{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5HJ65S3JW3LMSP3QCTIBWQXAXK","short_pith_number":"pith:5HJ65S3J","canonical_record":{"source":{"id":"2406.01333","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T13:58:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7c88b639fca240efd22513fa8965c033c3033c35d5bd0a718df6bba865c91017","abstract_canon_sha256":"beb514d49d26aa36f00051cc20ce3b8f34ff216f0b5d037ac837c4eb01bd9bf6"},"schema_version":"1.0"},"canonical_sha256":"e9d3eecb69b6d6c93f7014d01b42e0ba9b84bc993142ce09eb2e4654c2e4aa94","source":{"kind":"arxiv","id":"2406.01333","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01333","created_at":"2026-07-05T08:26:38Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01333v1","created_at":"2026-07-05T08:26:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01333","created_at":"2026-07-05T08:26:38Z"},{"alias_kind":"pith_short_12","alias_value":"5HJ65S3JW3LM","created_at":"2026-07-05T08:26:38Z"},{"alias_kind":"pith_short_16","alias_value":"5HJ65S3JW3LMSP3Q","created_at":"2026-07-05T08:26:38Z"},{"alias_kind":"pith_short_8","alias_value":"5HJ65S3J","created_at":"2026-07-05T08:26:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5HJ65S3JW3LMSP3QCTIBWQXAXK","target":"record","payload":{"canonical_record":{"source":{"id":"2406.01333","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T13:58:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7c88b639fca240efd22513fa8965c033c3033c35d5bd0a718df6bba865c91017","abstract_canon_sha256":"beb514d49d26aa36f00051cc20ce3b8f34ff216f0b5d037ac837c4eb01bd9bf6"},"schema_version":"1.0"},"canonical_sha256":"e9d3eecb69b6d6c93f7014d01b42e0ba9b84bc993142ce09eb2e4654c2e4aa94","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:38.458581Z","signature_b64":"DghCdV3vsfrQmvRWn1ZBEEcRK+DBjyr52ioN5MatdN3xMtFssP5VMp2mWrslcuzMFrPpccb28Ulm81KX1Y7ODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9d3eecb69b6d6c93f7014d01b42e0ba9b84bc993142ce09eb2e4654c2e4aa94","last_reissued_at":"2026-07-05T08:26:38.458169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:38.458169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.01333","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":"2026-07-05T08:26:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NF8PwqMWYiDhOI01h/oh7QGA15SZNKDh12ou89VUPz2BaprH7H0AJ7RpbgS1VT6/dA9WSNAwJe2kbeolFWKnAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:28:40.331576Z"},"content_sha256":"6c9ac537093cf9d5f570efb663ce6199fcc45357d45cb997cd4cec6c866c183b","schema_version":"1.0","event_id":"sha256:6c9ac537093cf9d5f570efb663ce6199fcc45357d45cb997cd4cec6c866c183b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5HJ65S3JW3LMSP3QCTIBWQXAXK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Probing Language Models for Pre-training Data Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bing Liu, Chuanyuan Tan, Haonan Lu, Tong Zhu, Wenliang Chen, Zhenhua Liu","submitted_at":"2024-06-03T13:58:04Z","abstract_excerpt":"Large Language Models (LLMs) have shown their impressive capabilities, while also raising concerns about the data contamination problems due to privacy issues and leakage of benchmark datasets in the pre-training phase. Therefore, it is vital to detect the contamination by checking whether an LLM has been pre-trained on the target texts. Recent studies focus on the generated texts and compute perplexities, which are superficial features and not reliable. In this study, we propose to utilize the probing technique for pre-training data detection by examining the model's internal activations. Our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01333","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/2406.01333/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":"2026-07-05T08:26:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gg+t1IWQk8shVv8LQYc7aFf11bqG8habNesNuHAfAR2oym4MJX9CIl8fv83WR6CsexsRsYtsimRoA1iQaFEgAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:28:40.332478Z"},"content_sha256":"5967e08b84c44d135e9510aec297923a4965382c083f9c1be3c67fe32aa9d919","schema_version":"1.0","event_id":"sha256:5967e08b84c44d135e9510aec297923a4965382c083f9c1be3c67fe32aa9d919"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5HJ65S3JW3LMSP3QCTIBWQXAXK/bundle.json","