{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N6RK5ZJLXYLB4COZOL7CABDXKV","short_pith_number":"pith:N6RK5ZJL","schema_version":"1.0","canonical_sha256":"6fa2aee52bbe161e09d972fe200477556d79a171bfef36ce61427c2bfda06e7f","source":{"kind":"arxiv","id":"2408.09574","version":1},"attestation_state":"computed","paper":{"title":"PhysBERT: A Text Embedding Model for Physics Scientific Literature","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"physics.comp-ph","authors_text":"Andrea Pollastro, Jo\\~ao Montenegro, Thorsten Hellert","submitted_at":"2024-08-18T19:18:12Z","abstract_excerpt":"The specialized language and complex concepts in physics pose significant challenges for information extraction through Natural Language Processing (NLP). Central to effective NLP applications is the text embedding model, which converts text into dense vector representations for efficient information retrieval and semantic analysis. In this work, we introduce PhysBERT, the first physics-specific text embedding model. Pre-trained on a curated corpus of 1.2 million arXiv physics papers and fine-tuned with supervised data, PhysBERT outperforms leading general-purpose models on physics-specific ta"},"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":"2408.09574","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.comp-ph","submitted_at":"2024-08-18T19:18:12Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"599ffd7cfbbf2dea9897159c519d0fc49b0132595a2ddbe2d3b26a10e9e21d40","abstract_canon_sha256":"4fc97040ad6e8085c383fa6abc74f2d01b8ab335a52193e6fabf8fa2d9f370ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:34.280204Z","signature_b64":"cgVvFyhqXKz6LthWN0aInIUKx1IedKFdjds/szwByyyjJ/Ct+9Imh3iDXHhV7Lf0Zdb98xW76gM4U3CIcIpEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fa2aee52bbe161e09d972fe200477556d79a171bfef36ce61427c2bfda06e7f","last_reissued_at":"2026-07-05T08:56:34.279798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:34.279798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PhysBERT: A Text Embedding Model for Physics Scientific Literature","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"physics.comp-ph","authors_text":"Andrea Pollastro, Jo\\~ao Montenegro, Thorsten Hellert","submitted_at":"2024-08-18T19:18:12Z","abstract_excerpt":"The specialized language and complex concepts in physics pose significant challenges for information extraction through Natural Language Processing (NLP). Central to effective NLP applications is the text embedding model, which converts text into dense vector representations for efficient information retrieval and semantic analysis. In this work, we introduce PhysBERT, the first physics-specific text embedding model. Pre-trained on a curated corpus of 1.2 million arXiv physics papers and fine-tuned with supervised data, PhysBERT outperforms leading general-purpose models on physics-specific ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09574","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/2408.09574/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":"2408.09574","created_at":"2026-07-05T08:56:34.279853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09574v1","created_at":"2026-07-05T08:56:34.279853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09574","created_at":"2026-07-05T08:56:34.279853+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6RK5ZJLXYLB","created_at":"2026-07-05T08:56:34.279853+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6RK5ZJLXYLB4COZ","created_at":"2026-07-05T08:56:34.279853+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6RK5ZJL","created_at":"2026-07-05T08:56:34.279853+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00391","citing_title":"Trajectories of Change: Approaches for Tracking Knowledge Evolution","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N6RK5ZJLXYLB4COZOL7CABDXKV","json":"https://pith.science/pith/N6RK5ZJLXYLB4COZOL7CABDXKV.json","graph_json":"https://pith.science/api/pith-number/N6RK5ZJLXYLB4COZOL7CABDXKV/graph.json","events_json":"https://pith.science/api/pith-number/N6RK5ZJLXYLB4COZOL7CABDXKV/events.json","paper":"https://pith.science/paper/N6RK5ZJL"},"agent_actions":{"view_html":"https://pith.science/pith/N6RK5ZJLXYLB4COZOL7CABDXKV","download_json":"https://pith.science/pith/N6RK5ZJLXYLB4COZOL7CABDXKV.json","view_paper":"https://pith.science/paper/N6RK5ZJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09574&json=true","fetch_graph":"https://pith.science/api/pith-number/N6RK5ZJLXYLB4COZOL7CABDXKV/graph.json","fetch_events":"https://pith.science/api/pith-number/N6RK5ZJLXYLB4COZOL7CABDXKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6RK5ZJLXYLB4COZOL7CABDXKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6RK5ZJLXYLB4COZOL7CABDXKV/action/storage_attestation","attest_author":"https://pith.science/pith/N6RK5ZJLXYLB4COZOL7CABDXKV/action/author_attestation","sign_citation":"https://pith.science/pith/N6RK5ZJLXYLB4COZOL7CABDXKV/action/citation_signature","submit_replication":"https://pith.science/pith/N6RK5ZJLXYLB4COZOL7CABDXKV/action/replication_record"}},"created_at":"2026-07-05T08:56:34.279853+00:00","updated_at":"2026-07-05T08:56:34.279853+00:00"}