{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NAIWJV5T3OTIAPR236GFNEF5UM","short_pith_number":"pith:NAIWJV5T","schema_version":"1.0","canonical_sha256":"681164d7b3dba6803e3adf8c5690bda314453bc7f4b57ac5e22c30b452ca49f7","source":{"kind":"arxiv","id":"2603.27146","version":3},"attestation_state":"computed","paper":{"title":"Learning to Predict Future-Aligned Research Proposals with Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Tuning language models on past research data improves their ability to forecast future-aligned research proposals.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haofei Yu, Heng Ji, Heng Wang, Jiashuo Sun, Jiawei Han, Pengcheng Jiang, Zhiyi Shi","submitted_at":"2026-03-28T05:41:15Z","abstract_excerpt":"Large language models (LLMs) are increasingly used to assist ideation in research, but evaluating the quality of LLM-generated research proposals remains difficult: novelty and soundness are hard to measure automatically, and large-scale human evaluation is costly. We propose a verifiable alternative by reframing proposal generation as a time-sliced scientific forecasting problem. Given a research question and inspiring papers available before a cutoff time, the model generates a structured proposal and is evaluated by whether it anticipates research directions that appear in papers published "},"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":true},"canonical_record":{"source":{"id":"2603.27146","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-28T05:41:15Z","cross_cats_sorted":[],"title_canon_sha256":"62778adf0200f2921e3fed3605c1962c537526af6a758f24a8872ce1cf6c1cde","abstract_canon_sha256":"ed901b210b9f3c46cff3cab48342a42ffc0d06299b857cea1597ca8e8770804e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:04:57.433772Z","signature_b64":"Z28eYJ9ckqLiypTSvXW/k179rRcbvr8FTOc6OjKfAOb42/dXLCKBOKsgS3yTFeaABSB8G33Vw/CCRY0voMojCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"681164d7b3dba6803e3adf8c5690bda314453bc7f4b57ac5e22c30b452ca49f7","last_reissued_at":"2026-05-27T01:04:57.433251Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:04:57.433251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Predict Future-Aligned Research Proposals with Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Tuning language models on past research data improves their ability to forecast future-aligned research proposals.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haofei Yu, Heng Ji, Heng Wang, Jiashuo Sun, Jiawei Han, Pengcheng Jiang, Zhiyi Shi","submitted_at":"2026-03-28T05:41:15Z","abstract_excerpt":"Large language models (LLMs) are increasingly used to assist ideation in research, but evaluating the quality of LLM-generated research proposals remains difficult: novelty and soundness are hard to measure automatically, and large-scale human evaluation is costly. We propose a verifiable alternative by reframing proposal generation as a time-sliced scientific forecasting problem. Given a research question and inspiring papers available before a cutoff time, the model generates a structured proposal and is evaluated by whether it anticipates research directions that appear in papers published "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Across Llama-3.1 and Qwen2.5 models, future-aligned tuning improves future alignment over unaligned baselines (up to +10.6% overall FAS), and domain-expert human evaluation corroborates improved proposal quality. Finally, we demonstrate practical impact by implementing two model-generated proposals with a code agent, obtaining 4.17% accuracy gain on MATH from a new prompting strategy and consistent improvements for a novel model-merging method.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That semantic similarity between a generated proposal and future published papers, measured via retrieval and LLM-based scoring, serves as a valid proxy for the proposal's novelty, soundness, and overall quality.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LLMs fine-tuned on time-sliced paper data generate proposals with up to 10.6% higher Future Alignment Score against actual later publications, with human experts and real implementations confirming gains.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Tuning language models on past research data improves their ability to forecast future-aligned research proposals.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"de301f198b833a235497909a7f175d4319ad3333875495cc360e3176c2cebfad"},"source":{"id":"2603.27146","kind":"arxiv","version":3},"verdict":{"id":"e11188c2-b7b8-4aa3-8bcf-881160bfcb3e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T22:58:13.114798Z","strongest_claim":"Across Llama-3.1 and Qwen2.5 models, future-aligned tuning improves future alignment over unaligned baselines (up to +10.6% overall FAS), and domain-expert human evaluation corroborates improved proposal quality. Finally, we demonstrate practical impact by implementing two model-generated proposals with a code agent, obtaining 4.17% accuracy gain on MATH from a new prompting strategy and consistent improvements for a novel model-merging method.","one_line_summary":"LLMs fine-tuned on time-sliced paper data generate proposals with up to 10.6% higher Future Alignment Score against actual later publications, with human experts and real implementations confirming gains.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That semantic similarity between a generated proposal and future published papers, measured via retrieval and LLM-based scoring, serves as a valid proxy for the proposal's novelty, soundness, and overall quality.","pith_extraction_headline":"Tuning language models on past research data improves their ability to forecast future-aligned research proposals."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.27146/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":1,"snapshot_sha256":"cfdb198fe15a5424f1e4a066ca804f9019bba4e98a9853799a01ac1079ca3b37"},"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":"2603.27146","created_at":"2026-05-27T01:04:57.433326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.27146v3","created_at":"2026-05-27T01:04:57.433326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.27146","created_at":"2026-05-27T01:04:57.433326+00:00"},{"alias_kind":"pith_short_12","alias_value":"NAIWJV5T3OTI","created_at":"2026-05-27T01:04:57.433326+00:00"},{"alias_kind":"pith_short_16","alias_value":"NAIWJV5T3OTIAPR2","created_at":"2026-05-27T01:04:57.433326+00:00"},{"alias_kind":"pith_short_8","alias_value":"NAIWJV5T","created_at":"2026-05-27T01:04:57.433326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NAIWJV5T3OTIAPR236GFNEF5UM","json":"https://pith.science/pith/NAIWJV5T3OTIAPR236GFNEF5UM.json","graph_json":"https://pith.science/api/pith-number/NAIWJV5T3OTIAPR236GFNEF5UM/graph.json","events_json":"https://pith.science/api/pith-number/NAIWJV5T3OTIAPR236GFNEF5UM/events.json","paper":"https://pith.science/paper/NAIWJV5T"},"agent_actions":{"view_html":"https://pith.science/pith/NAIWJV5T3OTIAPR236GFNEF5UM","download_json":"https://pith.science/pith/NAIWJV5T3OTIAPR236GFNEF5UM.json","view_paper":"https://pith.science/paper/NAIWJV5T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.27146&json=true","fetch_graph":"https://pith.science/api/pith-number/NAIWJV5T3OTIAPR236GFNEF5UM/graph.json","fetch_events":"https://pith.science/api/pith-number/NAIWJV5T3OTIAPR236GFNEF5UM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NAIWJV5T3OTIAPR236GFNEF5UM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NAIWJV5T3OTIAPR236GFNEF5UM/action/storage_attestation","attest_author":"https://pith.science/pith/NAIWJV5T3OTIAPR236GFNEF5UM/action/author_attestation","sign_citation":"https://pith.science/pith/NAIWJV5T3OTIAPR236GFNEF5UM/action/citation_signature","submit_replication":"https://pith.science/pith/NAIWJV5T3OTIAPR236GFNEF5UM/action/replication_record"}},"created_at":"2026-05-27T01:04:57.433326+00:00","updated_at":"2026-05-27T01:04:57.433326+00:00"}