{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NAIWJV5T3OTIAPR236GFNEF5UM","short_pith_number":"pith:NAIWJV5T","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"},"canonical_sha256":"681164d7b3dba6803e3adf8c5690bda314453bc7f4b57ac5e22c30b452ca49f7","source":{"kind":"arxiv","id":"2603.27146","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.27146","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2603.27146v3","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.27146","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"NAIWJV5T3OTI","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"NAIWJV5T3OTIAPR2","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"NAIWJV5T","created_at":"2026-05-27T01:04:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NAIWJV5T3OTIAPR236GFNEF5UM","target":"record","payload":{"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"},"canonical_sha256":"681164d7b3dba6803e3adf8c5690bda314453bc7f4b57ac5e22c30b452ca49f7","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"},"source_kind":"arxiv","source_id":"2603.27146","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:04:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yltHszBAIN5IjIv5sZxg60kmr3ZcwVPjFBbRnxd8p79hx6ISGL6IM3FA/4GwiByWENZ4LsVNwg6ifCOg6m66CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T19:35:47.388593Z"},"content_sha256":"081c1e0dfaae54c70f6303ba5f4740d5c8f09bd8d49cf256cc276c77ba968ff8","schema_version":"1.0","event_id":"sha256:081c1e0dfaae54c70f6303ba5f4740d5c8f09bd8d49cf256cc276c77ba968ff8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NAIWJV5T3OTIAPR236GFNEF5UM","target":"graph","payload":{"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"},"verdict_id":"e11188c2-b7b8-4aa3-8bcf-881160bfcb3e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:04:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E9edZFkTG/WZo7IOU9AMPbKj6OmspN+RWXsA4GOkaFhiOJOlDYGeiaGwBkK6jt6m1uiycFZ0aJxVm5uUJGEcBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T19:35:47.389467Z"},"content_sha256":"e3baf4a4b395244bcf3285d0b19e7aa8a7cb96fc44e3b85e698311de02f00909","schema_version":"1.0","event_id":"sha256:e3baf4a4b395244bcf3285d0b19e7aa8a7cb96fc44e3b85e698311de02f00909"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NAIWJV5T3OTIAPR236GFNEF5UM/bundle.json","state_url":"https://pith.science/pith/NAIWJV5T3OTIAPR236GFNEF5UM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NAIWJV5T3OTIAPR236GFNEF5UM/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":"2026-06-08T19:35:47Z","links":{"resolver":"https://pith.science/pith/NAIWJV5T3OTIAPR236GFNEF5UM","bundle":"https://pith.science/pith/NAIWJV5T3OTIAPR236GFNEF5UM/bundle.json","state":"https://pith.science/pith/NAIWJV5T3OTIAPR236GFNEF5UM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NAIWJV5T3OTIAPR236GFNEF5UM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NAIWJV5T3OTIAPR236GFNEF5UM","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":"ed901b210b9f3c46cff3cab48342a42ffc0d06299b857cea1597ca8e8770804e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-28T05:41:15Z","title_canon_sha256":"62778adf0200f2921e3fed3605c1962c537526af6a758f24a8872ce1cf6c1cde"},"schema_version":"1.0","source":{"id":"2603.27146","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.27146","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2603.27146v3","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.27146","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"NAIWJV5T3OTI","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"NAIWJV5T3OTIAPR2","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"NAIWJV5T","created_at":"2026-05-27T01:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:e3baf4a4b395244bcf3285d0b19e7aa8a7cb96fc44e3b85e698311de02f00909","target":"graph","created_at":"2026-05-27T01:04:57Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Tuning language models on past research data improves their ability to forecast future-aligned research proposals."}],"snapshot_sha256":"de301f198b833a235497909a7f175d4319ad3333875495cc360e3176c2cebfad"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"cfdb198fe15a5424f1e4a066ca804f9019bba4e98a9853799a01ac1079ca3b37"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.27146/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Haofei Yu, Heng Ji, Heng Wang, Jiashuo Sun, Jiawei Han, Pengcheng Jiang, Zhiyi Shi","cross_cats":[],"headline":"Tuning language models on past research data improves their ability to forecast future-aligned research proposals.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-28T05:41:15Z","title":"Learning to Predict Future-Aligned Research Proposals with Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.27146","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-14T22:58:13.114798Z","id":"e11188c2-b7b8-4aa3-8bcf-881160bfcb3e","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Tuning language models on past research data improves their ability to forecast future-aligned research proposals.","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.","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."}},"verdict_id":"e11188c2-b7b8-4aa3-8bcf-881160bfcb3e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:081c1e0dfaae54c70f6303ba5f4740d5c8f09bd8d49cf256cc276c77ba968ff8","target":"record","created_at":"2026-05-27T01:04:57Z","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":"ed901b210b9f3c46cff3cab48342a42ffc0d06299b857cea1597ca8e8770804e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-28T05:41:15Z","title_canon_sha256":"62778adf0200f2921e3fed3605c1962c537526af6a758f24a8872ce1cf6c1cde"},"schema_version":"1.0","source":{"id":"2603.27146","kind":"arxiv","version":3}},"canonical_sha256":"681164d7b3dba6803e3adf8c5690bda314453bc7f4b57ac5e22c30b452ca49f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"681164d7b3dba6803e3adf8c5690bda314453bc7f4b57ac5e22c30b452ca49f7","first_computed_at":"2026-05-27T01:04:57.433251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:04:57.433251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z28eYJ9ckqLiypTSvXW/k179rRcbvr8FTOc6OjKfAOb42/dXLCKBOKsgS3yTFeaABSB8G33Vw/CCRY0voMojCg==","signature_status":"signed_v1","signed_at":"2026-05-27T01:04:57.433772Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.27146","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:081c1e0dfaae54c70f6303ba5f4740d5c8f09bd8d49cf256cc276c77ba968ff8","sha256:e3baf4a4b395244bcf3285d0b19e7aa8a7cb96fc44e3b85e698311de02f00909"],"state_sha256":"ebe98f55e279704ab3057ad5f4b9b0620b0ec4d9ebf2fd603b208175d831fbbd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"anf8cSod/U6vFb4PU9uWvMtiAlQimk1CQKvCWzCD9OCjxgIkMQ9DtDGK92sVRnM19MORQOmaQGErGK4eCxr2Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T19:35:47.393635Z","bundle_sha256":"8baffd3a87eebb8102094ffa9b139998c211a60a5005ed1aa9b08f79d8776c85"}}