{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VRYWF2W3IDLF4PKOBKNWIAVMN4","short_pith_number":"pith:VRYWF2W3","schema_version":"1.0","canonical_sha256":"ac7162eadb40d65e3d4e0a9b6402ac6f3e4df006c9ff15fdf5a6bec5a8d8bbff","source":{"kind":"arxiv","id":"2509.06986","version":1},"attestation_state":"computed","paper":{"title":"CellPainTR: Generalizable Representation Learning for Cross-Dataset Cell Painting Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cedric Caruzzo, Jong Chul Ye","submitted_at":"2025-09-02T03:30:07Z","abstract_excerpt":"Large-scale biological discovery requires integrating massive, heterogeneous datasets like those from the JUMP Cell Painting consortium, but technical batch effects and a lack of generalizable models remain critical roadblocks. To address this, we introduce CellPainTR, a Transformer-based architecture designed to learn foundational representations of cellular morphology that are robust to batch effects. Unlike traditional methods that require retraining on new data, CellPainTR's design, featuring source-specific context tokens, allows for effective out-of-distribution (OOD) generalization to e"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.06986","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T03:30:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"58d9af9dfe2c87c289b0eb1be19e4a0c0f5ed8b6300d997299d3deb5bb843636","abstract_canon_sha256":"257382cf7778a1045d0cc099969988cc4c84e2a99ff3e3406ce451793e56e3b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:13.509440Z","signature_b64":"dK4YaFnQrkzmLTzSR+B/7dsrQy+i6tHfkjWnFSKWAaS7E+E4zNEJcZPwrzwSYityVLdfg5im9MabPe1UEoaoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac7162eadb40d65e3d4e0a9b6402ac6f3e4df006c9ff15fdf5a6bec5a8d8bbff","last_reissued_at":"2026-07-05T12:07:13.508921Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:13.508921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CellPainTR: Generalizable Representation Learning for Cross-Dataset Cell Painting Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cedric Caruzzo, Jong Chul Ye","submitted_at":"2025-09-02T03:30:07Z","abstract_excerpt":"Large-scale biological discovery requires integrating massive, heterogeneous datasets like those from the JUMP Cell Painting consortium, but technical batch effects and a lack of generalizable models remain critical roadblocks. To address this, we introduce CellPainTR, a Transformer-based architecture designed to learn foundational representations of cellular morphology that are robust to batch effects. Unlike traditional methods that require retraining on new data, CellPainTR's design, featuring source-specific context tokens, allows for effective out-of-distribution (OOD) generalization to e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06986","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/2509.06986/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.06986","created_at":"2026-07-05T12:07:13.509002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06986v1","created_at":"2026-07-05T12:07:13.509002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06986","created_at":"2026-07-05T12:07:13.509002+00:00"},{"alias_kind":"pith_short_12","alias_value":"VRYWF2W3IDLF","created_at":"2026-07-05T12:07:13.509002+00:00"},{"alias_kind":"pith_short_16","alias_value":"VRYWF2W3IDLF4PKO","created_at":"2026-07-05T12:07:13.509002+00:00"},{"alias_kind":"pith_short_8","alias_value":"VRYWF2W3","created_at":"2026-07-05T12:07:13.509002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VRYWF2W3IDLF4PKOBKNWIAVMN4","json":"https://pith.science/pith/VRYWF2W3IDLF4PKOBKNWIAVMN4.json","graph_json":"https://pith.science/api/pith-number/VRYWF2W3IDLF4PKOBKNWIAVMN4/graph.json","events_json":"https://pith.science/api/pith-number/VRYWF2W3IDLF4PKOBKNWIAVMN4/events.json","paper":"https://pith.science/paper/VRYWF2W3"},"agent_actions":{"view_html":"https://pith.science/pith/VRYWF2W3IDLF4PKOBKNWIAVMN4","download_json":"https://pith.science/pith/VRYWF2W3IDLF4PKOBKNWIAVMN4.json","view_paper":"https://pith.science/paper/VRYWF2W3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06986&json=true","fetch_graph":"https://pith.science/api/pith-number/VRYWF2W3IDLF4PKOBKNWIAVMN4/graph.json","fetch_events":"https://pith.science/api/pith-number/VRYWF2W3IDLF4PKOBKNWIAVMN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VRYWF2W3IDLF4PKOBKNWIAVMN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VRYWF2W3IDLF4PKOBKNWIAVMN4/action/storage_attestation","attest_author":"https://pith.science/pith/VRYWF2W3IDLF4PKOBKNWIAVMN4/action/author_attestation","sign_citation":"https://pith.science/pith/VRYWF2W3IDLF4PKOBKNWIAVMN4/action/citation_signature","submit_replication":"https://pith.science/pith/VRYWF2W3IDLF4PKOBKNWIAVMN4/action/replication_record"}},"created_at":"2026-07-05T12:07:13.509002+00:00","updated_at":"2026-07-05T12:07:13.509002+00:00"}