{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:K6E2MM5DZE7AANNQEGZHTOD7SM","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":"67d42ed87e302305fc5f7a16d7d99301ce1c15dbaa41f7aaddf44b6b7bd6a9d3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-22T20:39:18Z","title_canon_sha256":"690891f005264361c851591daaa8434dba4a55cccd41566ee0e0daa257756ebb"},"schema_version":"1.0","source":{"id":"2601.16312","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.16312","created_at":"2026-05-17T23:39:00Z"},{"alias_kind":"arxiv_version","alias_value":"2601.16312v2","created_at":"2026-05-17T23:39:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.16312","created_at":"2026-05-17T23:39:00Z"},{"alias_kind":"pith_short_12","alias_value":"K6E2MM5DZE7A","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"K6E2MM5DZE7AANNQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"K6E2MM5D","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:ab67e7451b923618c2eab2357b9b13dfa4ae40b3c144f40f8358b139cb20d8b0","target":"graph","created_at":"2026-05-17T23:39:00Z","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":"small language models (SLMs) with 7B to 14B parameters, trained on PolyBench, outperform similar-sized models and remain competitive with closed-source frontier LLMs on PolyBench's test dataset, while demonstrating performance gains on external polymer benchmarks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The tasks in PolyBench and the underlying knowledge base of 13 million data points accurately represent the knowledge and reasoning demands of real-world polymer design without major gaps, biases, or inaccuracies from the experimental and synthetic sources."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Small 7B-14B parameter language models trained on the new PolyBench dataset for polymer design tasks outperform similar-sized models and compete with large frontier LLMs while improving on external benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Small language models trained on PolyBench match or beat larger models on polymer design reasoning tasks."}],"snapshot_sha256":"e0017d5f117bfced1a30a9a94f4b66f10767b0397058ed71bedc6e05c5da0f27"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bafe42996f3a0f8bcc9c7d6a962d13e8a8bc0170e8a6d33427bf00128be8f92b"},"paper":{"abstract_excerpt":"Research in AI4Science has shown promise in many science applications, including polymer design. However, current LLMs are ineffective in this problem space because: (i) most models lack polymer-specific knowledge, and (ii) existing aligned models have limited coverage of knowledge and capabilities relevant to polymer design. Addressing this, we introduce PolyBench, a large-scale training and test benchmark dataset of more than 125K polymer design-related tasks, leveraging a knowledge base of more than 13 million data points obtained from experimental and synthetic data sources to ensure broad","authors_text":"Benjamin Hsiao, Dikshya Mohanty, Mohammad Saqib Hasan, Niranjan Balasubramanian, Size Zheng, Syed Mostofa Monsur","cross_cats":["cs.AI"],"headline":"Small language models trained on PolyBench match or beat larger models on polymer design reasoning tasks.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-22T20:39:18Z","title":"Teaching and Evaluating LLMs to Reason About Polymer Design Related Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.16312","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T11:31:08.017151Z","id":"6a5c5619-10db-4c94-9197-016d580cb279","model_set":{"reader":"grok-4.3"},"one_line_summary":"Small 7B-14B parameter language models trained on the new PolyBench dataset for polymer design tasks outperform similar-sized models and compete with large frontier LLMs while improving on external benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Small language models trained on PolyBench match or beat larger models on polymer design reasoning tasks.","strongest_claim":"small language models (SLMs) with 7B to 14B parameters, trained on PolyBench, outperform similar-sized models and remain competitive with closed-source frontier LLMs on PolyBench's test dataset, while demonstrating performance gains on external polymer benchmarks.","weakest_assumption":"The tasks in PolyBench and the underlying knowledge base of 13 million data points accurately represent the knowledge and reasoning demands of real-world polymer design without major gaps, biases, or inaccuracies from the experimental and synthetic sources."}},"verdict_id":"6a5c5619-10db-4c94-9197-016d580cb279"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b781fff70eede22c77902b6e202c1896d89ca5e31ffb38189226564449c0d716","target":"record","created_at":"2026-05-17T23:39:00Z","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":"67d42ed87e302305fc5f7a16d7d99301ce1c15dbaa41f7aaddf44b6b7bd6a9d3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-22T20:39:18Z","title_canon_sha256":"690891f005264361c851591daaa8434dba4a55cccd41566ee0e0daa257756ebb"},"schema_version":"1.0","source":{"id":"2601.16312","kind":"arxiv","version":2}},"canonical_sha256":"5789a633a3c93e0035b021b279b87f93019e84449256715f416c0bebda3274fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5789a633a3c93e0035b021b279b87f93019e84449256715f416c0bebda3274fe","first_computed_at":"2026-05-17T23:39:00.199888Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:00.199888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CMi/GemuEaC1wlGnJbCa7d1JeWJG6/Hbwns7YNzLsbP0sNNgP/MMFJYVHWa1CQte1S9ZaIb30Llwo/IOHUWTBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:00.200561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.16312","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b781fff70eede22c77902b6e202c1896d89ca5e31ffb38189226564449c0d716","sha256:ab67e7451b923618c2eab2357b9b13dfa4ae40b3c144f40f8358b139cb20d8b0"],"state_sha256":"edf223e526bc7e3b8c973b7351249f83512efeab55645919e3481fa44f5a321f"}