{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RZC5SVGGNLHYAUQY57IYVROVS3","short_pith_number":"pith:RZC5SVGG","schema_version":"1.0","canonical_sha256":"8e45d954c66acf805218efd18ac5d596ccde27b535b09c6fa14f27cebf8eb4e6","source":{"kind":"arxiv","id":"2305.04177","version":1},"attestation_state":"computed","paper":{"title":"MIReAD: Simple Method for Learning High-quality Representations from Scientific Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexander Brechalov, Anastasia Razdaibiedina","submitted_at":"2023-05-07T03:29:55Z","abstract_excerpt":"Learning semantically meaningful representations from scientific documents can facilitate academic literature search and improve performance of recommendation systems. Pre-trained language models have been shown to learn rich textual representations, yet they cannot provide powerful document-level representations for scientific articles. We propose MIReAD, a simple method that learns high-quality representations of scientific papers by fine-tuning transformer model to predict the target journal class based on the abstract. We train MIReAD on more than 500,000 PubMed and arXiv abstracts across "},"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":"2305.04177","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-07T03:29:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"349a1bdba6d6692856afe51f9077c25167419f9d4733ce0f3312cb4f0ca8b6b6","abstract_canon_sha256":"8d2d6afca206707cf52df19a7317c81c472c0d97a324b66f44723e562943c552"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:45.459944Z","signature_b64":"Lt/R40aQ/GmwYgqmSjaKsQIO+saVTA7/waVJQbLnh+jtAJYbwZ8UzqTc3MVpQDKyvAbElZbz67o0DcatyBwbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e45d954c66acf805218efd18ac5d596ccde27b535b09c6fa14f27cebf8eb4e6","last_reissued_at":"2026-07-05T06:07:45.459564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:45.459564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIReAD: Simple Method for Learning High-quality Representations from Scientific Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexander Brechalov, Anastasia Razdaibiedina","submitted_at":"2023-05-07T03:29:55Z","abstract_excerpt":"Learning semantically meaningful representations from scientific documents can facilitate academic literature search and improve performance of recommendation systems. Pre-trained language models have been shown to learn rich textual representations, yet they cannot provide powerful document-level representations for scientific articles. We propose MIReAD, a simple method that learns high-quality representations of scientific papers by fine-tuning transformer model to predict the target journal class based on the abstract. We train MIReAD on more than 500,000 PubMed and arXiv abstracts across "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.04177","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/2305.04177/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":"2305.04177","created_at":"2026-07-05T06:07:45.459620+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.04177v1","created_at":"2026-07-05T06:07:45.459620+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04177","created_at":"2026-07-05T06:07:45.459620+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZC5SVGGNLHY","created_at":"2026-07-05T06:07:45.459620+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZC5SVGGNLHYAUQY","created_at":"2026-07-05T06:07:45.459620+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZC5SVGG","created_at":"2026-07-05T06:07:45.459620+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/RZC5SVGGNLHYAUQY57IYVROVS3","json":"https://pith.science/pith/RZC5SVGGNLHYAUQY57IYVROVS3.json","graph_json":"https://pith.science/api/pith-number/RZC5SVGGNLHYAUQY57IYVROVS3/graph.json","events_json":"https://pith.science/api/pith-number/RZC5SVGGNLHYAUQY57IYVROVS3/events.json","paper":"https://pith.science/paper/RZC5SVGG"},"agent_actions":{"view_html":"https://pith.science/pith/RZC5SVGGNLHYAUQY57IYVROVS3","download_json":"https://pith.science/pith/RZC5SVGGNLHYAUQY57IYVROVS3.json","view_paper":"https://pith.science/paper/RZC5SVGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.04177&json=true","fetch_graph":"https://pith.science/api/pith-number/RZC5SVGGNLHYAUQY57IYVROVS3/graph.json","fetch_events":"https://pith.science/api/pith-number/RZC5SVGGNLHYAUQY57IYVROVS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZC5SVGGNLHYAUQY57IYVROVS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZC5SVGGNLHYAUQY57IYVROVS3/action/storage_attestation","attest_author":"https://pith.science/pith/RZC5SVGGNLHYAUQY57IYVROVS3/action/author_attestation","sign_citation":"https://pith.science/pith/RZC5SVGGNLHYAUQY57IYVROVS3/action/citation_signature","submit_replication":"https://pith.science/pith/RZC5SVGGNLHYAUQY57IYVROVS3/action/replication_record"}},"created_at":"2026-07-05T06:07:45.459620+00:00","updated_at":"2026-07-05T06:07:45.459620+00:00"}