{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4FNNWK37QUN3WKZK2CD7PG6C5G","short_pith_number":"pith:4FNNWK37","schema_version":"1.0","canonical_sha256":"e15adb2b7f851bbb2b2ad087f79bc2e99a1eca05a2d62a23dff51d1a805d61b5","source":{"kind":"arxiv","id":"2607.13233","version":1},"attestation_state":"computed","paper":{"title":"When X-ray Features Hurt: Label Noise and Luminosity Overlap in Machine Learning Classification of AGN and Star-forming Galaxies","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["astro-ph.IM"],"primary_cat":"astro-ph.GA","authors_text":"Jaymin Ding","submitted_at":"2026-07-14T19:51:47Z","abstract_excerpt":"In a previous paper, we found that adding an X-ray flux feature to a Random Forest Classifier of active galactic nuclei (AGN) and star-forming galaxies (SFGs) decreased classification accuracy from 97.51% to 89.26%, a counterintuitive result given the prevailing theory that X-rays are a reliable AGN diagnostic. This paper investigates the source of that discrepancy through both astrophysical and machine learning lenses. On the astrophysical side, we show that the X-ray luminosities of AGN and SFGs in the sample substantially overlap across the canonical $10^{42}$ erg/s threshold, reflecting th"},"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":"2607.13233","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"astro-ph.GA","submitted_at":"2026-07-14T19:51:47Z","cross_cats_sorted":["astro-ph.IM"],"title_canon_sha256":"9fe749f478bb525dc03204695361fe87f7d26bd364186a905adf10ff84cf146b","abstract_canon_sha256":"ce681eb16cbe2dabad7f8001f747499e8cf71d929e341287852109a0a1d4c3e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T00:22:04.097114Z","signature_b64":"XtROiROQyL/5zEfmxqGb9GOCMhxegCO0HIsDFj2/hS0zkay28n4uJMB20RZnxbLQwtmkpUpcIlWwx90qpIFRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e15adb2b7f851bbb2b2ad087f79bc2e99a1eca05a2d62a23dff51d1a805d61b5","last_reissued_at":"2026-07-16T00:22:04.096249Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T00:22:04.096249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When X-ray Features Hurt: Label Noise and Luminosity Overlap in Machine Learning Classification of AGN and Star-forming Galaxies","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["astro-ph.IM"],"primary_cat":"astro-ph.GA","authors_text":"Jaymin Ding","submitted_at":"2026-07-14T19:51:47Z","abstract_excerpt":"In a previous paper, we found that adding an X-ray flux feature to a Random Forest Classifier of active galactic nuclei (AGN) and star-forming galaxies (SFGs) decreased classification accuracy from 97.51% to 89.26%, a counterintuitive result given the prevailing theory that X-rays are a reliable AGN diagnostic. This paper investigates the source of that discrepancy through both astrophysical and machine learning lenses. On the astrophysical side, we show that the X-ray luminosities of AGN and SFGs in the sample substantially overlap across the canonical $10^{42}$ erg/s threshold, reflecting th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13233","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/2607.13233/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":"2607.13233","created_at":"2026-07-16T00:22:04.096708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.13233v1","created_at":"2026-07-16T00:22:04.096708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13233","created_at":"2026-07-16T00:22:04.096708+00:00"},{"alias_kind":"pith_short_12","alias_value":"4FNNWK37QUN3","created_at":"2026-07-16T00:22:04.096708+00:00"},{"alias_kind":"pith_short_16","alias_value":"4FNNWK37QUN3WKZK","created_at":"2026-07-16T00:22:04.096708+00:00"},{"alias_kind":"pith_short_8","alias_value":"4FNNWK37","created_at":"2026-07-16T00:22:04.096708+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/4FNNWK37QUN3WKZK2CD7PG6C5G","json":"https://pith.science/pith/4FNNWK37QUN3WKZK2CD7PG6C5G.json","graph_json":"https://pith.science/api/pith-number/4FNNWK37QUN3WKZK2CD7PG6C5G/graph.json","events_json":"https://pith.science/api/pith-number/4FNNWK37QUN3WKZK2CD7PG6C5G/events.json","paper":"https://pith.science/paper/4FNNWK37"},"agent_actions":{"view_html":"https://pith.science/pith/4FNNWK37QUN3WKZK2CD7PG6C5G","download_json":"https://pith.science/pith/4FNNWK37QUN3WKZK2CD7PG6C5G.json","view_paper":"https://pith.science/paper/4FNNWK37","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.13233&json=true","fetch_graph":"https://pith.science/api/pith-number/4FNNWK37QUN3WKZK2CD7PG6C5G/graph.json","fetch_events":"https://pith.science/api/pith-number/4FNNWK37QUN3WKZK2CD7PG6C5G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4FNNWK37QUN3WKZK2CD7PG6C5G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4FNNWK37QUN3WKZK2CD7PG6C5G/action/storage_attestation","attest_author":"https://pith.science/pith/4FNNWK37QUN3WKZK2CD7PG6C5G/action/author_attestation","sign_citation":"https://pith.science/pith/4FNNWK37QUN3WKZK2CD7PG6C5G/action/citation_signature","submit_replication":"https://pith.science/pith/4FNNWK37QUN3WKZK2CD7PG6C5G/action/replication_record"}},"created_at":"2026-07-16T00:22:04.096708+00:00","updated_at":"2026-07-16T00:22:04.096708+00:00"}