anhdTUUPHHxuyuFF4cNKs2vSbh6tDvi42IncWhO80nIB1Ac+QISYZXfyTn3B2LPnhl8NoWz5UvNGF0kM9q5iCw==","signature_status":"signed_v1","signed_at":"2026-06-23T03:13:57.403406Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.20824","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:816d6d08719438b7a14fb5114c1ae02b1534fc1a0623aaec3889e95b412ce800","sha256:5ec3da9790a860a056f2e48edccfca2a37d46ee63374761a8dac8ae330f47747"],"state_sha256":"640722ad8bf168d51ac385c012c36091a838adeda7899a47b86490b73bef4014"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KKm8dzYY7v54RG/fdB7xvPqBTbpcr1nb7CkThUAxiZWZi6OQ/IJHOzPG29NRF9kBbpu4X+vyVEp4/DG/LohHBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T10:36:30.522358Z","bundle_sha256":"9e7bd9c2a1161bc1193609ff5b373928e1ed68ac59a5b179c77546f5f9a8876d"}}