{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z7HGA53T4W63WNE56Q6ZH4Q2I6","short_pith_number":"pith:Z7HGA53T","schema_version":"1.0","canonical_sha256":"cfce607773e5bdbb349df43d93f21a47b88eecdc8bc853af008f5f17274288cb","source":{"kind":"arxiv","id":"2606.31741","version":1},"attestation_state":"computed","paper":{"title":"STEB: Style Text Embedding Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anna Wegmann, Cristina Aggazzotti, Rafael Rivera Soto","submitted_at":"2026-06-30T14:35:02Z","abstract_excerpt":"While semantic embeddings are rigorously evaluated on the Massive Text Embedding Benchmark, the evaluation of style embeddings remains fragmented, with each work relying on their own set of tasks and datasets. To bridge this gap, we introduce the Style Text Embedding Benchmark, a comprehensive open-source benchmark intended to standardize the evaluation of style embeddings. STEB encompasses 96 datasets across 7 languages, spanning applications such as authorship verification, authorship retrieval, AI-text detection, probing of linguistic features, and others. We find that semantic embeddings c"},"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":"2606.31741","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T14:35:02Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8bfa325563e7b3c8d32d9ceaaf126c130a90246383f0eb0859c232fe6108e0fd","abstract_canon_sha256":"9b2e333eb21ae701df6524f0c982c8aae3d22a069e221996eeb0cd6051a11ffb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:13.378282Z","signature_b64":"feVvsXD5PXLvA0dHBVq1CGgGVVqQzBZGPZ2y/GkWybg3y0JDptBSw/Tg/luvOscOzC2UrRQurNCj6ag7x+gmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfce607773e5bdbb349df43d93f21a47b88eecdc8bc853af008f5f17274288cb","last_reissued_at":"2026-07-01T01:18:13.377837Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:13.377837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STEB: Style Text Embedding Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anna Wegmann, Cristina Aggazzotti, Rafael Rivera Soto","submitted_at":"2026-06-30T14:35:02Z","abstract_excerpt":"While semantic embeddings are rigorously evaluated on the Massive Text Embedding Benchmark, the evaluation of style embeddings remains fragmented, with each work relying on their own set of tasks and datasets. To bridge this gap, we introduce the Style Text Embedding Benchmark, a comprehensive open-source benchmark intended to standardize the evaluation of style embeddings. STEB encompasses 96 datasets across 7 languages, spanning applications such as authorship verification, authorship retrieval, AI-text detection, probing of linguistic features, and others. We find that semantic embeddings c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31741","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/2606.31741/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":"2606.31741","created_at":"2026-07-01T01:18:13.377895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31741v1","created_at":"2026-07-01T01:18:13.377895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31741","created_at":"2026-07-01T01:18:13.377895+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7HGA53T4W63","created_at":"2026-07-01T01:18:13.377895+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7HGA53T4W63WNE5","created_at":"2026-07-01T01:18:13.377895+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7HGA53T","created_at":"2026-07-01T01:18:13.377895+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/Z7HGA53T4W63WNE56Q6ZH4Q2I6","json":"https://pith.science/pith/Z7HGA53T4W63WNE56Q6ZH4Q2I6.json","graph_json":"https://pith.science/api/pith-number/Z7HGA53T4W63WNE56Q6ZH4Q2I6/graph.json","events_json":"https://pith.science/api/pith-number/Z7HGA53T4W63WNE56Q6ZH4Q2I6/events.json","paper":"https://pith.science/paper/Z7HGA53T"},"agent_actions":{"view_html":"https://pith.science/pith/Z7HGA53T4W63WNE56Q6ZH4Q2I6","download_json":"https://pith.science/pith/Z7HGA53T4W63WNE56Q6ZH4Q2I6.json","view_paper":"https://pith.science/paper/Z7HGA53T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31741&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7HGA53T4W63WNE56Q6ZH4Q2I6/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7HGA53T4W63WNE56Q6ZH4Q2I6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7HGA53T4W63WNE56Q6ZH4Q2I6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7HGA53T4W63WNE56Q6ZH4Q2I6/action/storage_attestation","attest_author":"https://pith.science/pith/Z7HGA53T4W63WNE56Q6ZH4Q2I6/action/author_attestation","sign_citation":"https://pith.science/pith/Z7HGA53T4W63WNE56Q6ZH4Q2I6/action/citation_signature","submit_replication":"https://pith.science/pith/Z7HGA53T4W63WNE56Q6ZH4Q2I6/action/replication_record"}},"created_at":"2026-07-01T01:18:13.377895+00:00","updated_at":"2026-07-01T01:18:13.377895+00:00"}