{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MBR7VRFMULEVTLDQLAGOYHOBN4","short_pith_number":"pith:MBR7VRFM","schema_version":"1.0","canonical_sha256":"6063fac4aca2c959ac70580cec1dc16f04c443dc95f1242cc241182d1d6cddc4","source":{"kind":"arxiv","id":"2608.10030","version":1},"attestation_state":"computed","paper":{"title":"Automating and Scaling Behavioral Scientific Research on AI Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Denny Borsboom, Fanchen Bu, Hyunjin Hwang, Jaemin Yoo, Jaewan Chun, Jongha Lee, Kijung Shin, Soo Yong Lee, Taekwan Kim, Ziv Ben-Zion","submitted_at":"2026-08-10T01:14:31Z","abstract_excerpt":"As AI agents are increasingly deployed in complex environments, understanding their behaviors becomes critical. Yet behavioral scientific research on AI agents remains manual and labor-intensive. We introduce AEROBAT, the first multi-agent system to automate behavioral scientific research on AI agents. Given an arbitrary target behavior by its user, AEROBAT automatically executes a full pipeline of behavioral scientific research---generating hypotheses about the behavior, designing and executing controlled experiments, making behavioral assessments, analyzing the results, and writing reports. "},"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":"2608.10030","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T01:14:31Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"6da7331de59ccb85bda6ea8339502210a5c0d8c28baac954f714de277744def1","abstract_canon_sha256":"9ea90ab7b0ef06999d94cb18476a29bf9e82b6fe1adbdcf65945af50fa8ec8f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T00:22:37.871889Z","signature_b64":"uRVZ2VJv5+znVQ8BspETp0UCUn6vkaeUzic5JX+PTGjHVhnGUVulCC24e0twO8oCI2VLGe0Ht55QR1EIdYVnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6063fac4aca2c959ac70580cec1dc16f04c443dc95f1242cc241182d1d6cddc4","last_reissued_at":"2026-08-12T00:22:37.870382Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T00:22:37.870382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automating and Scaling Behavioral Scientific Research on AI Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Denny Borsboom, Fanchen Bu, Hyunjin Hwang, Jaemin Yoo, Jaewan Chun, Jongha Lee, Kijung Shin, Soo Yong Lee, Taekwan Kim, Ziv Ben-Zion","submitted_at":"2026-08-10T01:14:31Z","abstract_excerpt":"As AI agents are increasingly deployed in complex environments, understanding their behaviors becomes critical. Yet behavioral scientific research on AI agents remains manual and labor-intensive. We introduce AEROBAT, the first multi-agent system to automate behavioral scientific research on AI agents. Given an arbitrary target behavior by its user, AEROBAT automatically executes a full pipeline of behavioral scientific research---generating hypotheses about the behavior, designing and executing controlled experiments, making behavioral assessments, analyzing the results, and writing reports. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10030","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/2608.10030/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":"2608.10030","created_at":"2026-08-12T00:22:37.873018+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.10030v1","created_at":"2026-08-12T00:22:37.873018+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10030","created_at":"2026-08-12T00:22:37.873018+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBR7VRFMULEV","created_at":"2026-08-12T00:22:37.873018+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBR7VRFMULEVTLDQ","created_at":"2026-08-12T00:22:37.873018+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBR7VRFM","created_at":"2026-08-12T00:22:37.873018+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/MBR7VRFMULEVTLDQLAGOYHOBN4","json":"https://pith.science/pith/MBR7VRFMULEVTLDQLAGOYHOBN4.json","graph_json":"https://pith.science/api/pith-number/MBR7VRFMULEVTLDQLAGOYHOBN4/graph.json","events_json":"https://pith.science/api/pith-number/MBR7VRFMULEVTLDQLAGOYHOBN4/events.json","paper":"https://pith.science/paper/MBR7VRFM"},"agent_actions":{"view_html":"https://pith.science/pith/MBR7VRFMULEVTLDQLAGOYHOBN4","download_json":"https://pith.science/pith/MBR7VRFMULEVTLDQLAGOYHOBN4.json","view_paper":"https://pith.science/paper/MBR7VRFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.10030&json=true","fetch_graph":"https://pith.science/api/pith-number/MBR7VRFMULEVTLDQLAGOYHOBN4/graph.json","fetch_events":"https://pith.science/api/pith-number/MBR7VRFMULEVTLDQLAGOYHOBN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBR7VRFMULEVTLDQLAGOYHOBN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBR7VRFMULEVTLDQLAGOYHOBN4/action/storage_attestation","attest_author":"https://pith.science/pith/MBR7VRFMULEVTLDQLAGOYHOBN4/action/author_attestation","sign_citation":"https://pith.science/pith/MBR7VRFMULEVTLDQLAGOYHOBN4/action/citation_signature","submit_replication":"https://pith.science/pith/MBR7VRFMULEVTLDQLAGOYHOBN4/action/replication_record"}},"created_at":"2026-08-12T00:22:37.873018+00:00","updated_at":"2026-08-12T00:22:37.873018+00:00"}