{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6TU2IR6AE5C7IAZLVEDWGCBCSK","short_pith_number":"pith:6TU2IR6A","canonical_record":{"source":{"id":"2401.00676","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-01-01T06:04:52Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"249d7af5b2c8fa11422569c0ea47971f67adba8464586c613ecf05d0c2522885","abstract_canon_sha256":"b5951ad5d0ab3af4c782a6bffab70411deba5ad1d6acebfb03e96e0eb530d0b4"},"schema_version":"1.0"},"canonical_sha256":"f4e9a447c02745f4032ba90763082292b95cd65570d8049e6095edc61949a54f","source":{"kind":"arxiv","id":"2401.00676","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00676","created_at":"2026-07-05T07:29:21Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00676v1","created_at":"2026-07-05T07:29:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00676","created_at":"2026-07-05T07:29:21Z"},{"alias_kind":"pith_short_12","alias_value":"6TU2IR6AE5C7","created_at":"2026-07-05T07:29:21Z"},{"alias_kind":"pith_short_16","alias_value":"6TU2IR6AE5C7IAZL","created_at":"2026-07-05T07:29:21Z"},{"alias_kind":"pith_short_8","alias_value":"6TU2IR6A","created_at":"2026-07-05T07:29:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6TU2IR6AE5C7IAZLVEDWGCBCSK","target":"record","payload":{"canonical_record":{"source":{"id":"2401.00676","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-01-01T06:04:52Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"249d7af5b2c8fa11422569c0ea47971f67adba8464586c613ecf05d0c2522885","abstract_canon_sha256":"b5951ad5d0ab3af4c782a6bffab70411deba5ad1d6acebfb03e96e0eb530d0b4"},"schema_version":"1.0"},"canonical_sha256":"f4e9a447c02745f4032ba90763082292b95cd65570d8049e6095edc61949a54f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:21.826966Z","signature_b64":"j7Vtk/hkRBKr+u1iI++borzqaxVTpbwCDOyHg80xmyHYLiwcvsU+RvY+gd7OPE0xlwjy7Z1pbGchP/W2FfHCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4e9a447c02745f4032ba90763082292b95cd65570d8049e6095edc61949a54f","last_reissued_at":"2026-07-05T07:29:21.826415Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:21.826415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.00676","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":"2026-07-05T07:29:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LxeVusDO1HAIrAQoNqGW7zTQi03j6tXPtc00Y7zl3Ab7k6WB/ESLN0s3GKEGeAeEFxLizfLlyQH5jf+NatkCCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:19:50.384604Z"},"content_sha256":"dd5ad15d23f2afbf0d735006bacf962e833b248a3ad7c086277c7a86d5c42c25","schema_version":"1.0","event_id":"sha256:dd5ad15d23f2afbf0d735006bacf962e833b248a3ad7c086277c7a86d5c42c25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6TU2IR6AE5C7IAZLVEDWGCBCSK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Digger: Detecting Copyright Content Mis-usage in Large Language Model Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CR","authors_text":"Gelei Deng, Guoai Xu, Guosheng Xu, Haodong Li, Haoyu Wang, Kailong Wang, Tianwei Zhang, Yang Liu, Yi Liu, Yuekang Li","submitted_at":"2024-01-01T06:04:52Z","abstract_excerpt":"Pre-training, which utilizes extensive and varied datasets, is a critical factor in the success of Large Language Models (LLMs) across numerous applications. However, the detailed makeup of these datasets is often not disclosed, leading to concerns about data security and potential misuse. This is particularly relevant when copyrighted material, still under legal protection, is used inappropriately, either intentionally or unintentionally, infringing on the rights of the authors.\n  In this paper, we introduce a detailed framework designed to detect and assess the presence of content from poten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00676","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/2401.00676/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":"2026-07-05T07:29:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xy69pxH7p2u6jh4mmocGT+ezEZ9JeRFViE1/Vj1Bfja2QMFs0HZrdZ5W8pCadUIRpLkULRC1xYeGoCbHOm7ABw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:19:50.385531Z"},"content_sha256":"c051379393b867199682b794e07ad92544e1e80cbeaf406833420ed3dd08ec6b","schema_version":"1.0","event_id":"sha256:c051379393b867199682b794e07ad92544e1e80cbeaf406833420ed3dd08ec6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6TU2IR6AE5C7IAZLVEDWGCBCSK/bundle.json","state_url":"https