{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y25DU36ACHY6WKG67DQXAO2V5B","short_pith_number":"pith:Y25DU36A","schema_version":"1.0","canonical_sha256":"c6ba3a6fc011f1eb28def8e1703b55e847b05e6bdf8fafec87048e6ada8975ac","source":{"kind":"arxiv","id":"2606.07103","version":1},"attestation_state":"computed","paper":{"title":"Style or Content? Evaluating Style Classifiers with Controlled Content Overlap","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hangfeng He, Haozheng Du, Xiangxiang Xu, Zhuo Liu","submitted_at":"2026-06-05T09:53:51Z","abstract_excerpt":"Style classifiers can use content cues that correlate with style labels in naturally collected data, yet we lack a systematic way to measure this reliance. We study this problem with a controlled content overlap setup built on parallel Bible translations. Specifically, we define the overlap parameter $\\alpha$ as the normalized residual of mutual information between content identity and style label, so that it measures how much content is shared across style classes: from no shared content ($\\alpha=0$) to fully shared content ($\\alpha=1$). Cross-overlap evaluation of RoBERTa-based classifiers s"},"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":"2606.07103","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T09:53:51Z","cross_cats_sorted":[],"title_canon_sha256":"3a61b8395ff42761a4bac456a4fb535a89c22770932d1c8f4805cc3db944d6f3","abstract_canon_sha256":"a4f4bcd22847c76e789452295f66d0fb38e4d2cb5c0ddb6ba338783b2414302f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:46.403491Z","signature_b64":"Nf01drSMCuHRDKthtf7hVdMR+xB0q26J+wOGX7apgFzcUh7LRH7ZtPvvJC9Fv9PW6EsjV/Whfts8m/fZnLq9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6ba3a6fc011f1eb28def8e1703b55e847b05e6bdf8fafec87048e6ada8975ac","last_reissued_at":"2026-06-08T01:04:46.402693Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:46.402693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Style or Content? Evaluating Style Classifiers with Controlled Content Overlap","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hangfeng He, Haozheng Du, Xiangxiang Xu, Zhuo Liu","submitted_at":"2026-06-05T09:53:51Z","abstract_excerpt":"Style classifiers can use content cues that correlate with style labels in naturally collected data, yet we lack a systematic way to measure this reliance. We study this problem with a controlled content overlap setup built on parallel Bible translations. Specifically, we define the overlap parameter $\\alpha$ as the normalized residual of mutual information between content identity and style label, so that it measures how much content is shared across style classes: from no shared content ($\\alpha=0$) to fully shared content ($\\alpha=1$). Cross-overlap evaluation of RoBERTa-based classifiers s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07103","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/2606.07103/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":"2606.07103","created_at":"2026-06-08T01:04:46.402816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07103v1","created_at":"2026-06-08T01:04:46.402816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07103","created_at":"2026-06-08T01:04:46.402816+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y25DU36ACHY6","created_at":"2026-06-08T01:04:46.402816+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y25DU36ACHY6WKG6","created_at":"2026-06-08T01:04:46.402816+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y25DU36A","created_at":"2026-06-08T01:04:46.402816+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/Y25DU36ACHY6WKG67DQXAO2V5B","json":"https://pith.science/pith/Y25DU36ACHY6WKG67DQXAO2V5B.json","graph_json":"https://pith.science/api/pith-number/Y25DU36ACHY6WKG67DQXAO2V5B/graph.json","events_json":"https://pith.science/api/pith-number/Y25DU36ACHY6WKG67DQXAO2V5B/events.json","paper":"https://pith.science/paper/Y25DU36A"},"agent_actions":{"view_html":"https://pith.science/pith/Y25DU36ACHY6WKG67DQXAO2V5B","download_json":"https://pith.science/pith/Y25DU36ACHY6WKG67DQXAO2V5B.json","view_paper":"https://pith.science/paper/Y25DU36A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07103&json=true","fetch_graph":"https://pith.science/api/pith-number/Y25DU36ACHY6WKG67DQXAO2V5B/graph.json","fetch_events":"https://pith.science/api/pith-number/Y25DU36ACHY6WKG67DQXAO2V5B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y25DU36ACHY6WKG67DQXAO2V5B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y25DU36ACHY6WKG67DQXAO2V5B/action/storage_attestation","attest_author":"https://pith.science/pith/Y25DU36ACHY6WKG67DQXAO2V5B/action/author_attestation","sign_citation":"https://pith.science/pith/Y25DU36ACHY6WKG67DQXAO2V5B/action/citation_signature","submit_replication":"https://pith.science/pith/Y25DU36ACHY6WKG67DQXAO2V5B/action/replication_record"}},"created_at":"2026-06-08T01:04:46.402816+00:00","updated_at":"2026-06-08T01:04:46.402816+00:00"}