{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VS6HEFFCCWQOZ6GIKP7BPZNKWD","short_pith_number":"pith:VS6HEFFC","canonical_record":{"source":{"id":"2506.15271","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T08:46:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6ec96af31a2b475624d97ca07871d06b0d79b7cda9527fd3d1871a284aa9a0a1","abstract_canon_sha256":"bef6b85a755c8bb3c6614a85ad3bd9ec166c8cd68afff798df09fe1b46c441a2"},"schema_version":"1.0"},"canonical_sha256":"acbc7214a215a0ecf8c853fe17e5aab0c5c70618c12575fc766a2578ac978076","source":{"kind":"arxiv","id":"2506.15271","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.15271","created_at":"2026-07-05T11:23:40Z"},{"alias_kind":"arxiv_version","alias_value":"2506.15271v1","created_at":"2026-07-05T11:23:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15271","created_at":"2026-07-05T11:23:40Z"},{"alias_kind":"pith_short_12","alias_value":"VS6HEFFCCWQO","created_at":"2026-07-05T11:23:40Z"},{"alias_kind":"pith_short_16","alias_value":"VS6HEFFCCWQOZ6GI","created_at":"2026-07-05T11:23:40Z"},{"alias_kind":"pith_short_8","alias_value":"VS6HEFFC","created_at":"2026-07-05T11:23:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VS6HEFFCCWQOZ6GIKP7BPZNKWD","target":"record","payload":{"canonical_record":{"source":{"id":"2506.15271","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T08:46:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6ec96af31a2b475624d97ca07871d06b0d79b7cda9527fd3d1871a284aa9a0a1","abstract_canon_sha256":"bef6b85a755c8bb3c6614a85ad3bd9ec166c8cd68afff798df09fe1b46c441a2"},"schema_version":"1.0"},"canonical_sha256":"acbc7214a215a0ecf8c853fe17e5aab0c5c70618c12575fc766a2578ac978076","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:40.509799Z","signature_b64":"OuBYZTt+HZDcxA+ybk7rDb+Jk75A6t3TeBh4zsmiOg9nPOiAmBdrHyCkWX65LBLEIDaiqfxV9dJVflkMOTD5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acbc7214a215a0ecf8c853fe17e5aab0c5c70618c12575fc766a2578ac978076","last_reissued_at":"2026-07-05T11:23:40.509142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:40.509142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.15271","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":"2026-07-05T11:23:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MvvXxbkp/Jfg6ZmUAH4PhToHU460hDPAfWtaDVa1hsy024xg60PeVyM/hFkmXcJw5lLmD6C9eDNm7kmp2UZKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T14:46:11.252511Z"},"content_sha256":"dda681ed7d1f49f08c4ed98070161c2553289809dc5392ac31e4c01594f6b884","schema_version":"1.0","event_id":"sha256:dda681ed7d1f49f08c4ed98070161c2553289809dc5392ac31e4c01594f6b884"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VS6HEFFCCWQOZ6GIKP7BPZNKWD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unlocking Post-hoc Dataset Inference with Synthetic Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adam Dziedzic, Bihe Zhao, Franziska Boenisch, Pratyush Maini","submitted_at":"2025-06-18T08:46:59Z","abstract_excerpt":"The remarkable capabilities of Large Language Models (LLMs) can be mainly attributed to their massive training datasets, which are often scraped from the internet without respecting data owners' intellectual property rights. Dataset Inference (DI) offers a potential remedy by identifying whether a suspect dataset was used in training, thereby enabling data owners to verify unauthorized use. However, existing DI methods require a private set-known to be absent from training-that closely matches the compromised dataset's distribution. Such in-distribution, held-out data is rarely available in pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15271","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/2506.15271/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":"2026-07-05T11:23:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c/s+epNAV6dv3k7BqoN8Xg04zvQL5r9dHC54qYxbnYeGKOY+enk5np2T57/eMfNMkFYB94oCIx6U/VzC3xQSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T14:46:11.253039Z"},"content_sha256":"ff565cf2fb46632da22ba950b2f7fde1e19d7af9631945e7b12a3e6bb4f4fd44","schema_version":"1.0","event_id":"sha256:ff565cf2fb46632da22ba950b2f7fde1e19d7af9631945e7b12a3e6bb4f4fd44"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VS6HEFFCCWQOZ6GIKP7BPZNKWD/bundle.json","state_url":"https