{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:K6E2MM5DZE7AANNQEGZHTOD7SM","short_pith_number":"pith:K6E2MM5D","canonical_record":{"source":{"id":"2601.16312","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-22T20:39:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"690891f005264361c851591daaa8434dba4a55cccd41566ee0e0daa257756ebb","abstract_canon_sha256":"67d42ed87e302305fc5f7a16d7d99301ce1c15dbaa41f7aaddf44b6b7bd6a9d3"},"schema_version":"1.0"},"canonical_sha256":"5789a633a3c93e0035b021b279b87f93019e84449256715f416c0bebda3274fe","source":{"kind":"arxiv","id":"2601.16312","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:K6E2MM5DZE7AANNQEGZHTOD7SM","target":"record","payload":{"canonical_record":{"source":{"id":"2601.16312","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-22T20:39:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"690891f005264361c851591daaa8434dba4a55cccd41566ee0e0daa257756ebb","abstract_canon_sha256":"67d42ed87e302305fc5f7a16d7d99301ce1c15dbaa41f7aaddf44b6b7bd6a9d3"},"schema_version":"1.0"},"canonical_sha256":"5789a633a3c93e0035b021b279b87f93019e84449256715f416c0bebda3274fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:00.200561Z","signature_b64":"CMi/GemuEaC1wlGnJbCa7d1JeWJG6/Hbwns7YNzLsbP0sNNgP/MMFJYVHWa1CQte1S9ZaIb30Llwo/IOHUWTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5789a633a3c93e0035b021b279b87f93019e84449256715f416c0bebda3274fe","last_reissued_at":"2026-05-17T23:39:00.199888Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:00.199888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.16312","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TEnoU6bDIEL71dezDRL6MtrdhvN9eCFeNvlSy7eHKbVGZI0p3IVugOXtdY9y0uzEYSHgZVd/UuB53aSUd+cvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:17:51.035686Z"},"content_sha256":"b781fff70eede22c77902b6e202c1896d89ca5e31ffb38189226564449c0d716","schema_version":"1.0","event_id":"sha256:b781fff70eede22c77902b6e202c1896d89ca5e31ffb38189226564449c0d716"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:K6E2MM5DZE7AANNQEGZHTOD7SM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Teaching and Evaluating LLMs to Reason About Polymer Design Related Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Small language models trained on PolyBench match or beat larger models on polymer design reasoning tasks.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Benjamin Hsiao, Dikshya Mohanty, Mohammad Saqib Hasan, Niranjan Balasubramanian, Size Zheng, Syed Mostofa Monsur","submitted_at":"2026-01-22T20:39:18Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Small language models trained on PolyBench match or beat larger models on polymer design reasoning tasks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e0017d5f117bfced1a30a9a94f4b66f10767b0397058ed71bedc6e05c5da0f27"},"source":{"id":"2601.16312","kind":"arxiv","version":2},"verdict":{"id":"6a5c5619-10db-4c94-9197-016d580cb279","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T11:31:08.017151Z","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.","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","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.","pith_extraction_headline":"Small language models trained on PolyBench match or beat larger models on polymer design reasoning tasks."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bafe42996f3a0f8bcc9c7d6a962d13e8a8bc0170e8a6d33427bf00128be8f92b"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"6a5c5619-10db-4c94-9197-016d580cb279"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TX50l+hO3pU4WrT9T6/LlLMaK9tlOcjOu9QzoRNL5emvzweDZIs3CTOXfF8YmJbejzBcTN0RxgPOf/JsdVy+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:17:51.036196Z"},"content_sha256":"ab67e7451b923618c2eab2357b9b13dfa4ae40b3c144f40f8358b139cb20d8b0","schema_version":"1.0","event_id":"sha256:ab67e7451b923618c2eab2357b9b13dfa4ae40b3c144f40f8358b139cb20d8b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K6E2MM5DZE7AANNQEGZHTOD7SM/bundle.json","state_url":"https://pith.science/pith/K6E2MM5DZE7AANNQEGZHTOD7SM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K6E2MM5DZE7AANNQEGZHTOD7SM/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":"2026-06-01T05:17:51Z","links":{"resolver":"https://pith.science/pith/K6E2MM5DZE7AANNQEGZHTOD7SM","bundle":"https://pith.science/pith/K6E2MM5DZE7AANNQEGZHTOD7SM/bundle.json","state":"https://pith.science/pith/K6E2MM5DZE7AANNQEGZHTOD7SM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K6E2MM5DZE7AANNQEGZHTOD7SM/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"46GQrPRXeidZXGGO9ljVyIfgbuLa3jyq8OHlo9kZj+CSRcXCxl06ZR76HFe6HrnCijFAwvY1hSFmj7dqmVosCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T05:17:51.039483Z","bundle_sha256":"aa2fbb96e89a6b36d127e7f551c1720f7c75b98ddfe830a2a0f0ef4b103d6278"}}