{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BWDDQEWXQU34NQ3SF7B4VGVDH6","short_pith_number":"pith:BWDDQEWX","schema_version":"1.0","canonical_sha256":"0d863812d78537c6c3722fc3ca9aa33f88d00ea37e0d4d737a324d151c93ae92","source":{"kind":"arxiv","id":"2606.00644","version":1},"attestation_state":"computed","paper":{"title":"ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haojie Yin, Qiuyu Tian, Yingce Xia, Youyong Kong, Zequn Liu","submitted_at":"2026-05-30T09:41:26Z","abstract_excerpt":"AI research often requires decisions before future evidence exists: which bottleneck to attack, which direction to pursue, or where a project should be positioned. We introduce ForeSci, a temporally controlled benchmark for evaluating whether LLM agents can make such forward-looking research judgements from historical evidence. ForeSci contains 500 tasks across four fast-moving AI domains and four decision families. Each task is paired with a cutoff-aligned offline knowledge base; post-cutoff papers are hidden during generation and used only for validation. To avoid random future-event predict"},"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":"2606.00644","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-30T09:41:26Z","cross_cats_sorted":[],"title_canon_sha256":"976790653c0faaeaa4745907495e0018b95ef5140fcdb41cd8b9f3f5f318e4bf","abstract_canon_sha256":"c5b765ab59de62a1073835183552daf2c44de9cbb55199bdd9a8d2b52f891eff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:00.759426Z","signature_b64":"TuFJKGdVwuB09Wh+Eiy00ufF62W+XGgJML0KUThXmyi4DtS/QgOkVaxHycqLyKdzrPAG8HGDOvlYbYEqGpB8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d863812d78537c6c3722fc3ca9aa33f88d00ea37e0d4d737a324d151c93ae92","last_reissued_at":"2026-06-02T01:04:00.758885Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:00.758885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haojie Yin, Qiuyu Tian, Yingce Xia, Youyong Kong, Zequn Liu","submitted_at":"2026-05-30T09:41:26Z","abstract_excerpt":"AI research often requires decisions before future evidence exists: which bottleneck to attack, which direction to pursue, or where a project should be positioned. We introduce ForeSci, a temporally controlled benchmark for evaluating whether LLM agents can make such forward-looking research judgements from historical evidence. ForeSci contains 500 tasks across four fast-moving AI domains and four decision families. Each task is paired with a cutoff-aligned offline knowledge base; post-cutoff papers are hidden during generation and used only for validation. To avoid random future-event predict"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00644","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/2606.00644/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":"2606.00644","created_at":"2026-06-02T01:04:00.758970+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00644v1","created_at":"2026-06-02T01:04:00.758970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00644","created_at":"2026-06-02T01:04:00.758970+00:00"},{"alias_kind":"pith_short_12","alias_value":"BWDDQEWXQU34","created_at":"2026-06-02T01:04:00.758970+00:00"},{"alias_kind":"pith_short_16","alias_value":"BWDDQEWXQU34NQ3S","created_at":"2026-06-02T01:04:00.758970+00:00"},{"alias_kind":"pith_short_8","alias_value":"BWDDQEWX","created_at":"2026-06-02T01:04:00.758970+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/BWDDQEWXQU34NQ3SF7B4VGVDH6","json":"https://pith.science/pith/BWDDQEWXQU34NQ3SF7B4VGVDH6.json","graph_json":"https://pith.science/api/pith-number/BWDDQEWXQU34NQ3SF7B4VGVDH6/graph.json","events_json":"https://pith.science/api/pith-number/BWDDQEWXQU34NQ3SF7B4VGVDH6/events.json","paper":"https://pith.science/paper/BWDDQEWX"},"agent_actions":{"view_html":"https://pith.science/pith/BWDDQEWXQU34NQ3SF7B4VGVDH6","download_json":"https://pith.science/pith/BWDDQEWXQU34NQ3SF7B4VGVDH6.json","view_paper":"https://pith.science/paper/BWDDQEWX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00644&json=true","fetch_graph":"https://pith.science/api/pith-number/BWDDQEWXQU34NQ3SF7B4VGVDH6/graph.json","fetch_events":"https://pith.science/api/pith-number/BWDDQEWXQU34NQ3SF7B4VGVDH6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BWDDQEWXQU34NQ3SF7B4VGVDH6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BWDDQEWXQU34NQ3SF7B4VGVDH6/action/storage_attestation","attest_author":"https://pith.science/pith/BWDDQEWXQU34NQ3SF7B4VGVDH6/action/author_attestation","sign_citation":"https://pith.science/pith/BWDDQEWXQU34NQ3SF7B4VGVDH6/action/citation_signature","submit_replication":"https://pith.science/pith/BWDDQEWXQU34NQ3SF7B4VGVDH6/action/replication_record"}},"created_at":"2026-06-02T01:04:00.758970+00:00","updated_at":"2026-06-02T01:04:00.758970+00:00"}