://pith.science/pith/VS6HEFFCCWQOZ6GIKP7BPZNKWD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VS6HEFFCCWQOZ6GIKP7BPZNKWD/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":"2026-08-22T14:46:11Z","links":{"resolver":"https://pith.science/pith/VS6HEFFCCWQOZ6GIKP7BPZNKWD","bundle":"https://pith.science/pith/VS6HEFFCCWQOZ6GIKP7BPZNKWD/bundle.json","state":"https://pith.science/pith/VS6HEFFCCWQOZ6GIKP7BPZNKWD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VS6HEFFCCWQOZ6GIKP7BPZNKWD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VS6HEFFCCWQOZ6GIKP7BPZNKWD","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":"bef6b85a755c8bb3c6614a85ad3bd9ec166c8cd68afff798df09fe1b46c441a2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T08:46:59Z","title_canon_sha256":"6ec96af31a2b475624d97ca07871d06b0d79b7cda9527fd3d1871a284aa9a0a1"},"schema_version":"1.0","source":{"id":"2506.15271","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.15271","created_at":"2026-07-05T11:23:40Z"},{"alias_kind":"arxiv_version","alias_value":"2506.15271v1","created_at":"2026-07-05T11:23:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15271","created_at":"2026-07-05T11:23:40Z"},{"alias_kind":"pith_short_12","alias_value":"VS6HEFFCCWQO","created_at":"2026-07-05T11:23:40Z"},{"alias_kind":"pith_short_16","alias_value":"VS6HEFFCCWQOZ6GI","created_at":"2026-07-05T11:23:40Z"},{"alias_kind":"pith_short_8","alias_value":"VS6HEFFC","created_at":"2026-07-05T11:23:40Z"}],"graph_snapshots":[{"event_id":"sha256:ff565cf2fb46632da22ba950b2f7fde1e19d7af9631945e7b12a3e6bb4f4fd44","target":"graph","created_at":"2026-07-05T11:23:40Z","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/2506.15271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The remarkable capabilities of Large Language Models (LLMs) can be mainly attributed to their massive training datasets, which are often scraped from the internet without respecting data owners' intellectual property rights. Dataset Inference (DI) offers a potential remedy by identifying whether a suspect dataset was used in training, thereby enabling data owners to verify unauthorized use. However, existing DI methods require a private set-known to be absent from training-that closely matches the compromised dataset's distribution. Such in-distribution, held-out data is rarely available in pr","authors_text":"Adam Dziedzic, Bihe Zhao, Franziska Boenisch, Pratyush Maini","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T08:46:59Z","title":"Unlocking Post-hoc Dataset Inference with Synthetic Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15271","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:dda681ed7d1f49f08c4ed98070161c2553289809dc5392ac31e4c01594f6b884","target":"record","created_at":"2026-07-05T11:23:40Z","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":"bef6b85a755c8bb3c6614a85ad3bd9ec166c8cd68afff798df09fe1b46c441a2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T08:46:59Z","title_canon_sha256":"6ec96af31a2b475624d97ca07871d06b0d79b7cda9527fd3d1871a284aa9a0a1"},"schema_version":"1.0","source":{"id":"2506.15271","kind":"arxiv","version":1}},"canonical_sha256":"acbc7214a215a0ecf8c853fe17e5aab0c5c70618c12575fc766a2578ac978076","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acbc7214a215a0ecf8c853fe17e5aab0c5c70618c12575fc766a2578ac978076","first_computed_at":"2026-07-05T11:23:40.509142Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:40.509142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OuBYZTt+HZDcxA+ybk7rDb+Jk75A6t3TeBh4zsmiOg9nPOiAmBdrHyCkWX65LBLEIDaiqfxV9dJVflkMOTD5CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:40.509799Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.15271","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dda681ed7d1f49f08c4ed98070161c2553289809dc5392ac31e4c01594f6b884","sha256:ff565cf2fb46632da22ba950b2f7fde1e19d7af9631945e7b12a3e6bb4f4fd44"],"state_sha256":"bc7065172f23a39e491d582ec68f8895b6d27370bdaf6e1d8ad2682c477cd7ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xd9JMaBDS454o/7Sh0fRjSJgkm/genrJsSTyklmEQ09oDAjAlP4PrFsyp9S34eWfat3nIcOGSDOoVWUR3dK1Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T14:46:11.257455Z","bundle_sha256":"b5d8cf94bb0184865a44a74f11da8bdbcf845ac360b3672d046e3c2b8f5c2925"}}