{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M3DYGVYV6KATZ7NLRO5W5W2GXS","short_pith_number":"pith:M3DYGVYV","schema_version":"1.0","canonical_sha256":"66c7835715f2813cfdab8bbb6edb46bcbc43852dc235e7d78791a8b0c90077c5","source":{"kind":"arxiv","id":"2507.13105","version":1},"attestation_state":"computed","paper":{"title":"SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstracts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Marc Brinner, Sina Zarriess","submitted_at":"2025-07-17T13:19:50Z","abstract_excerpt":"We introduce SemCSE, an unsupervised method for learning semantic embeddings of scientific texts. Building on recent advances in contrastive learning for text embeddings, our approach leverages LLM-generated summaries of scientific abstracts to train a model that positions semantically related summaries closer together in the embedding space. This resulting objective ensures that the model captures the true semantic content of a text, in contrast to traditional citation-based approaches that do not necessarily reflect semantic similarity. To validate this, we propose a novel benchmark designed"},"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":"2507.13105","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-17T13:19:50Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"05e9b8e9f1b30950584b3dce394b444ffadf68bc6276945af1bff55ca44a734a","abstract_canon_sha256":"9ac9d87517971a6507f0e199b407d33f108cb1f72b6d9906f3b56143ff53473e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:54.743133Z","signature_b64":"YBQ5QPHLX0te0it1nTOjqgEYeAWDnr61OpIqPwXNLQhhWXVKUz5ygAfCcCt+OUCsCRZR5WJH9CKyYhH/WtzsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66c7835715f2813cfdab8bbb6edb46bcbc43852dc235e7d78791a8b0c90077c5","last_reissued_at":"2026-07-05T11:38:54.742677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:54.742677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstracts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Marc Brinner, Sina Zarriess","submitted_at":"2025-07-17T13:19:50Z","abstract_excerpt":"We introduce SemCSE, an unsupervised method for learning semantic embeddings of scientific texts. Building on recent advances in contrastive learning for text embeddings, our approach leverages LLM-generated summaries of scientific abstracts to train a model that positions semantically related summaries closer together in the embedding space. This resulting objective ensures that the model captures the true semantic content of a text, in contrast to traditional citation-based approaches that do not necessarily reflect semantic similarity. To validate this, we propose a novel benchmark designed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13105","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/2507.13105/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":"2507.13105","created_at":"2026-07-05T11:38:54.742722+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.13105v1","created_at":"2026-07-05T11:38:54.742722+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13105","created_at":"2026-07-05T11:38:54.742722+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3DYGVYV6KAT","created_at":"2026-07-05T11:38:54.742722+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3DYGVYV6KATZ7NL","created_at":"2026-07-05T11:38:54.742722+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3DYGVYV","created_at":"2026-07-05T11:38:54.742722+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/M3DYGVYV6KATZ7NLRO5W5W2GXS","json":"https://pith.science/pith/M3DYGVYV6KATZ7NLRO5W5W2GXS.json","graph_json":"https://pith.science/api/pith-number/M3DYGVYV6KATZ7NLRO5W5W2GXS/graph.json","events_json":"https://pith.science/api/pith-number/M3DYGVYV6KATZ7NLRO5W5W2GXS/events.json","paper":"https://pith.science/paper/M3DYGVYV"},"agent_actions":{"view_html":"https://pith.science/pith/M3DYGVYV6KATZ7NLRO5W5W2GXS","download_json":"https://pith.science/pith/M3DYGVYV6KATZ7NLRO5W5W2GXS.json","view_paper":"https://pith.science/paper/M3DYGVYV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.13105&json=true","fetch_graph":"https://pith.science/api/pith-number/M3DYGVYV6KATZ7NLRO5W5W2GXS/graph.json","fetch_events":"https://pith.science/api/pith-number/M3DYGVYV6KATZ7NLRO5W5W2GXS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3DYGVYV6KATZ7NLRO5W5W2GXS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3DYGVYV6KATZ7NLRO5W5W2GXS/action/storage_attestation","attest_author":"https://pith.science/pith/M3DYGVYV6KATZ7NLRO5W5W2GXS/action/author_attestation","sign_citation":"https://pith.science/pith/M3DYGVYV6KATZ7NLRO5W5W2GXS/action/citation_signature","submit_replication":"https://pith.science/pith/M3DYGVYV6KATZ7NLRO5W5W2GXS/action/replication_record"}},"created_at":"2026-07-05T11:38:54.742722+00:00","updated_at":"2026-07-05T11:38:54.742722+00:00"}