{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KKSP7VC7PWO6ECJVXGMMAA2WVS","short_pith_number":"pith:KKSP7VC7","schema_version":"1.0","canonical_sha256":"52a4ffd45f7d9de20935b998c00356ac805f05d8918af71e6d52b372989aa383","source":{"kind":"arxiv","id":"2605.28065","version":1},"attestation_state":"computed","paper":{"title":"Verifiable Benchmarking of Long-Horizon Spatial Biology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Harihara Muralidharan, Ian Diks, Kenny Workman, Tim Proctor","submitted_at":"2026-05-27T07:19:18Z","abstract_excerpt":"AI agents are increasingly useful for biological data analysis, but existing benchmarks mostly test broad biological knowledge, executable workflows, or localized analysis steps rather than end-to-end scientific reasoning over spatial measurements. We introduce SpatialBench-Long, a benchmark for long-horizon spatial biology in which agents must recover biological claims from raw or near-raw data and calibrated experimental context without prescribed methods. SpatialBench-Long contains 24 evaluations across primary pancreatic ductal adenocarcinoma (PDAC), engineered glioblastoma organoids and i"},"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":"2605.28065","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T07:19:18Z","cross_cats_sorted":[],"title_canon_sha256":"5e748d1a693f656e0b704e2524baf432d8562191f62cf3b1125c02025880ccbc","abstract_canon_sha256":"cad7d6a021a29f1fd0cb555ccf432322bae40dad775fc1bb842f6a79f4b3eebd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:57.500325Z","signature_b64":"Bm9nO003Gya4IVjZzrbN4JcT7tMg4FEY4ppyDuoWn60ZeosaEnbB6BxucnG7CcZkkeoWdjuMawYg619c2nCkDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52a4ffd45f7d9de20935b998c00356ac805f05d8918af71e6d52b372989aa383","last_reissued_at":"2026-05-28T01:04:57.499893Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:57.499893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Verifiable Benchmarking of Long-Horizon Spatial Biology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Harihara Muralidharan, Ian Diks, Kenny Workman, Tim Proctor","submitted_at":"2026-05-27T07:19:18Z","abstract_excerpt":"AI agents are increasingly useful for biological data analysis, but existing benchmarks mostly test broad biological knowledge, executable workflows, or localized analysis steps rather than end-to-end scientific reasoning over spatial measurements. We introduce SpatialBench-Long, a benchmark for long-horizon spatial biology in which agents must recover biological claims from raw or near-raw data and calibrated experimental context without prescribed methods. SpatialBench-Long contains 24 evaluations across primary pancreatic ductal adenocarcinoma (PDAC), engineered glioblastoma organoids and i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28065","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/2605.28065/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":"2605.28065","created_at":"2026-05-28T01:04:57.499960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28065v1","created_at":"2026-05-28T01:04:57.499960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28065","created_at":"2026-05-28T01:04:57.499960+00:00"},{"alias_kind":"pith_short_12","alias_value":"KKSP7VC7PWO6","created_at":"2026-05-28T01:04:57.499960+00:00"},{"alias_kind":"pith_short_16","alias_value":"KKSP7VC7PWO6ECJV","created_at":"2026-05-28T01:04:57.499960+00:00"},{"alias_kind":"pith_short_8","alias_value":"KKSP7VC7","created_at":"2026-05-28T01:04:57.499960+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.19245","citing_title":"TxBench-PP: Analyzing AI Agent Performance on Small-Molecule Preclinical Pharmacology","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KKSP7VC7PWO6ECJVXGMMAA2WVS","json":"https://pith.science/pith/KKSP7VC7PWO6ECJVXGMMAA2WVS.json","graph_json":"https://pith.science/api/pith-number/KKSP7VC7PWO6ECJVXGMMAA2WVS/graph.json","events_json":"https://pith.science/api/pith-number/KKSP7VC7PWO6ECJVXGMMAA2WVS/events.json","paper":"https://pith.science/paper/KKSP7VC7"},"agent_actions":{"view_html":"https://pith.science/pith/KKSP7VC7PWO6ECJVXGMMAA2WVS","download_json":"https://pith.science/pith/KKSP7VC7PWO6ECJVXGMMAA2WVS.json","view_paper":"https://pith.science/paper/KKSP7VC7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28065&json=true","fetch_graph":"https://pith.science/api/pith-number/KKSP7VC7PWO6ECJVXGMMAA2WVS/graph.json","fetch_events":"https://pith.science/api/pith-number/KKSP7VC7PWO6ECJVXGMMAA2WVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KKSP7VC7PWO6ECJVXGMMAA2WVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KKSP7VC7PWO6ECJVXGMMAA2WVS/action/storage_attestation","attest_author":"https://pith.science/pith/KKSP7VC7PWO6ECJVXGMMAA2WVS/action/author_attestation","sign_citation":"https://pith.science/pith/KKSP7VC7PWO6ECJVXGMMAA2WVS/action/citation_signature","submit_replication":"https://pith.science/pith/KKSP7VC7PWO6ECJVXGMMAA2WVS/action/replication_record"}},"created_at":"2026-05-28T01:04:57.499960+00:00","updated_at":"2026-05-28T01:04:57.499960+00:00"}