{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7JC4UHETZJHFPI7KRA4CNM6X4A","short_pith_number":"pith:7JC4UHET","canonical_record":{"source":{"id":"2606.07996","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-06T06:27:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"37b109bdab4f7a421235dc199045b812187455d4f2aab82525aff9a537a82b92","abstract_canon_sha256":"d540930f8342571ef443eaba397762d3d8c31ac3648b789642c7fb77de0fe92c"},"schema_version":"1.0"},"canonical_sha256":"fa45ca1c93ca4e57a3ea883826b3d7e0365d95a085ec7a978f3ae1fe23aa6a2f","source":{"kind":"arxiv","id":"2606.07996","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07996","created_at":"2026-06-09T01:05:22Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07996v1","created_at":"2026-06-09T01:05:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07996","created_at":"2026-06-09T01:05:22Z"},{"alias_kind":"pith_short_12","alias_value":"7JC4UHETZJHF","created_at":"2026-06-09T01:05:22Z"},{"alias_kind":"pith_short_16","alias_value":"7JC4UHETZJHFPI7K","created_at":"2026-06-09T01:05:22Z"},{"alias_kind":"pith_short_8","alias_value":"7JC4UHET","created_at":"2026-06-09T01:05:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7JC4UHETZJHFPI7KRA4CNM6X4A","target":"record","payload":{"canonical_record":{"source":{"id":"2606.07996","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-06T06:27:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"37b109bdab4f7a421235dc199045b812187455d4f2aab82525aff9a537a82b92","abstract_canon_sha256":"d540930f8342571ef443eaba397762d3d8c31ac3648b789642c7fb77de0fe92c"},"schema_version":"1.0"},"canonical_sha256":"fa45ca1c93ca4e57a3ea883826b3d7e0365d95a085ec7a978f3ae1fe23aa6a2f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:22.011122Z","signature_b64":"PFdCel+cA85IMMTyGlBlueploo1ZfUKPoh7oHnnAdN2sOE2GsElkK8hGmBnTwfM2HpaLHNsYgRntieAGbmnaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa45ca1c93ca4e57a3ea883826b3d7e0365d95a085ec7a978f3ae1fe23aa6a2f","last_reissued_at":"2026-06-09T01:05:22.010411Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:22.010411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.07996","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T01:05:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/zPsaRRnHGS9mX98CkPBZ2aVKQyGN6XqQxauSovtZwxemF6cwuME6SZF8oyIZHBenYxAshG+AiWbKnqV6xD/Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T20:27:34.807159Z"},"content_sha256":"7827762b5851da19f946d53b343be422ccff0de1fd77b43998b8c9c78b299662","schema_version":"1.0","event_id":"sha256:7827762b5851da19f946d53b343be422ccff0de1fd77b43998b8c9c78b299662"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7JC4UHETZJHFPI7KRA4CNM6X4A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MC-PDD: Masked Corpus-Level Pretraining Data Detection for Black-Box Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Binkai Ou, Derek F. Wong, Kaixin Lan, Lidia S. Chao, Mu You, Tao Fang","submitted_at":"2026-06-06T06:27:54Z","abstract_excerpt":"Pretraining is fundamental to the development of Large Language Models (LLMs), yet the opacity of pretraining data complicates model analysis and raises ethical, legal, and fairness concerns. Detecting whether specific datasets were used during pretraining is, therefore, critical. Existing state-of-the-art methods typically rely on access to model probability distributions, making them unsuitable for closed-source LLMs that provide only input-output interfaces. To address this limitation, we introduce Masked Corpus-level Pretraining Data Detection (MC-PDD), a novel method inspired by the maske"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07996","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/2606.07996/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T01:05:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9xuCemlo5eS+yQgRGJE6uoqzIRdxGFcSthlZmDyj90IKvTcqLBP0GOzNWVN89NHu49ogCEORLJqdvz7IZbUuDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T20:27:34.807541Z"},"content_sha256":"05891aaaf8e622196c7229fae9f74375aa4ba1f2853997a2a78001b347d9a950","schema_version":"1.0","event_id":"sha256:05891aaaf8e622196c7229fae9f74375aa4ba1f2853997a2a78001b347d9a950"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7JC4UHETZJHFPI7KRA4CNM6X4A/bundle.json","state_url":"