{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VBK5IWPEGPLM3YBECFECDOYOQZ","short_pith_number":"pith:VBK5IWPE","schema_version":"1.0","canonical_sha256":"a855d459e433d6cde024114821bb0e866f97089c79fd8e997f7e02dcc7d824cb","source":{"kind":"arxiv","id":"2607.18960","version":1},"attestation_state":"computed","paper":{"title":"SFGA: A Statistics-First Gating Architecture with Adjudicative Escalation for Trustworthy SFT Data Procurement","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Aaron Chan, Alex Ding, Arther Tian, Simon Wu","submitted_at":"2026-07-21T10:52:04Z","abstract_excerpt":"Procuring supervised fine-tuning (SFT) data forces a buyer to decide, before any downstream training, whether a candidate corpus is worth acquiring. We present \\sys{}, a statistics-first gating architecture that treats procurement as a cost-aware routing problem over three intrinsic quality axes -- diversity, utility, and redundancy. Cheap blind measurements are summarised into per-axis estimates with confidence intervals; a gate accepts a decision only when intervals are tight, sample sizes are adequate, and the axes agree, otherwise it escalates the case to an adjudicative debate between a b"},"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":"2607.18960","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T10:52:04Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"6023c07e9a20ae17700fea0582284942ba9e9425647a8a54f8ab5629c1ca9e3d","abstract_canon_sha256":"fe6839a0ab70bf74812098e926541159fae7df1f7e70e59d91ae67a0d79b4a98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:23:21.954397Z","signature_b64":"KhC1+6jhdYi1OR8DVTrRKC+4z5sa8kuD01Nt5K3wJQNodt0DfjHFf8moL5dCLrcNtG+92TRFoeH9ctorTdEgAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a855d459e433d6cde024114821bb0e866f97089c79fd8e997f7e02dcc7d824cb","last_reissued_at":"2026-07-22T01:23:21.953424Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:23:21.953424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SFGA: A Statistics-First Gating Architecture with Adjudicative Escalation for Trustworthy SFT Data Procurement","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Aaron Chan, Alex Ding, Arther Tian, Simon Wu","submitted_at":"2026-07-21T10:52:04Z","abstract_excerpt":"Procuring supervised fine-tuning (SFT) data forces a buyer to decide, before any downstream training, whether a candidate corpus is worth acquiring. We present \\sys{}, a statistics-first gating architecture that treats procurement as a cost-aware routing problem over three intrinsic quality axes -- diversity, utility, and redundancy. Cheap blind measurements are summarised into per-axis estimates with confidence intervals; a gate accepts a decision only when intervals are tight, sample sizes are adequate, and the axes agree, otherwise it escalates the case to an adjudicative debate between a b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18960","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/2607.18960/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":"2607.18960","created_at":"2026-07-22T01:23:21.953846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18960v1","created_at":"2026-07-22T01:23:21.953846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18960","created_at":"2026-07-22T01:23:21.953846+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBK5IWPEGPLM","created_at":"2026-07-22T01:23:21.953846+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBK5IWPEGPLM3YBE","created_at":"2026-07-22T01:23:21.953846+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBK5IWPE","created_at":"2026-07-22T01:23:21.953846+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/VBK5IWPEGPLM3YBECFECDOYOQZ","json":"https://pith.science/pith/VBK5IWPEGPLM3YBECFECDOYOQZ.json","graph_json":"https://pith.science/api/pith-number/VBK5IWPEGPLM3YBECFECDOYOQZ/graph.json","events_json":"https://pith.science/api/pith-number/VBK5IWPEGPLM3YBECFECDOYOQZ/events.json","paper":"https://pith.science/paper/VBK5IWPE"},"agent_actions":{"view_html":"https://pith.science/pith/VBK5IWPEGPLM3YBECFECDOYOQZ","download_json":"https://pith.science/pith/VBK5IWPEGPLM3YBECFECDOYOQZ.json","view_paper":"https://pith.science/paper/VBK5IWPE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18960&json=true","fetch_graph":"https://pith.science/api/pith-number/VBK5IWPEGPLM3YBECFECDOYOQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/VBK5IWPEGPLM3YBECFECDOYOQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBK5IWPEGPLM3YBECFECDOYOQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBK5IWPEGPLM3YBECFECDOYOQZ/action/storage_attestation","attest_author":"https://pith.science/pith/VBK5IWPEGPLM3YBECFECDOYOQZ/action/author_attestation","sign_citation":"https://pith.science/pith/VBK5IWPEGPLM3YBECFECDOYOQZ/action/citation_signature","submit_replication":"https://pith.science/pith/VBK5IWPEGPLM3YBECFECDOYOQZ/action/replication_record"}},"created_at":"2026-07-22T01:23:21.953846+00:00","updated_at":"2026-07-22T01:23:21.953846+00:00"}