{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YV226XEX4ZNTAIG2O7ZHJBBCHC","short_pith_number":"pith:YV226XEX","schema_version":"1.0","canonical_sha256":"c575af5c97e65b3020da77f2748422389e227f937869456f1de7ed09b9e211f1","source":{"kind":"arxiv","id":"2504.09544","version":3},"attestation_state":"computed","paper":{"title":"Integrating chemical structures as treatments improves representations of microscopy images for morphological profiling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE","cs.CV"],"primary_cat":"cs.LG","authors_text":"Alex X. Lu, Ava P. Amini, David Alvarez-Melis, Emre Hayir, Lester Mackey, Neil Tenenholtz, Yemin Yu, Ying Wei","submitted_at":"2025-04-13T12:27:21Z","abstract_excerpt":"Recent advances in self-supervised deep learning have improved our ability to quantify cellular morphological changes in high-throughput microscopy screens, a process known as morphological profiling. However, most current methods only learn from images, despite many screens being inherently multimodal, as they involve both a chemical or genetic perturbation as well as an image-based readout. We hypothesized that incorporating chemical compound structures during self-supervised pre-training could improve learned representations of images from high-throughput microscopy screens. We introduce a "},"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":"2504.09544","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-13T12:27:21Z","cross_cats_sorted":["cs.CE","cs.CV"],"title_canon_sha256":"24022ce06aeb25eaa6a1f2e841e0c9829b520a31166e34a1bdf10c6616bf66b0","abstract_canon_sha256":"b8c3cb43de1e523a115ac7802612e91b9c1660c75e6fa8da15423cafb6bc545e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:19.235927Z","signature_b64":"aYExk+n1O1SezRB6GHqv52kOJUzA22l2JaZAIDkOvAo3IvUDHDWS6HJwdLEcR7Uha/l0EGi93GlEtMWmYWuDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c575af5c97e65b3020da77f2748422389e227f937869456f1de7ed09b9e211f1","last_reissued_at":"2026-05-20T00:00:19.234996Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:19.234996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Integrating chemical structures as treatments improves representations of microscopy images for morphological profiling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE","cs.CV"],"primary_cat":"cs.LG","authors_text":"Alex X. Lu, Ava P. Amini, David Alvarez-Melis, Emre Hayir, Lester Mackey, Neil Tenenholtz, Yemin Yu, Ying Wei","submitted_at":"2025-04-13T12:27:21Z","abstract_excerpt":"Recent advances in self-supervised deep learning have improved our ability to quantify cellular morphological changes in high-throughput microscopy screens, a process known as morphological profiling. However, most current methods only learn from images, despite many screens being inherently multimodal, as they involve both a chemical or genetic perturbation as well as an image-based readout. We hypothesized that incorporating chemical compound structures during self-supervised pre-training could improve learned representations of images from high-throughput microscopy screens. We introduce a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09544","kind":"arxiv","version":3},"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/2504.09544/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":"2504.09544","created_at":"2026-05-20T00:00:19.235082+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.09544v3","created_at":"2026-05-20T00:00:19.235082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09544","created_at":"2026-05-20T00:00:19.235082+00:00"},{"alias_kind":"pith_short_12","alias_value":"YV226XEX4ZNT","created_at":"2026-05-20T00:00:19.235082+00:00"},{"alias_kind":"pith_short_16","alias_value":"YV226XEX4ZNTAIG2","created_at":"2026-05-20T00:00:19.235082+00:00"},{"alias_kind":"pith_short_8","alias_value":"YV226XEX","created_at":"2026-05-20T00:00:19.235082+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.15383","citing_title":"MorphoHELM: A Comprehensive Benchmark for Evaluating Representations for Microscopy-Based Morphology Assays","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YV226XEX4ZNTAIG2O7ZHJBBCHC","json":"https://pith.science/pith/YV226XEX4ZNTAIG2O7ZHJBBCHC.json","graph_json":"https://pith.science/api/pith-number/YV226XEX4ZNTAIG2O7ZHJBBCHC/graph.json","events_json":"https://pith.science/api/pith-number/YV226XEX4ZNTAIG2O7ZHJBBCHC/events.json","paper":"https://pith.science/paper/YV226XEX"},"agent_actions":{"view_html":"https://pith.science/pith/YV226XEX4ZNTAIG2O7ZHJBBCHC","download_json":"https://pith.science/pith/YV226XEX4ZNTAIG2O7ZHJBBCHC.json","view_paper":"https://pith.science/paper/YV226XEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.09544&json=true","fetch_graph":"https://pith.science/api/pith-number/YV226XEX4ZNTAIG2O7ZHJBBCHC/graph.json","fetch_events":"https://pith.science/api/pith-number/YV226XEX4ZNTAIG2O7ZHJBBCHC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YV226XEX4ZNTAIG2O7ZHJBBCHC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YV226XEX4ZNTAIG2O7ZHJBBCHC/action/storage_attestation","attest_author":"https://pith.science/pith/YV226XEX4ZNTAIG2O7ZHJBBCHC/action/author_attestation","sign_citation":"https://pith.science/pith/YV226XEX4ZNTAIG2O7ZHJBBCHC/action/citation_signature","submit_replication":"https://pith.science/pith/YV226XEX4ZNTAIG2O7ZHJBBCHC/action/replication_record"}},"created_at":"2026-05-20T00:00:19.235082+00:00","updated_at":"2026-05-20T00:00:19.235082+00:00"}