{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NCZBVNQAWBBSODJS5C7JVTHCSU","short_pith_number":"pith:NCZBVNQA","schema_version":"1.0","canonical_sha256":"68b21ab600b043270d32e8be9acce29538fbb3f81a19c6d3ce66bb6cb257f4d2","source":{"kind":"arxiv","id":"2411.14877","version":1},"attestation_state":"computed","paper":{"title":"Astro-HEP-BERT: A bidirectional language model for studying the meanings of concepts in astrophysics and high energy physics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.hist-ph"],"primary_cat":"cs.CL","authors_text":"Arno Simons","submitted_at":"2024-11-22T11:59:15Z","abstract_excerpt":"I present Astro-HEP-BERT, a transformer-based language model specifically designed for generating contextualized word embeddings (CWEs) to study the meanings of concepts in astrophysics and high-energy physics. Built on a general pretrained BERT model, Astro-HEP-BERT underwent further training over three epochs using the Astro-HEP Corpus, a dataset I curated from 21.84 million paragraphs extracted from more than 600,000 scholarly articles on arXiv, all belonging to at least one of these two scientific domains. The project demonstrates both the effectiveness and feasibility of adapting a bidire"},"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":"2411.14877","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-22T11:59:15Z","cross_cats_sorted":["physics.hist-ph"],"title_canon_sha256":"fccacef72f2fd9257351641132bb88bfa62f839c6e9da9ad4712185c0239f7e7","abstract_canon_sha256":"1daa8ab406f21dcc7a8c177ad11c064208f566b7aefbdcf1ea45cbf780458e2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:13.051385Z","signature_b64":"2ufAaH21AKvrQPQp4vVz46Qxg4OnTSMTGeN70hkli1VUt+Sk0kAdEWHDaVlQ64HaI+Orb0DRzzr58h0yQk3lAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68b21ab600b043270d32e8be9acce29538fbb3f81a19c6d3ce66bb6cb257f4d2","last_reissued_at":"2026-07-05T09:39:13.050958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:13.050958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Astro-HEP-BERT: A bidirectional language model for studying the meanings of concepts in astrophysics and high energy physics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.hist-ph"],"primary_cat":"cs.CL","authors_text":"Arno Simons","submitted_at":"2024-11-22T11:59:15Z","abstract_excerpt":"I present Astro-HEP-BERT, a transformer-based language model specifically designed for generating contextualized word embeddings (CWEs) to study the meanings of concepts in astrophysics and high-energy physics. Built on a general pretrained BERT model, Astro-HEP-BERT underwent further training over three epochs using the Astro-HEP Corpus, a dataset I curated from 21.84 million paragraphs extracted from more than 600,000 scholarly articles on arXiv, all belonging to at least one of these two scientific domains. The project demonstrates both the effectiveness and feasibility of adapting a bidire"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14877","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/2411.14877/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":"2411.14877","created_at":"2026-07-05T09:39:13.051010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14877v1","created_at":"2026-07-05T09:39:13.051010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14877","created_at":"2026-07-05T09:39:13.051010+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCZBVNQAWBBS","created_at":"2026-07-05T09:39:13.051010+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCZBVNQAWBBSODJS","created_at":"2026-07-05T09:39:13.051010+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCZBVNQA","created_at":"2026-07-05T09:39:13.051010+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NCZBVNQAWBBSODJS5C7JVTHCSU","json":"https://pith.science/pith/NCZBVNQAWBBSODJS5C7JVTHCSU.json","graph_json":"https://pith.science/api/pith-number/NCZBVNQAWBBSODJS5C7JVTHCSU/graph.json","events_json":"https://pith.science/api/pith-number/NCZBVNQAWBBSODJS5C7JVTHCSU/events.json","paper":"https://pith.science/paper/NCZBVNQA"},"agent_actions":{"view_html":"https://pith.science/pith/NCZBVNQAWBBSODJS5C7JVTHCSU","download_json":"https://pith.science/pith/NCZBVNQAWBBSODJS5C7JVTHCSU.json","view_paper":"https://pith.science/paper/NCZBVNQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14877&json=true","fetch_graph":"https://pith.science/api/pith-number/NCZBVNQAWBBSODJS5C7JVTHCSU/graph.json","fetch_events":"https://pith.science/api/pith-number/NCZBVNQAWBBSODJS5C7JVTHCSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCZBVNQAWBBSODJS5C7JVTHCSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCZBVNQAWBBSODJS5C7JVTHCSU/action/storage_attestation","attest_author":"https://pith.science/pith/NCZBVNQAWBBSODJS5C7JVTHCSU/action/author_attestation","sign_citation":"https://pith.science/pith/NCZBVNQAWBBSODJS5C7JVTHCSU/action/citation_signature","submit_replication":"https://pith.science/pith/NCZBVNQAWBBSODJS5C7JVTHCSU/action/replication_record"}},"created_at":"2026-07-05T09:39:13.051010+00:00","updated_at":"2026-07-05T09:39:13.051010+00:00"}