{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NNF6RDRM7XP6OORZJHC3EJUDHW","short_pith_number":"pith:NNF6RDRM","schema_version":"1.0","canonical_sha256":"6b4be88e2cfddfe73a3949c5b226833db8847a4785266409d221475eb53ee841","source":{"kind":"arxiv","id":"2301.12031","version":1},"attestation_state":"computed","paper":{"title":"Context Matters: A Strategy to Pre-train Language Model for Science Education","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lei Liu, Tianming Liu, Xiaoming Zhai, Xinyu He, Zhengliang Liu","submitted_at":"2023-01-27T23:50:16Z","abstract_excerpt":"This study aims at improving the performance of scoring student responses in science education automatically. BERT-based language models have shown significant superiority over traditional NLP models in various language-related tasks. However, science writing of students, including argumentation and explanation, is domain-specific. In addition, the language used by students is different from the language in journals and Wikipedia, which are training sources of BERT and its existing variants. All these suggest that a domain-specific model pre-trained using science education data may improve mod"},"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":false},"canonical_record":{"source":{"id":"2301.12031","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-01-27T23:50:16Z","cross_cats_sorted":[],"title_canon_sha256":"e80942e209de883c014515becd0062313b130d225951ee29d5fa601a4882c1a0","abstract_canon_sha256":"df43d19deade53a8456bef59c4c1220d04cf4c4d903b36b55db9016e35ffa9c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:09.050878Z","signature_b64":"cfKbQ8mHjplahUIBqjg11X/zOgtCqFhiLebQN4l3fpqxioaSV3hO/F7IWopAj4vH9+h+BGlrhFXf9TSzj7HBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b4be88e2cfddfe73a3949c5b226833db8847a4785266409d221475eb53ee841","last_reissued_at":"2026-07-05T07:14:09.050388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:09.050388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context Matters: A Strategy to Pre-train Language Model for Science Education","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lei Liu, Tianming Liu, Xiaoming Zhai, Xinyu He, Zhengliang Liu","submitted_at":"2023-01-27T23:50:16Z","abstract_excerpt":"This study aims at improving the performance of scoring student responses in science education automatically. BERT-based language models have shown significant superiority over traditional NLP models in various language-related tasks. However, science writing of students, including argumentation and explanation, is domain-specific. In addition, the language used by students is different from the language in journals and Wikipedia, which are training sources of BERT and its existing variants. All these suggest that a domain-specific model pre-trained using science education data may improve mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12031","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/2301.12031/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2301.12031","created_at":"2026-07-05T07:14:09.050449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.12031v1","created_at":"2026-07-05T07:14:09.050449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12031","created_at":"2026-07-05T07:14:09.050449+00:00"},{"alias_kind":"pith_short_12","alias_value":"NNF6RDRM7XP6","created_at":"2026-07-05T07:14:09.050449+00:00"},{"alias_kind":"pith_short_16","alias_value":"NNF6RDRM7XP6OORZ","created_at":"2026-07-05T07:14:09.050449+00:00"},{"alias_kind":"pith_short_8","alias_value":"NNF6RDRM","created_at":"2026-07-05T07:14:09.050449+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.04497","citing_title":"Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NNF6RDRM7XP6OORZJHC3EJUDHW","json":"https://pith.science/pith/NNF6RDRM7XP6OORZJHC3EJUDHW.json","graph_json":"https://pith.science/api/pith-number/NNF6RDRM7XP6OORZJHC3EJUDHW/graph.json","events_json":"https://pith.science/api/pith-number/NNF6RDRM7XP6OORZJHC3EJUDHW/events.json","paper":"https://pith.science/paper/NNF6RDRM"},"agent_actions":{"view_html":"https://pith.science/pith/NNF6RDRM7XP6OORZJHC3EJUDHW","download_json":"https://pith.science/pith/NNF6RDRM7XP6OORZJHC3EJUDHW.json","view_paper":"https://pith.science/paper/NNF6RDRM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.12031&json=true","fetch_graph":"https://pith.science/api/pith-number/NNF6RDRM7XP6OORZJHC3EJUDHW/graph.json","fetch_events":"https://pith.science/api/pith-number/NNF6RDRM7XP6OORZJHC3EJUDHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NNF6RDRM7XP6OORZJHC3EJUDHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NNF6RDRM7XP6OORZJHC3EJUDHW/action/storage_attestation","attest_author":"https://pith.science/pith/NNF6RDRM7XP6OORZJHC3EJUDHW/action/author_attestation","sign_citation":"https://pith.science/pith/NNF6RDRM7XP6OORZJHC3EJUDHW/action/citation_signature","submit_replication":"https://pith.science/pith/NNF6RDRM7XP6OORZJHC3EJUDHW/action/replication_record"}},"created_at":"2026-07-05T07:14:09.050449+00:00","updated_at":"2026-07-05T07:14:09.050449+00:00"}