://pith.science/pith/6TU2IR6AE5C7IAZLVEDWGCBCSK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6TU2IR6AE5C7IAZLVEDWGCBCSK/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":"2026-08-09T08:19:50Z","links":{"resolver":"https://pith.science/pith/6TU2IR6AE5C7IAZLVEDWGCBCSK","bundle":"https://pith.science/pith/6TU2IR6AE5C7IAZLVEDWGCBCSK/bundle.json","state":"https://pith.science/pith/6TU2IR6AE5C7IAZLVEDWGCBCSK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6TU2IR6AE5C7IAZLVEDWGCBCSK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6TU2IR6AE5C7IAZLVEDWGCBCSK","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":"b5951ad5d0ab3af4c782a6bffab70411deba5ad1d6acebfb03e96e0eb530d0b4","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-01-01T06:04:52Z","title_canon_sha256":"249d7af5b2c8fa11422569c0ea47971f67adba8464586c613ecf05d0c2522885"},"schema_version":"1.0","source":{"id":"2401.00676","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00676","created_at":"2026-07-05T07:29:21Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00676v1","created_at":"2026-07-05T07:29:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00676","created_at":"2026-07-05T07:29:21Z"},{"alias_kind":"pith_short_12","alias_value":"6TU2IR6AE5C7","created_at":"2026-07-05T07:29:21Z"},{"alias_kind":"pith_short_16","alias_value":"6TU2IR6AE5C7IAZL","created_at":"2026-07-05T07:29:21Z"},{"alias_kind":"pith_short_8","alias_value":"6TU2IR6A","created_at":"2026-07-05T07:29:21Z"}],"graph_snapshots":[{"event_id":"sha256:c051379393b867199682b794e07ad92544e1e80cbeaf406833420ed3dd08ec6b","target":"graph","created_at":"2026-07-05T07:29:21Z","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/2401.00676/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-training, which utilizes extensive and varied datasets, is a critical factor in the success of Large Language Models (LLMs) across numerous applications. However, the detailed makeup of these datasets is often not disclosed, leading to concerns about data security and potential misuse. This is particularly relevant when copyrighted material, still under legal protection, is used inappropriately, either intentionally or unintentionally, infringing on the rights of the authors.\n  In this paper, we introduce a detailed framework designed to detect and assess the presence of content from poten","authors_text":"Gelei Deng, Guoai Xu, Guosheng Xu, Haodong Li, Haoyu Wang, Kailong Wang, Tianwei Zhang, Yang Liu, Yi Liu, Yuekang Li","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-01-01T06:04:52Z","title":"Digger: Detecting Copyright Content Mis-usage in Large Language Model Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00676","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:dd5ad15d23f2afbf0d735006bacf962e833b248a3ad7c086277c7a86d5c42c25","target":"record","created_at":"2026-07-05T07:29:21Z","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":"b5951ad5d0ab3af4c782a6bffab70411deba5ad1d6acebfb03e96e0eb530d0b4","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-01-01T06:04:52Z","title_canon_sha256":"249d7af5b2c8fa11422569c0ea47971f67adba8464586c613ecf05d0c2522885"},"schema_version":"1.0","source":{"id":"2401.00676","kind":"arxiv","version":1}},"canonical_sha256":"f4e9a447c02745f4032ba90763082292b95cd65570d8049e6095edc61949a54f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4e9a447c02745f4032ba90763082292b95cd65570d8049e6095edc61949a54f","first_computed_at":"2026-07-05T07:29:21.826415Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:29:21.826415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j7Vtk/hkRBKr+u1iI++borzqaxVTpbwCDOyHg80xmyHYLiwcvsU+RvY+gd7OPE0xlwjy7Z1pbGchP/W2FfHCBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:29:21.826966Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.00676","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd5ad15d23f2afbf0d735006bacf962e833b248a3ad7c086277c7a86d5c42c25","sha256:c051379393b867199682b794e07ad92544e1e80cbeaf406833420ed3dd08ec6b"],"state_sha256":"95975e5594794478be5c90e7e3a987661652e7476012f491733a5fd064c0a6eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+PBc++1gltYAPVnnC9DTxskkH4wXKkmtEucpMHT476sFUUxVHFwELxx7f//8T7eTs0cX9CexSn0n+rCLUPt2AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T08:19:50.392895Z","bundle_sha256":"8061e90217b175b1c0cca89700b8a24a244928b21954e71a460ec771d593c008"}}