{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BYGWOJXNUMM7RUWDV3256YDQ34","short_pith_number":"pith:BYGWOJXN","canonical_record":{"source":{"id":"2605.30462","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T18:38:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fbf3bd24e15a85c7fd07a958bdb6619eb2839eaa1bb904663da65caf561e56b8","abstract_canon_sha256":"3bb1dff6db7e88336fbde64a8aaac83be5199fb22036c1ae25c97fefe4968306"},"schema_version":"1.0"},"canonical_sha256":"0e0d6726eda319f8d2c3aef5df6070df178b7501d58a99900b5d1b5eb1ede7f2","source":{"kind":"arxiv","id":"2605.30462","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30462","created_at":"2026-06-01T01:02:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30462v1","created_at":"2026-06-01T01:02:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30462","created_at":"2026-06-01T01:02:55Z"},{"alias_kind":"pith_short_12","alias_value":"BYGWOJXNUMM7","created_at":"2026-06-01T01:02:55Z"},{"alias_kind":"pith_short_16","alias_value":"BYGWOJXNUMM7RUWD","created_at":"2026-06-01T01:02:55Z"},{"alias_kind":"pith_short_8","alias_value":"BYGWOJXN","created_at":"2026-06-01T01:02:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BYGWOJXNUMM7RUWDV3256YDQ34","target":"record","payload":{"canonical_record":{"source":{"id":"2605.30462","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T18:38:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fbf3bd24e15a85c7fd07a958bdb6619eb2839eaa1bb904663da65caf561e56b8","abstract_canon_sha256":"3bb1dff6db7e88336fbde64a8aaac83be5199fb22036c1ae25c97fefe4968306"},"schema_version":"1.0"},"canonical_sha256":"0e0d6726eda319f8d2c3aef5df6070df178b7501d58a99900b5d1b5eb1ede7f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:55.610628Z","signature_b64":"sBOg5UEdZWKVjswQVPlzJLtfXzZxR5OiPPCA7uECJkYoS4K7m4bJ/9EeSZgkPpiprRQOqh87jpH3Hx2GOuYAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e0d6726eda319f8d2c3aef5df6070df178b7501d58a99900b5d1b5eb1ede7f2","last_reissued_at":"2026-06-01T01:02:55.609720Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:55.609720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.30462","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":"2026-06-01T01:02:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q9+yZ74kBDr2VZcGXXUUgkXq4pfie9zXYJhb7wePFVqUjH3TNsABj3siUP2TZYwLnrQDSdgSGMqggoqB472OCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T14:39:13.508773Z"},"content_sha256":"d28f7b8912be2b6ea862bca387987f4f0317b3e1fe6664976b3952536b8c6d75","schema_version":"1.0","event_id":"sha256:d28f7b8912be2b6ea862bca387987f4f0317b3e1fe6664976b3952536b8c6d75"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BYGWOJXNUMM7RUWDV3256YDQ34","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"idSCD: Identifying Training Datasets through Semantic Correlation Descriptors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andrada Gobeaja, Elena Burceanu, Ionut Hodoroaga, Marius Leordeanu","submitted_at":"2026-05-28T18:38:15Z","abstract_excerpt":"Can a dataset be recognized from the spurious correlations it induces during training? We argue that datasets leave dataset-specific traces in a model's learned semantic correlation structure: incidental regularities that are predictive within a dataset, but not causal for the underlying task, can be internalized during training. We use this insight to study dataset-level membership inference, moving beyond existing methods that rely on behavioral or distributional evidence such as confidence scores, losses, margins, generated samples, or query responses. We introduce a white-box semantic fing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30462","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/2605.30462/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":"2026-06-01T01:02:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/xVoUxd0NEU3wW8DMocfdVZvb1q6ffQ2OWJqLRguQFnUMYYaq3W9cCQmGvXVMG+sZawTu0um+KqQDJbLWP3YCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T14:39:13.509536Z"},"content_sha256":"d06140166fb1514e63a8ca54a0a32c44bdfc72a6d2469edf78041e3d870da3e4","schema_version":"1.0","event_id":"sha256:d06140166fb1514e63a8ca54a0a32c44bdfc72a6d2469edf78041e3d870da3e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BYGWOJXNUMM7RUWDV3256YDQ34/bundle.json","state_url":"https://pith.science/pith/BYGWOJXNUMM7RUWDV3256YDQ34/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BYGWOJXNUMM7RUWDV3256YDQ34/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":"2026-06-08T14:39:13Z","links":{"resolver":"https://pith.science/pith/BYGWOJXNUMM7RUWDV3256YDQ34","bundle":"https://pith.science/pith/BYGWOJXNUMM7RUWDV3256YDQ34/bundle.json","state":"https://pith.science/pith/BYGWOJXNUMM7RUWDV3256YDQ34/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BYGWOJXNUMM7RUWDV3256YDQ34/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BYGWOJXNUMM7RUWDV3256YDQ34","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":"3bb1dff6db7e88336fbde64a8aaac83be5199fb22036c1ae25c97fefe4968306","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T18:38:15Z","title_canon_sha256":"fbf3bd24e15a85c7fd07a958bdb6619eb2839eaa1bb904663da65caf561e56b8"},"schema_version":"1.0","source":{"id":"2605.30462","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30462","created_at":"2026-06-01T01:02:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30462v1","created_at":"2026-06-01T01:02:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30462","created_at":"2026-06-01T01:02:55Z"},{"alias_kind":"pith_short_12","alias_value":"BYGWOJXNUMM7","created_at":"2026-06-01T01:02:55Z"},{"alias_kind":"pith_short_16","alias_value":"BYGWOJXNUMM7RUWD","created_at":"2026-06-01T01:02:55Z"},{"alias_kind":"pith_short_8","alias_value":"BYGWOJXN","created_at":"2026-06-01T01:02:55Z"}],"graph_snapshots":[{"event_id":"sha256:d06140166fb1514e63a8ca54a0a32c44bdfc72a6d2469edf78041e3d870da3e4","target":"graph","created_at":"2026-06-01T01:02:55Z","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/2605.30462/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Can a dataset be recognized from the spurious correlations it induces during training? We argue that datasets leave dataset-specific traces in a model's learned semantic correlation structure: incidental regularities that are predictive within a dataset, but not causal for the underlying task, can be internalized during training. We use this insight to study dataset-level membership inference, moving beyond existing methods that rely on behavioral or distributional evidence such as confidence scores, losses, margins, generated samples, or query responses. We introduce a white-box semantic fing","authors_text":"Andrada Gobeaja, Elena Burceanu, Ionut Hodoroaga, Marius Leordeanu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T18:38:15Z","title":"idSCD: Identifying Training Datasets through Semantic Correlation Descriptors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30462","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:d28f7b8912be2b6ea862bca387987f4f0317b3e1fe6664976b3952536b8c6d75","target":"record","created_at":"2026-06-01T01:02:55Z","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":"3bb1dff6db7e88336fbde64a8aaac83be5199fb22036c1ae25c97fefe4968306","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T18:38:15Z","title_canon_sha256":"fbf3bd24e15a85c7fd07a958bdb6619eb2839eaa1bb904663da65caf561e56b8"},"schema_version":"1.0","source":{"id":"2605.30462","kind":"arxiv","version":1}},"canonical_sha256":"0e0d6726eda319f8d2c3aef5df6070df178b7501d58a99900b5d1b5eb1ede7f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e0d6726eda319f8d2c3aef5df6070df178b7501d58a99900b5d1b5eb1ede7f2","first_computed_at":"2026-06-01T01:02:55.609720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:02:55.609720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sBOg5UEdZWKVjswQVPlzJLtfXzZxR5OiPPCA7uECJkYoS4K7m4bJ/9EeSZgkPpiprRQOqh87jpH3Hx2GOuYAAQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:02:55.610628Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30462","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d28f7b8912be2b6ea862bca387987f4f0317b3e1fe6664976b3952536b8c6d75","sha256:d06140166fb1514e63a8ca54a0a32c44bdfc72a6d2469edf78041e3d870da3e4"],"state_sha256":"d11126e8692890bb4ba2536ea3d1e1b347ab8e14350fd996a581549bcc8cebcd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6nmi0yGsWphgAy3QV7fGsRbQkNfURqmtQzl/P1FvM5fMUMGK4tXaF4nj01XRB2wBewQYEWxKgtYkcU/kbek1Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T14:39:13.514022Z","bundle_sha256":"cf560129be4fb13e3008c9576bce773a45756ace2c73da98afec9d0e965f1851"}}