{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3VRZX6QL735JDHIEDH2TBLNUXT","short_pith_number":"pith:3VRZX6QL","canonical_record":{"source":{"id":"2606.24162","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T05:30:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ab96de4052e6ba5e9f5fae7735c0affbc4cf114d9fe78530838f2deb7c2e7cce","abstract_canon_sha256":"9af7f80c50e46e9198754b9f8e24ec3f0166403fafb257aa4cdce349c30b79a2"},"schema_version":"1.0"},"canonical_sha256":"dd639bfa0bfefa919d0419f530adb4bce9c62782a84fd9496721a6bd2aa77d2a","source":{"kind":"arxiv","id":"2606.24162","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24162","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24162v1","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24162","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"pith_short_12","alias_value":"3VRZX6QL735J","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"pith_short_16","alias_value":"3VRZX6QL735JDHIE","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"pith_short_8","alias_value":"3VRZX6QL","created_at":"2026-06-24T01:14:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3VRZX6QL735JDHIEDH2TBLNUXT","target":"record","payload":{"canonical_record":{"source":{"id":"2606.24162","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T05:30:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ab96de4052e6ba5e9f5fae7735c0affbc4cf114d9fe78530838f2deb7c2e7cce","abstract_canon_sha256":"9af7f80c50e46e9198754b9f8e24ec3f0166403fafb257aa4cdce349c30b79a2"},"schema_version":"1.0"},"canonical_sha256":"dd639bfa0bfefa919d0419f530adb4bce9c62782a84fd9496721a6bd2aa77d2a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:43.429824Z","signature_b64":"WLKpFso+xuuWqe0P5stwOA94oc3kYGdtNNao7XRYEaWtPR1vgQHOWhBXmoxRcnRUp4npzZCOhB4Fmwnl+/QECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd639bfa0bfefa919d0419f530adb4bce9c62782a84fd9496721a6bd2aa77d2a","last_reissued_at":"2026-06-24T01:14:43.429023Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:43.429023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.24162","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-24T01:14:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H3BOxzH49R1a9oGg9Hu88onNoSGWLCgBZFmp/sO5wYFQ4y8tk6+biMy+5EC/rvh874DAhwvJfonXytSoDYqXCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T18:33:41.522708Z"},"content_sha256":"2ec73906c274be2e63440ca9385cdabcbc64d1d6976275fe83d93b6758ea5412","schema_version":"1.0","event_id":"sha256:2ec73906c274be2e63440ca9385cdabcbc64d1d6976275fe83d93b6758ea5412"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3VRZX6QL735JDHIEDH2TBLNUXT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jin Huang, Matthew O. Jackson, Qiaozhu Mei, Walter Yuan, Wanli Song, Xingjian Zhang, Yutong Xie","submitted_at":"2026-06-23T05:30:54Z","abstract_excerpt":"Foundation models have been increasingly applied to behavioral science domains such as psychology, sociology, and economics. While these models show promise in individual tasks such as survey response prediction and human-subject experiment simulation, there remains no systematic understanding of how well they perform across diverse behavioral science tasks, contexts, and populations. We introduce BehaviorBench, a comprehensive benchmark that evaluates foundation models along four core capabilities: (1) behavior prediction and simulation, (2) strategic decision-making, (3) subject-trait infere"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24162","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/2606.24162/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-24T01:14:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xYJjq5i5fNCKbrge7TEZcVt23p/xCqLsaWf56BjGhpfe4hOppJ4XG/ldobCSr8MC6jMdU5770/JnIkVA97n5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T18:33:41.523080Z"},"content_sha256":"9dca53dd75cf5fd2a2e6e89790a013468d44afa0651c0e7b75ede24013a94179","schema_version":"1.0","event_id":"sha256:9dca53dd75cf5fd2a2e6e89790a013468d44afa0651c0e7b75ede24013a94179"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3VRZX6QL735JDHIEDH2TBLNUXT/bundle.json","state_url":"https://pith.science/