{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KQMU5UVILWR3PX7AC2RRH4J6HJ","short_pith_number":"pith:KQMU5UVI","canonical_record":{"source":{"id":"2303.03919","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-06T04:22:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"36e775a514ff76ed947fec69e680aea760a2f380ca98f61cc7ebc68d369c804e","abstract_canon_sha256":"f72ea60b19cfc8f8731ccac7bc294bbca2e5bdb20e74da151a84c278530c5564"},"schema_version":"1.0"},"canonical_sha256":"54194ed2a85da3b7dfe016a313f13e3a5cc6c936ee6403d0031b88207852cb6f","source":{"kind":"arxiv","id":"2303.03919","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.03919","created_at":"2026-07-05T07:23:56Z"},{"alias_kind":"arxiv_version","alias_value":"2303.03919v2","created_at":"2026-07-05T07:23:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03919","created_at":"2026-07-05T07:23:56Z"},{"alias_kind":"pith_short_12","alias_value":"KQMU5UVILWR3","created_at":"2026-07-05T07:23:56Z"},{"alias_kind":"pith_short_16","alias_value":"KQMU5UVILWR3PX7A","created_at":"2026-07-05T07:23:56Z"},{"alias_kind":"pith_short_8","alias_value":"KQMU5UVI","created_at":"2026-07-05T07:23:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KQMU5UVILWR3PX7AC2RRH4J6HJ","target":"record","payload":{"canonical_record":{"source":{"id":"2303.03919","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-06T04:22:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"36e775a514ff76ed947fec69e680aea760a2f380ca98f61cc7ebc68d369c804e","abstract_canon_sha256":"f72ea60b19cfc8f8731ccac7bc294bbca2e5bdb20e74da151a84c278530c5564"},"schema_version":"1.0"},"canonical_sha256":"54194ed2a85da3b7dfe016a313f13e3a5cc6c936ee6403d0031b88207852cb6f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:56.132842Z","signature_b64":"exeToSXSRnjrtqITh8GZLFYL2t0Cv57igM43SXZLky3PlWFD/1CqhR8w/gUIg0pvUkm3tkv3R9K1EOmUXo/JCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54194ed2a85da3b7dfe016a313f13e3a5cc6c936ee6403d0031b88207852cb6f","last_reissued_at":"2026-07-05T07:23:56.132352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:56.132352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.03919","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:23:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jXCgGnXNEx4r1OzFx5zdS6f81xazKYX5S0jFPQrmmJXG9N1weKLQtOX6J9Col/14I/eCDnpHdD5hWfa7rNt1DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T01:35:09.501228Z"},"content_sha256":"33bfcaaf05c2c6267463b039da41e47f0deecb95d52f871d688641d862b20465","schema_version":"1.0","event_id":"sha256:33bfcaaf05c2c6267463b039da41e47f0deecb95d52f871d688641d862b20465"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KQMU5UVILWR3PX7AC2RRH4J6HJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Portraits: Recording Foundation Model Training Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Benjamin Van Durme, Marc Marone","submitted_at":"2023-03-06T04:22:33Z","abstract_excerpt":"Foundation models are trained on increasingly immense and opaque datasets. Even while these models are now key in AI system building, it can be difficult to answer the straightforward question: has the model already encountered a given example during training? We therefore propose a widespread adoption of Data Portraits: artifacts that record training data and allow for downstream inspection. First we outline the properties of such an artifact and discuss how existing solutions can be used to increase transparency. We then propose and implement a solution based on data sketching, stressing fas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03919","kind":"arxiv","version":2},"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/2303.03919/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":"2026-07-05T07:23:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U4wCC9hptCjOZNWIBGwVfdN1f1Fvr2tn4ARSqQU7rMSd4b1riEKf1Wj1XQeJII7zQOq+zLgTqoLeGgh+f64ZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T01:35:09.502170Z"},"content_sha256":"027ac52a603544aec19d141efd7867863c976e55f56757418c9fe7f082e483e5","schema_version":"1.0","event_id":"sha256:027ac52a603544aec19d141efd7867863c976e55f56757418c9fe7f082e483e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KQMU5UVILWR3PX7AC2RRH4J6HJ/bundle.json","state_url":"https://pith.science/pith/KQMU5UVILWR3PX7AC2RRH4J6HJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KQMU5UVILWR3PX7AC2RRH4J6HJ/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":"2026-08-14T01:35:09Z","links":{"resolver":"https://pith.science/pith/KQMU5UVILWR3PX7AC2RRH4J6HJ","bundle":"https://pith.science/pith/KQMU5UVILWR3PX7AC2RRH4J6HJ/bundle.json","state":"https://pith.science/pith/KQMU5UVILWR3PX7AC2RRH4J6HJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KQMU5UVILWR3PX7AC2RRH4J6HJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KQMU5UVILWR3PX7AC2RRH4J6HJ","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":"f72ea60b19cfc8f8731ccac7bc294bbca2e5bdb20e74da151a84c278530c5564","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-06T04:22:33Z","title_canon_sha256":"36e775a514ff76ed947fec69e680aea760a2f380ca98f61cc7ebc68d369c804e"},"schema_version":"1.0","source":{"id":"2303.03919","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.03919","created_at":"2026-07-05T07:23:56Z"},{"alias_kind":"arxiv_version","alias_value":"2303.03919v2","created_at":"2026-07-05T07:23:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03919","created_at":"2026-07-05T07:23:56Z"},{"alias_kind":"pith_short_12","alias_value":"KQMU5UVILWR3","created_at":"2026-07-05T07:23:56Z"},{"alias_kind":"pith_short_16","alias_value":"KQMU5UVILWR3PX7A","created_at":"2026-07-05T07:23:56Z"},{"alias_kind":"pith_short_8","alias_value":"KQMU5UVI","created_at":"2026-07-05T07:23:56Z"}],"graph_snapshots":[{"event_id":"sha256:027ac52a603544aec19d141efd7867863c976e55f56757418c9fe7f082e483e5","target":"graph","created_at":"2026-07-05T07:23:56Z","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/2303.03919/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Foundation models are trained on increasingly immense and opaque datasets. Even while these models are now key in AI system building, it can be difficult to answer the straightforward question: has the model already encountered a given example during training? We therefore propose a widespread adoption of Data Portraits: artifacts that record training data and allow for downstream inspection. First we outline the properties of such an artifact and discuss how existing solutions can be used to increase transparency. We then propose and implement a solution based on data sketching, stressing fas","authors_text":"Benjamin Van Durme, Marc Marone","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-06T04:22:33Z","title":"Data Portraits: Recording Foundation Model Training Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03919","kind":"arxiv","version":2},"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":"sha256:33bfcaaf05c2c6267463b039da41e47f0deecb95d52f871d688641d862b20465","target":"record","created_at":"2026-07-05T07:23:56Z","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":"f72ea60b19cfc8f8731ccac7bc294bbca2e5bdb20e74da151a84c278530c5564","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-06T04:22:33Z","title_canon_sha256":"36e775a514ff76ed947fec69e680aea760a2f380ca98f61cc7ebc68d369c804e"},"schema_version":"1.0","source":{"id":"2303.03919","kind":"arxiv","version":2}},"canonical_sha256":"54194ed2a85da3b7dfe016a313f13e3a5cc6c936ee6403d0031b88207852cb6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54194ed2a85da3b7dfe016a313f13e3a5cc6c936ee6403d0031b88207852cb6f","first_computed_at":"2026-07-05T07:23:56.132352Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:23:56.132352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"exeToSXSRnjrtqITh8GZLFYL2t0Cv57igM43SXZLky3PlWFD/1CqhR8w/gUIg0pvUkm3tkv3R9K1EOmUXo/JCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:23:56.132842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.03919","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33bfcaaf05c2c6267463b039da41e47f0deecb95d52f871d688641d862b20465","sha256:027ac52a603544aec19d141efd7867863c976e55f56757418c9fe7f082e483e5"],"state_sha256":"d0b0df2d419039602b516e641cd7af296909055e44a8fc4b9245b16b2fda375e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+LHYQYVfQgw4jTwyVfYccskwdCD+aBc08k3s/O5CWscO0T6zblTFeCwq8pQH0do7+Y2F3d4MRtmHigS2botzCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T01:35:09.515116Z","bundle_sha256":"0d244faeffff3f42db31a0c576c1d8d18067570e20897009bbf5b5bbafa1c2ab"}}