{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SPJOPGXU2W3KJMQ3VD7KFSNEAR","short_pith_number":"pith:SPJOPGXU","schema_version":"1.0","canonical_sha256":"93d2e79af4d5b6a4b21ba8fea2c9a40443046f085fefba8ce68f941030845e53","source":{"kind":"arxiv","id":"2606.07718","version":1},"attestation_state":"computed","paper":{"title":"A case study of evaluating AI agents on a neuroscience data-to-discovery pipeline","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Alice A. Robie, Ethan Lin, Jennifer J. Sun, Kai A. Horstmann, Kristin Branson","submitted_at":"2026-06-05T15:38:18Z","abstract_excerpt":"Agentic AI tools offer a promising path to automating software development bottlenecks in scientific research pipelines, particularly for stages that take domain experts days to months to build, where scientists care about correctness and robustness, not implementation details. We present an empirical study of general-purpose coding agents on a fly optogenetics data-to-discovery pipeline. We assess agents on tasks substantially larger than existing benchmarks, datasets orders of magnitude bigger, and evaluation criteria grounded in domain expert standards. We show that agents can solve several"},"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":"2606.07718","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-05T15:38:18Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"be77c553190d42643e2be1a12dca05d8eba35c7e65c39f840aadf6ca510ba0fc","abstract_canon_sha256":"2eb98e2aec970647a5a1a2ccbe8cd60a71ae7d2b9751475e9f83811bb80c0996"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:50.172589Z","signature_b64":"YAX87ggFyc/3hN/sTa4iwwm1HFFoTzcWrnmlFuUEBmH+1ugeKCyjNiTPRxpc2clBQlqyreFlqpXBVW62c8buCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93d2e79af4d5b6a4b21ba8fea2c9a40443046f085fefba8ce68f941030845e53","last_reissued_at":"2026-06-09T01:04:50.172178Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:50.172178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A case study of evaluating AI agents on a neuroscience data-to-discovery pipeline","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Alice A. Robie, Ethan Lin, Jennifer J. Sun, Kai A. Horstmann, Kristin Branson","submitted_at":"2026-06-05T15:38:18Z","abstract_excerpt":"Agentic AI tools offer a promising path to automating software development bottlenecks in scientific research pipelines, particularly for stages that take domain experts days to months to build, where scientists care about correctness and robustness, not implementation details. We present an empirical study of general-purpose coding agents on a fly optogenetics data-to-discovery pipeline. We assess agents on tasks substantially larger than existing benchmarks, datasets orders of magnitude bigger, and evaluation criteria grounded in domain expert standards. We show that agents can solve several"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07718","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/2606.07718/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":"2606.07718","created_at":"2026-06-09T01:04:50.172241+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07718v1","created_at":"2026-06-09T01:04:50.172241+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07718","created_at":"2026-06-09T01:04:50.172241+00:00"},{"alias_kind":"pith_short_12","alias_value":"SPJOPGXU2W3K","created_at":"2026-06-09T01:04:50.172241+00:00"},{"alias_kind":"pith_short_16","alias_value":"SPJOPGXU2W3KJMQ3","created_at":"2026-06-09T01:04:50.172241+00:00"},{"alias_kind":"pith_short_8","alias_value":"SPJOPGXU","created_at":"2026-06-09T01:04:50.172241+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/SPJOPGXU2W3KJMQ3VD7KFSNEAR","json":"https://pith.science/pith/SPJOPGXU2W3KJMQ3VD7KFSNEAR.json","graph_json":"https://pith.science/api/pith-number/SPJOPGXU2W3KJMQ3VD7KFSNEAR/graph.json","events_json":"https://pith.science/api/pith-number/SPJOPGXU2W3KJMQ3VD7KFSNEAR/events.json","paper":"https://pith.science/paper/SPJOPGXU"},"agent_actions":{"view_html":"https://pith.science/pith/SPJOPGXU2W3KJMQ3VD7KFSNEAR","download_json":"https://pith.science/pith/SPJOPGXU2W3KJMQ3VD7KFSNEAR.json","view_paper":"https://pith.science/paper/SPJOPGXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07718&json=true","fetch_graph":"https://pith.science/api/pith-number/SPJOPGXU2W3KJMQ3VD7KFSNEAR/graph.json","fetch_events":"https://pith.science/api/pith-number/SPJOPGXU2W3KJMQ3VD7KFSNEAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SPJOPGXU2W3KJMQ3VD7KFSNEAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SPJOPGXU2W3KJMQ3VD7KFSNEAR/action/storage_attestation","attest_author":"https://pith.science/pith/SPJOPGXU2W3KJMQ3VD7KFSNEAR/action/author_attestation","sign_citation":"https://pith.science/pith/SPJOPGXU2W3KJMQ3VD7KFSNEAR/action/citation_signature","submit_replication":"https://pith.science/pith/SPJOPGXU2W3KJMQ3VD7KFSNEAR/action/replication_record"}},"created_at":"2026-06-09T01:04:50.172241+00:00","updated_at":"2026-06-09T01:04:50.172241+00:00"}