https://pith.science/pith/7JC4UHETZJHFPI7KRA4CNM6X4A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7JC4UHETZJHFPI7KRA4CNM6X4A/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-28T20:27:34Z","links":{"resolver":"https://pith.science/pith/7JC4UHETZJHFPI7KRA4CNM6X4A","bundle":"https://pith.science/pith/7JC4UHETZJHFPI7KRA4CNM6X4A/bundle.json","state":"https://pith.science/pith/7JC4UHETZJHFPI7KRA4CNM6X4A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7JC4UHETZJHFPI7KRA4CNM6X4A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7JC4UHETZJHFPI7KRA4CNM6X4A","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d540930f8342571ef443eaba397762d3d8c31ac3648b789642c7fb77de0fe92c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-06T06:27:54Z","title_canon_sha256":"37b109bdab4f7a421235dc199045b812187455d4f2aab82525aff9a537a82b92"},"schema_version":"1.0","source":{"id":"2606.07996","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07996","created_at":"2026-06-09T01:05:22Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07996v1","created_at":"2026-06-09T01:05:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07996","created_at":"2026-06-09T01:05:22Z"},{"alias_kind":"pith_short_12","alias_value":"7JC4UHETZJHF","created_at":"2026-06-09T01:05:22Z"},{"alias_kind":"pith_short_16","alias_value":"7JC4UHETZJHFPI7K","created_at":"2026-06-09T01:05:22Z"},{"alias_kind":"pith_short_8","alias_value":"7JC4UHET","created_at":"2026-06-09T01:05:22Z"}],"graph_snapshots":[{"event_id":"sha256:05891aaaf8e622196c7229fae9f74375aa4ba1f2853997a2a78001b347d9a950","target":"graph","created_at":"2026-06-09T01:05:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.07996/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretraining is fundamental to the development of Large Language Models (LLMs), yet the opacity of pretraining data complicates model analysis and raises ethical, legal, and fairness concerns. Detecting whether specific datasets were used during pretraining is, therefore, critical. Existing state-of-the-art methods typically rely on access to model probability distributions, making them unsuitable for closed-source LLMs that provide only input-output interfaces. To address this limitation, we introduce Masked Corpus-level Pretraining Data Detection (MC-PDD), a novel method inspired by the maske","authors_text":"Binkai Ou, Derek F. Wong, Kaixin Lan, Lidia S. Chao, Mu You, Tao Fang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-06T06:27:54Z","title":"MC-PDD: Masked Corpus-Level Pretraining Data Detection for Black-Box Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07996","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7827762b5851da19f946d53b343be422ccff0de1fd77b43998b8c9c78b299662","target":"record","created_at":"2026-06-09T01:05:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d540930f8342571ef443eaba397762d3d8c31ac3648b789642c7fb77de0fe92c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-06T06:27:54Z","title_canon_sha256":"37b109bdab4f7a421235dc199045b812187455d4f2aab82525aff9a537a82b92"},"schema_version":"1.0","source":{"id":"2606.07996","kind":"arxiv","version":1}},"canonical_sha256":"fa45ca1c93ca4e57a3ea883826b3d7e0365d95a085ec7a978f3ae1fe23aa6a2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa45ca1c93ca4e57a3ea883826b3d7e0365d95a085ec7a978f3ae1fe23aa6a2f","first_computed_at":"2026-06-09T01:05:22.010411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:22.010411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PFdCel+cA85IMMTyGlBlueploo1ZfUKPoh7oHnnAdN2sOE2GsElkK8hGmBnTwfM2HpaLHNsYgRntieAGbmnaDg==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:22.011122Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07996","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7827762b5851da19f946d53b343be422ccff0de1fd77b43998b8c9c78b299662","sha256:05891aaaf8e622196c7229fae9f74375aa4ba1f2853997a2a78001b347d9a950"],"state_sha256":"332dab02b87cd55e5a62c03158556b7d31c70202028b9f862f231b54f3280212"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0FEEAfZuC/7mXsVdEHdkEQSTAMmkyU+fvf4rWsGxZKlqjSddIipfcasq+P1IW7DJFv4iGz93i/+CUvsqjBcyBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T20:27:34.809481Z","bundle_sha256":"60a82daad413ce1b2e6c538d1098b2ecbc7a03c7fcc64cd4bec20f1fd89d63af"}}