{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EBATWQCZWZ5573QYNQ5HGRL6GJ","short_pith_number":"pith:EBATWQCZ","canonical_record":{"source":{"id":"2606.06502","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-18T14:48:44Z","cross_cats_sorted":[],"title_canon_sha256":"7e17914d5efa2a552c6b38aefd96e157fc13a36cd6e88451f2074b7078bba093","abstract_canon_sha256":"e14789642d7db903df6c83b81200a228da365bdc7316bda2c61878b9ef8fbf6f"},"schema_version":"1.0"},"canonical_sha256":"20413b4059b67bdfee186c3a73457e3245312f5abacd2498219f51648e56a67c","source":{"kind":"arxiv","id":"2606.06502","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06502","created_at":"2026-06-08T00:03:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06502v1","created_at":"2026-06-08T00:03:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06502","created_at":"2026-06-08T00:03:39Z"},{"alias_kind":"pith_short_12","alias_value":"EBATWQCZWZ55","created_at":"2026-06-08T00:03:39Z"},{"alias_kind":"pith_short_16","alias_value":"EBATWQCZWZ5573QY","created_at":"2026-06-08T00:03:39Z"},{"alias_kind":"pith_short_8","alias_value":"EBATWQCZ","created_at":"2026-06-08T00:03:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EBATWQCZWZ5573QYNQ5HGRL6GJ","target":"record","payload":{"canonical_record":{"source":{"id":"2606.06502","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-18T14:48:44Z","cross_cats_sorted":[],"title_canon_sha256":"7e17914d5efa2a552c6b38aefd96e157fc13a36cd6e88451f2074b7078bba093","abstract_canon_sha256":"e14789642d7db903df6c83b81200a228da365bdc7316bda2c61878b9ef8fbf6f"},"schema_version":"1.0"},"canonical_sha256":"20413b4059b67bdfee186c3a73457e3245312f5abacd2498219f51648e56a67c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T00:03:39.672999Z","signature_b64":"rlu9fMkDN5cN8GXty/ABcwVX/OWOaWQ8/L2Jgnx3KoGEwAAMRpDlLYTrQbjm97ClRKbnkdRlTAJTy0vESIAeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20413b4059b67bdfee186c3a73457e3245312f5abacd2498219f51648e56a67c","last_reissued_at":"2026-06-08T00:03:39.672121Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T00:03:39.672121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.06502","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":"2026-06-08T00:03:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xi6+XvTG0NR7EYDOGSZN+o/FvJWcoTs7Fa2jMl47x2XycjhAbHMQb9LSsBkGPZ11hlaqBHR5hbh9gAhw70qgBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T08:41:24.187645Z"},"content_sha256":"95c62584f7886c8432ecafa4b05b61b4389c6773625bd9260dfd9d60a7417600","schema_version":"1.0","event_id":"sha256:95c62584f7886c8432ecafa4b05b61b4389c6773625bd9260dfd9d60a7417600"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EBATWQCZWZ5573QYNQ5HGRL6GJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Subtle Injection for Ground-truth Inference of LLM Training Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Abraham Itzhak Weinberg","submitted_at":"2026-05-18T14:48:44Z","abstract_excerpt":"As large language models (LLMs) are increasingly trained on scraped web corpora without authorisation, content owners require forensic methods to prove that their documents were included in a model's training set. We propose \\textbf{SIGIL} (\\textbf{S}ubtle \\textbf{I}njection for \\textbf{G}round-truth \\textbf{I}nference of \\textbf{L}LM training data), a framework that embeds imperceptible \\emph{canary sequences} into protected text and code such that any LLM trained on those documents exhibits statistically detectable behavioural signatures when probed with targeted queries.\n  SIGIL defines fiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06502","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/2606.06502/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":"2026-06-08T00:03:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kztoVReLHMs/njC26Ut7ULx3t42/uDfmu/2jmtd8b0g7skDw2BsUfesDo8MtfHm0wFgVUb+FfqnmpjUZso4tAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T08:41:24.188014Z"},"content_sha256":"25ab134551bd1a0403a9894b1e5a71bde94bfab9ff34546224a5fc0666d6fed3","schema_version":"1.0","event_id":"sha256:25ab134551bd1a0403a9894b1e5a71bde94bfab9ff34546224a5fc0666d6fed3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EBATWQCZWZ5573QYNQ5HGRL6GJ/bundle.json","state_url":"