{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IFBHADW2APERPJNBZYBYOQV4DC","short_pith_number":"pith:IFBHADW2","canonical_record":{"source":{"id":"2310.08511","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T17:06:19Z","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI"],"title_canon_sha256":"46be301ef6219f598174aea41edd9e6497c530e0147e8aaaacad8552ec31b00c","abstract_canon_sha256":"1ce9aa2b5231c3916166cd14327f7b1f953df53c83f52f6efdc33674728658a4"},"schema_version":"1.0"},"canonical_sha256":"4142700eda03c917a5a1ce038742bc188659cc5a984a5016fcfbe7ec3a2e288d","source":{"kind":"arxiv","id":"2310.08511","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08511","created_at":"2026-07-05T07:00:16Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08511v1","created_at":"2026-07-05T07:00:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08511","created_at":"2026-07-05T07:00:16Z"},{"alias_kind":"pith_short_12","alias_value":"IFBHADW2APER","created_at":"2026-07-05T07:00:16Z"},{"alias_kind":"pith_short_16","alias_value":"IFBHADW2APERPJNB","created_at":"2026-07-05T07:00:16Z"},{"alias_kind":"pith_short_8","alias_value":"IFBHADW2","created_at":"2026-07-05T07:00:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IFBHADW2APERPJNBZYBYOQV4DC","target":"record","payload":{"canonical_record":{"source":{"id":"2310.08511","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T17:06:19Z","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI"],"title_canon_sha256":"46be301ef6219f598174aea41edd9e6497c530e0147e8aaaacad8552ec31b00c","abstract_canon_sha256":"1ce9aa2b5231c3916166cd14327f7b1f953df53c83f52f6efdc33674728658a4"},"schema_version":"1.0"},"canonical_sha256":"4142700eda03c917a5a1ce038742bc188659cc5a984a5016fcfbe7ec3a2e288d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:16.645436Z","signature_b64":"O6UHTgKPRmS8VEgrUayXUxxht++XBdMZPVmcEfL8YJyctADKRVlKvSo/GFTMgT10Cfwqx3Dfs2TBffRDK6IeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4142700eda03c917a5a1ce038742bc188659cc5a984a5016fcfbe7ec3a2e288d","last_reissued_at":"2026-07-05T07:00:16.644992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:16.644992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.08511","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:00:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lNTnNKQapk1dmFEy9hWw48xtmhKVgcT1V5yrIsD72F+jktFBWbZPDuW1EbS2fM/BYJXlAZltCJDak8LdHE1oAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:50:27.610911Z"},"content_sha256":"d7cb786a2d4063f48cb9216daad012a05f365d5fa5c2da43138cdb6dd22b69e6","schema_version":"1.0","event_id":"sha256:d7cb786a2d4063f48cb9216daad012a05f365d5fa5c2da43138cdb6dd22b69e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IFBHADW2APERPJNBZYBYOQV4DC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","cs.AI"],"primary_cat":"cs.CL","authors_text":"Bang Liu, Huan Zhang, Santiago Miret, Yu Song","submitted_at":"2023-10-12T17:06:19Z","abstract_excerpt":"We propose an instruction-based process for trustworthy data curation in materials science (MatSci-Instruct), which we then apply to finetune a LLaMa-based language model targeted for materials science (HoneyBee). MatSci-Instruct helps alleviate the scarcity of relevant, high-quality materials science textual data available in the open literature, and HoneyBee is the first billion-parameter language model specialized to materials science. In MatSci-Instruct we improve the trustworthiness of generated data by prompting multiple commercially available large language models for generation with an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08511","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/2310.08511/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:00:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1pZFfhwgUhcNwFLz6XHvS/7SwiXicGOSQqvyagadAULHEYUj1EgQFxgJ4InwKNJpQ5sp8qTMP2wVyC36dSjqBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:50:27.611411Z"},"content_sha256":"21d8bbe09dec32b448a9982a62f26e21ac7753c69ea4fd650ea50d368e507010","schema_version":"1.0","event_id":"sha256:21d8bbe09dec32b448a9982a62f26e21ac7753c69ea4fd650ea50d368e507010"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IFBHADW2APERPJNBZYBYOQV4DC/bundle.json","state_url":"https