{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2CWSDCK555K6ASRWNZAXJTZF3P","short_pith_number":"pith:2CWSDCK5","schema_version":"1.0","canonical_sha256":"d0ad21895def55e04a366e4174cf25dbcc813f319e59b23e0ce1111ab3d3dec8","source":{"kind":"arxiv","id":"2606.30081","version":1},"attestation_state":"computed","paper":{"title":"Discard the Dross and Select the Essential: Pre-query Sample Selection for Black-box Membership Inference Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Baogang Song, Changtian Song, Dongdong Zhao, Hongmin Wang, Jian Chen, Jinrong Hu","submitted_at":"2026-06-29T10:13:16Z","abstract_excerpt":"Black-box membership inference attacks (MIAs) rely on target-model queries to infer whether candidate samples were used for training. However, membership signals are highly non-uniform across samples: some candidate samples support strong member/non-member separability, whereas many others provide little useful signal. Consequently, indiscriminate querying can incur substantial query cost and increase query-induced exposure, with limited marginal benefit for inference. This raises a key question: which candidate samples are worth querying for black-box MIAs? To address this question, we propos"},"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":"2606.30081","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-06-29T10:13:16Z","cross_cats_sorted":[],"title_canon_sha256":"3c319c5b01ce3074b7f84f558d2da78f10e65bdcda16a50489a1ebec35c0ad2b","abstract_canon_sha256":"acd7d41cc4a9918262a4861c0a41fd43b07e19ed3e069b6f422315e5b03bd6ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:48.746241Z","signature_b64":"Yq4rVm983/jbY38T95gTuS1WRqfw4iSBslvSQW9Q5P4wcEpz6/3tpY1TJ+4flom8pRJYeKJJv0f3BTAuSIfXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0ad21895def55e04a366e4174cf25dbcc813f319e59b23e0ce1111ab3d3dec8","last_reissued_at":"2026-06-30T02:17:48.745421Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:48.745421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discard the Dross and Select the Essential: Pre-query Sample Selection for Black-box Membership Inference Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Baogang Song, Changtian Song, Dongdong Zhao, Hongmin Wang, Jian Chen, Jinrong Hu","submitted_at":"2026-06-29T10:13:16Z","abstract_excerpt":"Black-box membership inference attacks (MIAs) rely on target-model queries to infer whether candidate samples were used for training. However, membership signals are highly non-uniform across samples: some candidate samples support strong member/non-member separability, whereas many others provide little useful signal. Consequently, indiscriminate querying can incur substantial query cost and increase query-induced exposure, with limited marginal benefit for inference. This raises a key question: which candidate samples are worth querying for black-box MIAs? To address this question, we propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30081","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/2606.30081/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":"2606.30081","created_at":"2026-06-30T02:17:48.745546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30081v1","created_at":"2026-06-30T02:17:48.745546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30081","created_at":"2026-06-30T02:17:48.745546+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CWSDCK555K6","created_at":"2026-06-30T02:17:48.745546+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CWSDCK555K6ASRW","created_at":"2026-06-30T02:17:48.745546+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CWSDCK5","created_at":"2026-06-30T02:17:48.745546+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/2CWSDCK555K6ASRWNZAXJTZF3P","json":"https://pith.science/pith/2CWSDCK555K6ASRWNZAXJTZF3P.json","graph_json":"https://pith.science/api/pith-number/2CWSDCK555K6ASRWNZAXJTZF3P/graph.json","events_json":"https://pith.science/api/pith-number/2CWSDCK555K6ASRWNZAXJTZF3P/events.json","paper":"https://pith.science/paper/2CWSDCK5"},"agent_actions":{"view_html":"https://pith.science/pith/2CWSDCK555K6ASRWNZAXJTZF3P","download_json":"https://pith.science/pith/2CWSDCK555K6ASRWNZAXJTZF3P.json","view_paper":"https://pith.science/paper/2CWSDCK5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30081&json=true","fetch_graph":"https://pith.science/api/pith-number/2CWSDCK555K6ASRWNZAXJTZF3P/graph.json","fetch_events":"https://pith.science/api/pith-number/2CWSDCK555K6ASRWNZAXJTZF3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CWSDCK555K6ASRWNZAXJTZF3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CWSDCK555K6ASRWNZAXJTZF3P/action/storage_attestation","attest_author":"https://pith.science/pith/2CWSDCK555K6ASRWNZAXJTZF3P/action/author_attestation","sign_citation":"https://pith.science/pith/2CWSDCK555K6ASRWNZAXJTZF3P/action/citation_signature","submit_replication":"https://pith.science/pith/2CWSDCK555K6ASRWNZAXJTZF3P/action/replication_record"}},"created_at":"2026-06-30T02:17:48.745546+00:00","updated_at":"2026-06-30T02:17:48.745546+00:00"}