https://pith.science/pith/EBATWQCZWZ5573QYNQ5HGRL6GJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EBATWQCZWZ5573QYNQ5HGRL6GJ/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":"2026-07-02T08:41:24Z","links":{"resolver":"https://pith.science/pith/EBATWQCZWZ5573QYNQ5HGRL6GJ","bundle":"https://pith.science/pith/EBATWQCZWZ5573QYNQ5HGRL6GJ/bundle.json","state":"https://pith.science/pith/EBATWQCZWZ5573QYNQ5HGRL6GJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EBATWQCZWZ5573QYNQ5HGRL6GJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EBATWQCZWZ5573QYNQ5HGRL6GJ","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":"e14789642d7db903df6c83b81200a228da365bdc7316bda2c61878b9ef8fbf6f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-18T14:48:44Z","title_canon_sha256":"7e17914d5efa2a552c6b38aefd96e157fc13a36cd6e88451f2074b7078bba093"},"schema_version":"1.0","source":{"id":"2606.06502","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06502","created_at":"2026-06-08T00:03:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06502v1","created_at":"2026-06-08T00:03:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06502","created_at":"2026-06-08T00:03:39Z"},{"alias_kind":"pith_short_12","alias_value":"EBATWQCZWZ55","created_at":"2026-06-08T00:03:39Z"},{"alias_kind":"pith_short_16","alias_value":"EBATWQCZWZ5573QY","created_at":"2026-06-08T00:03:39Z"},{"alias_kind":"pith_short_8","alias_value":"EBATWQCZ","created_at":"2026-06-08T00:03:39Z"}],"graph_snapshots":[{"event_id":"sha256:25ab134551bd1a0403a9894b1e5a71bde94bfab9ff34546224a5fc0666d6fed3","target":"graph","created_at":"2026-06-08T00:03:39Z","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/2606.06502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) are increasingly trained on scraped web corpora without authorisation, content owners require forensic methods to prove that their documents were included in a model's training set. We propose \\textbf{SIGIL} (\\textbf{S}ubtle \\textbf{I}njection for \\textbf{G}round-truth \\textbf{I}nference of \\textbf{L}LM training data), a framework that embeds imperceptible \\emph{canary sequences} into protected text and code such that any LLM trained on those documents exhibits statistically detectable behavioural signatures when probed with targeted queries.\n  SIGIL defines fiv","authors_text":"Abraham Itzhak Weinberg","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-18T14:48:44Z","title":"Subtle Injection for Ground-truth Inference of LLM Training Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06502","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":"sha256:95c62584f7886c8432ecafa4b05b61b4389c6773625bd9260dfd9d60a7417600","target":"record","created_at":"2026-06-08T00:03:39Z","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":"e14789642d7db903df6c83b81200a228da365bdc7316bda2c61878b9ef8fbf6f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-18T14:48:44Z","title_canon_sha256":"7e17914d5efa2a552c6b38aefd96e157fc13a36cd6e88451f2074b7078bba093"},"schema_version":"1.0","source":{"id":"2606.06502","kind":"arxiv","version":1}},"canonical_sha256":"20413b4059b67bdfee186c3a73457e3245312f5abacd2498219f51648e56a67c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20413b4059b67bdfee186c3a73457e3245312f5abacd2498219f51648e56a67c","first_computed_at":"2026-06-08T00:03:39.672121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T00:03:39.672121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rlu9fMkDN5cN8GXty/ABcwVX/OWOaWQ8/L2Jgnx3KoGEwAAMRpDlLYTrQbjm97ClRKbnkdRlTAJTy0vESIAeAw==","signature_status":"signed_v1","signed_at":"2026-06-08T00:03:39.672999Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06502","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95c62584f7886c8432ecafa4b05b61b4389c6773625bd9260dfd9d60a7417600","sha256:25ab134551bd1a0403a9894b1e5a71bde94bfab9ff34546224a5fc0666d6fed3"],"state_sha256":"8916be72e31aa09d66ef8eba54ed1d2c2375f6d788c0365c1adf371de10418ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l4EX3FPiBZlLNjL+/ffeCNgcK1os9+07oE2JGPGQSPvrCHspyCClSVOgMOKpjhGV2bUJZ8290g7ZLK6dfeQXDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T08:41:24.190139Z","bundle_sha256":"d43b2f7daba15725ef1762629f7fefd3504fd8750fabc4a8f76ac882f3fe3c87"}}