://pith.science/pith/IFBHADW2APERPJNBZYBYOQV4DC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IFBHADW2APERPJNBZYBYOQV4DC/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":"2026-08-06T07:50:27Z","links":{"resolver":"https://pith.science/pith/IFBHADW2APERPJNBZYBYOQV4DC","bundle":"https://pith.science/pith/IFBHADW2APERPJNBZYBYOQV4DC/bundle.json","state":"https://pith.science/pith/IFBHADW2APERPJNBZYBYOQV4DC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IFBHADW2APERPJNBZYBYOQV4DC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IFBHADW2APERPJNBZYBYOQV4DC","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":"1ce9aa2b5231c3916166cd14327f7b1f953df53c83f52f6efdc33674728658a4","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T17:06:19Z","title_canon_sha256":"46be301ef6219f598174aea41edd9e6497c530e0147e8aaaacad8552ec31b00c"},"schema_version":"1.0","source":{"id":"2310.08511","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08511","created_at":"2026-07-05T07:00:16Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08511v1","created_at":"2026-07-05T07:00:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08511","created_at":"2026-07-05T07:00:16Z"},{"alias_kind":"pith_short_12","alias_value":"IFBHADW2APER","created_at":"2026-07-05T07:00:16Z"},{"alias_kind":"pith_short_16","alias_value":"IFBHADW2APERPJNB","created_at":"2026-07-05T07:00:16Z"},{"alias_kind":"pith_short_8","alias_value":"IFBHADW2","created_at":"2026-07-05T07:00:16Z"}],"graph_snapshots":[{"event_id":"sha256:21d8bbe09dec32b448a9982a62f26e21ac7753c69ea4fd650ea50d368e507010","target":"graph","created_at":"2026-07-05T07:00:16Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.08511/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose an instruction-based process for trustworthy data curation in materials science (MatSci-Instruct), which we then apply to finetune a LLaMa-based language model targeted for materials science (HoneyBee). MatSci-Instruct helps alleviate the scarcity of relevant, high-quality materials science textual data available in the open literature, and HoneyBee is the first billion-parameter language model specialized to materials science. In MatSci-Instruct we improve the trustworthiness of generated data by prompting multiple commercially available large language models for generation with an","authors_text":"Bang Liu, Huan Zhang, Santiago Miret, Yu Song","cross_cats":["cond-mat.mtrl-sci","cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T17:06:19Z","title":"HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08511","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d7cb786a2d4063f48cb9216daad012a05f365d5fa5c2da43138cdb6dd22b69e6","target":"record","created_at":"2026-07-05T07:00:16Z","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":"1ce9aa2b5231c3916166cd14327f7b1f953df53c83f52f6efdc33674728658a4","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T17:06:19Z","title_canon_sha256":"46be301ef6219f598174aea41edd9e6497c530e0147e8aaaacad8552ec31b00c"},"schema_version":"1.0","source":{"id":"2310.08511","kind":"arxiv","version":1}},"canonical_sha256":"4142700eda03c917a5a1ce038742bc188659cc5a984a5016fcfbe7ec3a2e288d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4142700eda03c917a5a1ce038742bc188659cc5a984a5016fcfbe7ec3a2e288d","first_computed_at":"2026-07-05T07:00:16.644992Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:16.644992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O6UHTgKPRmS8VEgrUayXUxxht++XBdMZPVmcEfL8YJyctADKRVlKvSo/GFTMgT10Cfwqx3Dfs2TBffRDK6IeAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:16.645436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.08511","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7cb786a2d4063f48cb9216daad012a05f365d5fa5c2da43138cdb6dd22b69e6","sha256:21d8bbe09dec32b448a9982a62f26e21ac7753c69ea4fd650ea50d368e507010"],"state_sha256":"3ed43d2f886957ce655a24d26a47bb9cd02463fff675d01d66f83b8aa68b8c96"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p61w/2CVyiaWTSFrt5RBCbddnJB/2GR5ZgviQGXZHOloZzWw4OdkboK7XcoMt/1xcml9SrPbY5MDy7nNtp/VAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:50:27.615112Z","bundle_sha256":"2f4c6fa28d542990ab8102193732ab8f17548f2ca0d71551bb1eec348e9a2d08"}}