{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YVDY5JGCBJKP2B7L4PVAVFJKW4","short_pith_number":"pith:YVDY5JGC","schema_version":"1.0","canonical_sha256":"c5478ea4c20a54fd07ebe3ea0a952ab7046716e971b56f084afc0bfe74c932e8","source":{"kind":"arxiv","id":"2404.08066","version":1},"attestation_state":"computed","paper":{"title":"MSciNLI: A Diverse Benchmark for Scientific Natural Language Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cornelia Caragea, Mobashir Sadat","submitted_at":"2024-04-11T18:12:12Z","abstract_excerpt":"The task of scientific Natural Language Inference (NLI) involves predicting the semantic relation between two sentences extracted from research articles. This task was recently proposed along with a new dataset called SciNLI derived from papers published in the computational linguistics domain. In this paper, we aim to introduce diversity in the scientific NLI task and present MSciNLI, a dataset containing 132,320 sentence pairs extracted from five new scientific domains. The availability of multiple domains makes it possible to study domain shift for scientific NLI. We establish strong baseli"},"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":"2404.08066","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T18:12:12Z","cross_cats_sorted":[],"title_canon_sha256":"1ed6b9e8760aed51bdf1415bf94814b531bcd969f6832d9e874a61a6677e0606","abstract_canon_sha256":"ed817ff9c8138953069f98a03a4852331fc68ced9d24c2b0a6d4c5eddc070a26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:02.023949Z","signature_b64":"OUDFTG2GRkucx9rtrQJ+4OPmJg76LZ2wQfPlDlfg0M5PL4yl+NMsLCoTbYA8MZp+5iR7yk2Y/GaLy+bQRCgwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5478ea4c20a54fd07ebe3ea0a952ab7046716e971b56f084afc0bfe74c932e8","last_reissued_at":"2026-07-05T08:07:02.023537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:02.023537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MSciNLI: A Diverse Benchmark for Scientific Natural Language Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cornelia Caragea, Mobashir Sadat","submitted_at":"2024-04-11T18:12:12Z","abstract_excerpt":"The task of scientific Natural Language Inference (NLI) involves predicting the semantic relation between two sentences extracted from research articles. This task was recently proposed along with a new dataset called SciNLI derived from papers published in the computational linguistics domain. In this paper, we aim to introduce diversity in the scientific NLI task and present MSciNLI, a dataset containing 132,320 sentence pairs extracted from five new scientific domains. The availability of multiple domains makes it possible to study domain shift for scientific NLI. We establish strong baseli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08066","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/2404.08066/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":"2404.08066","created_at":"2026-07-05T08:07:02.023593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.08066v1","created_at":"2026-07-05T08:07:02.023593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08066","created_at":"2026-07-05T08:07:02.023593+00:00"},{"alias_kind":"pith_short_12","alias_value":"YVDY5JGCBJKP","created_at":"2026-07-05T08:07:02.023593+00:00"},{"alias_kind":"pith_short_16","alias_value":"YVDY5JGCBJKP2B7L","created_at":"2026-07-05T08:07:02.023593+00:00"},{"alias_kind":"pith_short_8","alias_value":"YVDY5JGC","created_at":"2026-07-05T08:07:02.023593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02491","citing_title":"From Experimental Limits to Physical Insight: A Retrieval-Augmented Multi-Agent Framework for Interpreting Searches Beyond the Standard Model","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YVDY5JGCBJKP2B7L4PVAVFJKW4","json":"https://pith.science/pith/YVDY5JGCBJKP2B7L4PVAVFJKW4.json","graph_json":"https://pith.science/api/pith-number/YVDY5JGCBJKP2B7L4PVAVFJKW4/graph.json","events_json":"https://pith.science/api/pith-number/YVDY5JGCBJKP2B7L4PVAVFJKW4/events.json","paper":"https://pith.science/paper/YVDY5JGC"},"agent_actions":{"view_html":"https://pith.science/pith/YVDY5JGCBJKP2B7L4PVAVFJKW4","download_json":"https://pith.science/pith/YVDY5JGCBJKP2B7L4PVAVFJKW4.json","view_paper":"https://pith.science/paper/YVDY5JGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.08066&json=true","fetch_graph":"https://pith.science/api/pith-number/YVDY5JGCBJKP2B7L4PVAVFJKW4/graph.json","fetch_events":"https://pith.science/api/pith-number/YVDY5JGCBJKP2B7L4PVAVFJKW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YVDY5JGCBJKP2B7L4PVAVFJKW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YVDY5JGCBJKP2B7L4PVAVFJKW4/action/storage_attestation","attest_author":"https://pith.science/pith/YVDY5JGCBJKP2B7L4PVAVFJKW4/action/author_attestation","sign_citation":"https://pith.science/pith/YVDY5JGCBJKP2B7L4PVAVFJKW4/action/citation_signature","submit_replication":"https://pith.science/pith/YVDY5JGCBJKP2B7L4PVAVFJKW4/action/replication_record"}},"created_at":"2026-07-05T08:07:02.023593+00:00","updated_at":"2026-07-05T08:07:02.023593+00:00"}