state_url":"https://pith.science/pith/5HJ65S3JW3LMSP3QCTIBWQXAXK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5HJ65S3JW3LMSP3QCTIBWQXAXK/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":"2026-08-07T18:28:40Z","links":{"resolver":"https://pith.science/pith/5HJ65S3JW3LMSP3QCTIBWQXAXK","bundle":"https://pith.science/pith/5HJ65S3JW3LMSP3QCTIBWQXAXK/bundle.json","state":"https://pith.science/pith/5HJ65S3JW3LMSP3QCTIBWQXAXK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5HJ65S3JW3LMSP3QCTIBWQXAXK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5HJ65S3JW3LMSP3QCTIBWQXAXK","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":"beb514d49d26aa36f00051cc20ce3b8f34ff216f0b5d037ac837c4eb01bd9bf6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T13:58:04Z","title_canon_sha256":"7c88b639fca240efd22513fa8965c033c3033c35d5bd0a718df6bba865c91017"},"schema_version":"1.0","source":{"id":"2406.01333","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01333","created_at":"2026-07-05T08:26:38Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01333v1","created_at":"2026-07-05T08:26:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01333","created_at":"2026-07-05T08:26:38Z"},{"alias_kind":"pith_short_12","alias_value":"5HJ65S3JW3LM","created_at":"2026-07-05T08:26:38Z"},{"alias_kind":"pith_short_16","alias_value":"5HJ65S3JW3LMSP3Q","created_at":"2026-07-05T08:26:38Z"},{"alias_kind":"pith_short_8","alias_value":"5HJ65S3J","created_at":"2026-07-05T08:26:38Z"}],"graph_snapshots":[{"event_id":"sha256:5967e08b84c44d135e9510aec297923a4965382c083f9c1be3c67fe32aa9d919","target":"graph","created_at":"2026-07-05T08:26:38Z","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/2406.01333/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown their impressive capabilities, while also raising concerns about the data contamination problems due to privacy issues and leakage of benchmark datasets in the pre-training phase. Therefore, it is vital to detect the contamination by checking whether an LLM has been pre-trained on the target texts. Recent studies focus on the generated texts and compute perplexities, which are superficial features and not reliable. In this study, we propose to utilize the probing technique for pre-training data detection by examining the model's internal activations. Our","authors_text":"Bing Liu, Chuanyuan Tan, Haonan Lu, Tong Zhu, Wenliang Chen, Zhenhua Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T13:58:04Z","title":"Probing Language Models for Pre-training Data Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01333","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":"sha256:6c9ac537093cf9d5f570efb663ce6199fcc45357d45cb997cd4cec6c866c183b","target":"record","created_at":"2026-07-05T08:26:38Z","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":"beb514d49d26aa36f00051cc20ce3b8f34ff216f0b5d037ac837c4eb01bd9bf6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T13:58:04Z","title_canon_sha256":"7c88b639fca240efd22513fa8965c033c3033c35d5bd0a718df6bba865c91017"},"schema_version":"1.0","source":{"id":"2406.01333","kind":"arxiv","version":1}},"canonical_sha256":"e9d3eecb69b6d6c93f7014d01b42e0ba9b84bc993142ce09eb2e4654c2e4aa94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9d3eecb69b6d6c93f7014d01b42e0ba9b84bc993142ce09eb2e4654c2e4aa94","first_computed_at":"2026-07-05T08:26:38.458169Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:38.458169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DghCdV3vsfrQmvRWn1ZBEEcRK+DBjyr52ioN5MatdN3xMtFssP5VMp2mWrslcuzMFrPpccb28Ulm81KX1Y7ODg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:38.458581Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01333","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c9ac537093cf9d5f570efb663ce6199fcc45357d45cb997cd4cec6c866c183b","sha256:5967e08b84c44d135e9510aec297923a4965382c083f9c1be3c67fe32aa9d919"],"state_sha256":"cd5914707a4633647ed12d0e7b9312d1637a810829a92ae267523d605120c14c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eifn1uGXlGxEBi7PlmpDpOL5bOuqAjjyOQagwXTCGSEAQbUOIHxdIzJsBzCy42fK2GKZtbd4ueGwRmCb3AqMAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:28:40.343605Z","bundle_sha256":"368745e1e86a6c224cef8adde2ec53305ebe5321c4f9611bcfabf234b401ead7"}}