{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KAFJW2O62P5QIWEDHRJFK37EWJ","short_pith_number":"pith:KAFJW2O6","schema_version":"1.0","canonical_sha256":"500a9b69ded3fb0458833c52556fe4b26d9cab0cd1480654dd7d37d4b30bb8a7","source":{"kind":"arxiv","id":"2605.31522","version":1},"attestation_state":"computed","paper":{"title":"Chem-PerturBridge: a harmonized compendium of small molecule perturbation transcriptomic effects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.GN","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Altynbek Zhubanchaliyev, Artur Sza{\\l}ata, Fabian J. Theis, Maiia Shulman, Matthew Mella, Olga Novitskaia","submitted_at":"2026-05-29T16:38:30Z","abstract_excerpt":"Large perturbation models require training data encompassing chemical, cellular, and assay diversity. Current transcriptomic resources for small-molecule modeling, however, are fragmented across technologies, metadata conventions, controls, doses, and preprocessing pipelines. We introduce Chem-PerturBridge, a harmonized multi-dataset resource comprising over 37k compounds, 136 cellular contexts, and 1.25M transcriptomic samples across eight assay types, with standardized identifiers, metadata, and replicate-aware condition-level effects. We use the resource to evaluate matched-condition agreem"},"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":"2605.31522","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T16:38:30Z","cross_cats_sorted":["q-bio.GN","q-bio.QM"],"title_canon_sha256":"e01361ea7efec3e570ab048246b2442ef77c88b9d2961821dd70764b4460b453","abstract_canon_sha256":"10091731a14dc78d3bbab06f141bf47bf8e393d980a716522ee94d949cf8f979"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:04:10.728284Z","signature_b64":"+kt4a2HY/mJXd7C2HFUAA9lGj+znn5z6w8hoqbT5fuVoSn/xHmnYuvFWUqPvPCUYW9YV8uLHuMm7r/9VUBqACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"500a9b69ded3fb0458833c52556fe4b26d9cab0cd1480654dd7d37d4b30bb8a7","last_reissued_at":"2026-06-01T02:04:10.727502Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:04:10.727502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chem-PerturBridge: a harmonized compendium of small molecule perturbation transcriptomic effects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.GN","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Altynbek Zhubanchaliyev, Artur Sza{\\l}ata, Fabian J. Theis, Maiia Shulman, Matthew Mella, Olga Novitskaia","submitted_at":"2026-05-29T16:38:30Z","abstract_excerpt":"Large perturbation models require training data encompassing chemical, cellular, and assay diversity. Current transcriptomic resources for small-molecule modeling, however, are fragmented across technologies, metadata conventions, controls, doses, and preprocessing pipelines. We introduce Chem-PerturBridge, a harmonized multi-dataset resource comprising over 37k compounds, 136 cellular contexts, and 1.25M transcriptomic samples across eight assay types, with standardized identifiers, metadata, and replicate-aware condition-level effects. We use the resource to evaluate matched-condition agreem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31522","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/2605.31522/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":"2605.31522","created_at":"2026-06-01T02:04:10.727649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31522v1","created_at":"2026-06-01T02:04:10.727649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31522","created_at":"2026-06-01T02:04:10.727649+00:00"},{"alias_kind":"pith_short_12","alias_value":"KAFJW2O62P5Q","created_at":"2026-06-01T02:04:10.727649+00:00"},{"alias_kind":"pith_short_16","alias_value":"KAFJW2O62P5QIWED","created_at":"2026-06-01T02:04:10.727649+00:00"},{"alias_kind":"pith_short_8","alias_value":"KAFJW2O6","created_at":"2026-06-01T02:04:10.727649+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/KAFJW2O62P5QIWEDHRJFK37EWJ","json":"https://pith.science/pith/KAFJW2O62P5QIWEDHRJFK37EWJ.json","graph_json":"https://pith.science/api/pith-number/KAFJW2O62P5QIWEDHRJFK37EWJ/graph.json","events_json":"https://pith.science/api/pith-number/KAFJW2O62P5QIWEDHRJFK37EWJ/events.json","paper":"https://pith.science/paper/KAFJW2O6"},"agent_actions":{"view_html":"https://pith.science/pith/KAFJW2O62P5QIWEDHRJFK37EWJ","download_json":"https://pith.science/pith/KAFJW2O62P5QIWEDHRJFK37EWJ.json","view_paper":"https://pith.science/paper/KAFJW2O6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31522&json=true","fetch_graph":"https://pith.science/api/pith-number/KAFJW2O62P5QIWEDHRJFK37EWJ/graph.json","fetch_events":"https://pith.science/api/pith-number/KAFJW2O62P5QIWEDHRJFK37EWJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KAFJW2O62P5QIWEDHRJFK37EWJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KAFJW2O62P5QIWEDHRJFK37EWJ/action/storage_attestation","attest_author":"https://pith.science/pith/KAFJW2O62P5QIWEDHRJFK37EWJ/action/author_attestation","sign_citation":"https://pith.science/pith/KAFJW2O62P5QIWEDHRJFK37EWJ/action/citation_signature","submit_replication":"https://pith.science/pith/KAFJW2O62P5QIWEDHRJFK37EWJ/action/replication_record"}},"created_at":"2026-06-01T02:04:10.727649+00:00","updated_at":"2026-06-01T02:04:10.727649+00:00"}