{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DVA4QIRIX5T44FEYPH6NOUTHWB","short_pith_number":"pith:DVA4QIRI","schema_version":"1.0","canonical_sha256":"1d41c82228bf67ce149879fcd75267b065e1efabe57d1ef3e448301988736abd","source":{"kind":"arxiv","id":"2305.14232","version":2},"attestation_state":"computed","paper":{"title":"Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hao Cheng, Jianfeng Gao, XiaoDong Liu, Ye-Yi Wang, Yu Zhang, Zhihong Shen","submitted_at":"2023-05-23T16:47:22Z","abstract_excerpt":"Scientific literature understanding tasks have gained significant attention due to their potential to accelerate scientific discovery. Pre-trained language models (LMs) have shown effectiveness in these tasks, especially when tuned via contrastive learning. However, jointly utilizing pre-training data across multiple heterogeneous tasks (e.g., extreme multi-label paper classification, citation prediction, and literature search) remains largely unexplored. To bridge this gap, we propose a multi-task contrastive learning framework, SciMult, with a focus on facilitating common knowledge sharing a"},"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":"2305.14232","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T16:47:22Z","cross_cats_sorted":["cs.DL","cs.IR","cs.LG"],"title_canon_sha256":"7c99b9596e55fec7ac9e0681a1aec27712b86985ddb797a712bb0553d101bdc6","abstract_canon_sha256":"ca241cff3cecf2001db49386bb905d5045d29cb5d831c837cbf38a6d2988da6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:25.340057Z","signature_b64":"rX9keyvznV6jBU2es01f8Q8zjJFkvpRvwKwJ0DGfcSeBQw7TY+Hl43cb9sh4jyd0gbLxrt3C192jaxGUrwKuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d41c82228bf67ce149879fcd75267b065e1efabe57d1ef3e448301988736abd","last_reissued_at":"2026-07-05T07:03:25.339561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:25.339561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hao Cheng, Jianfeng Gao, XiaoDong Liu, Ye-Yi Wang, Yu Zhang, Zhihong Shen","submitted_at":"2023-05-23T16:47:22Z","abstract_excerpt":"Scientific literature understanding tasks have gained significant attention due to their potential to accelerate scientific discovery. Pre-trained language models (LMs) have shown effectiveness in these tasks, especially when tuned via contrastive learning. However, jointly utilizing pre-training data across multiple heterogeneous tasks (e.g., extreme multi-label paper classification, citation prediction, and literature search) remains largely unexplored. To bridge this gap, we propose a multi-task contrastive learning framework, SciMult, with a focus on facilitating common knowledge sharing a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14232","kind":"arxiv","version":2},"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/2305.14232/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":"2305.14232","created_at":"2026-07-05T07:03:25.339621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14232v2","created_at":"2026-07-05T07:03:25.339621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14232","created_at":"2026-07-05T07:03:25.339621+00:00"},{"alias_kind":"pith_short_12","alias_value":"DVA4QIRIX5T4","created_at":"2026-07-05T07:03:25.339621+00:00"},{"alias_kind":"pith_short_16","alias_value":"DVA4QIRIX5T44FEY","created_at":"2026-07-05T07:03:25.339621+00:00"},{"alias_kind":"pith_short_8","alias_value":"DVA4QIRI","created_at":"2026-07-05T07:03:25.339621+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/DVA4QIRIX5T44FEYPH6NOUTHWB","json":"https://pith.science/pith/DVA4QIRIX5T44FEYPH6NOUTHWB.json","graph_json":"https://pith.science/api/pith-number/DVA4QIRIX5T44FEYPH6NOUTHWB/graph.json","events_json":"https://pith.science/api/pith-number/DVA4QIRIX5T44FEYPH6NOUTHWB/events.json","paper":"https://pith.science/paper/DVA4QIRI"},"agent_actions":{"view_html":"https://pith.science/pith/DVA4QIRIX5T44FEYPH6NOUTHWB","download_json":"https://pith.science/pith/DVA4QIRIX5T44FEYPH6NOUTHWB.json","view_paper":"https://pith.science/paper/DVA4QIRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14232&json=true","fetch_graph":"https://pith.science/api/pith-number/DVA4QIRIX5T44FEYPH6NOUTHWB/graph.json","fetch_events":"https://pith.science/api/pith-number/DVA4QIRIX5T44FEYPH6NOUTHWB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DVA4QIRIX5T44FEYPH6NOUTHWB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DVA4QIRIX5T44FEYPH6NOUTHWB/action/storage_attestation","attest_author":"https://pith.science/pith/DVA4QIRIX5T44FEYPH6NOUTHWB/action/author_attestation","sign_citation":"https://pith.science/pith/DVA4QIRIX5T44FEYPH6NOUTHWB/action/citation_signature","submit_replication":"https://pith.science/pith/DVA4QIRIX5T44FEYPH6NOUTHWB/action/replication_record"}},"created_at":"2026-07-05T07:03:25.339621+00:00","updated_at":"2026-07-05T07:03:25.339621+00:00"}