pith/3VRZX6QL735JDHIEDH2TBLNUXT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3VRZX6QL735JDHIEDH2TBLNUXT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-27T18:33:41Z","links":{"resolver":"https://pith.science/pith/3VRZX6QL735JDHIEDH2TBLNUXT","bundle":"https://pith.science/pith/3VRZX6QL735JDHIEDH2TBLNUXT/bundle.json","state":"https://pith.science/pith/3VRZX6QL735JDHIEDH2TBLNUXT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3VRZX6QL735JDHIEDH2TBLNUXT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3VRZX6QL735JDHIEDH2TBLNUXT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9af7f80c50e46e9198754b9f8e24ec3f0166403fafb257aa4cdce349c30b79a2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T05:30:54Z","title_canon_sha256":"ab96de4052e6ba5e9f5fae7735c0affbc4cf114d9fe78530838f2deb7c2e7cce"},"schema_version":"1.0","source":{"id":"2606.24162","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24162","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24162v1","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24162","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"pith_short_12","alias_value":"3VRZX6QL735J","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"pith_short_16","alias_value":"3VRZX6QL735JDHIE","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"pith_short_8","alias_value":"3VRZX6QL","created_at":"2026-06-24T01:14:43Z"}],"graph_snapshots":[{"event_id":"sha256:9dca53dd75cf5fd2a2e6e89790a013468d44afa0651c0e7b75ede24013a94179","target":"graph","created_at":"2026-06-24T01:14:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.24162/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Foundation models have been increasingly applied to behavioral science domains such as psychology, sociology, and economics. While these models show promise in individual tasks such as survey response prediction and human-subject experiment simulation, there remains no systematic understanding of how well they perform across diverse behavioral science tasks, contexts, and populations. We introduce BehaviorBench, a comprehensive benchmark that evaluates foundation models along four core capabilities: (1) behavior prediction and simulation, (2) strategic decision-making, (3) subject-trait infere","authors_text":"Jin Huang, Matthew O. Jackson, Qiaozhu Mei, Walter Yuan, Wanli Song, Xingjian Zhang, Yutong Xie","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T05:30:54Z","title":"BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24162","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2ec73906c274be2e63440ca9385cdabcbc64d1d6976275fe83d93b6758ea5412","target":"record","created_at":"2026-06-24T01:14:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9af7f80c50e46e9198754b9f8e24ec3f0166403fafb257aa4cdce349c30b79a2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T05:30:54Z","title_canon_sha256":"ab96de4052e6ba5e9f5fae7735c0affbc4cf114d9fe78530838f2deb7c2e7cce"},"schema_version":"1.0","source":{"id":"2606.24162","kind":"arxiv","version":1}},"canonical_sha256":"dd639bfa0bfefa919d0419f530adb4bce9c62782a84fd9496721a6bd2aa77d2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd639bfa0bfefa919d0419f530adb4bce9c62782a84fd9496721a6bd2aa77d2a","first_computed_at":"2026-06-24T01:14:43.429023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:43.429023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WLKpFso+xuuWqe0P5stwOA94oc3kYGdtNNao7XRYEaWtPR1vgQHOWhBXmoxRcnRUp4npzZCOhB4Fmwnl+/QECg==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:43.429824Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24162","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ec73906c274be2e63440ca9385cdabcbc64d1d6976275fe83d93b6758ea5412","sha256:9dca53dd75cf5fd2a2e6e89790a013468d44afa0651c0e7b75ede24013a94179"],"state_sha256":"95c34c2ee8083dd31798e88d79cb35b48a6093457e3483d5e89ba29ae08e5dfc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j7bQsZrp3cXxjTWLIeMmhuBN3hxEkx8+WsfxUie7eop1ZTwovY7TkH6h2XIxhzuE1LCAYA3q7WfpPh+cu0UZCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T18:33:41.525246Z","bundle_sha256":"814363e08c8ed37b5f1f4244e7a8a86bbfdf4ba1a0c9d5b701d26a75e7e6d09e"}}