{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GHPYH7DZAPQYW4VVIBUPO42HTR","short_pith_number":"pith:GHPYH7DZ","canonical_record":{"source":{"id":"2407.08707","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T17:44:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f3c3762c8c88397fefb329d99b33898c3fd68885018e1c730ae86b838f09788a","abstract_canon_sha256":"ee14b9f66a11437b07fb43f9cc6ae379a9bc4921a3f5ccb40a16943d199a5a78"},"schema_version":"1.0"},"canonical_sha256":"31df83fc7903e18b72b54068f773479c56379abeefcb035c231176ec3814bc3d","source":{"kind":"arxiv","id":"2407.08707","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08707","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08707v1","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08707","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"pith_short_12","alias_value":"GHPYH7DZAPQY","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"pith_short_16","alias_value":"GHPYH7DZAPQYW4VV","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"pith_short_8","alias_value":"GHPYH7DZ","created_at":"2026-07-05T08:42:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GHPYH7DZAPQYW4VVIBUPO42HTR","target":"record","payload":{"canonical_record":{"source":{"id":"2407.08707","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T17:44:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f3c3762c8c88397fefb329d99b33898c3fd68885018e1c730ae86b838f09788a","abstract_canon_sha256":"ee14b9f66a11437b07fb43f9cc6ae379a9bc4921a3f5ccb40a16943d199a5a78"},"schema_version":"1.0"},"canonical_sha256":"31df83fc7903e18b72b54068f773479c56379abeefcb035c231176ec3814bc3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:51.914396Z","signature_b64":"rty3Zk5PBYBlWaEXrnBOSs8u/HKKf7wGySrcPBcIzh+rcfaINEhH+l7njkyEvouQpjns4iVQKfGAqVIX0c83CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31df83fc7903e18b72b54068f773479c56379abeefcb035c231176ec3814bc3d","last_reissued_at":"2026-07-05T08:42:51.913982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:51.913982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.08707","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":"2026-07-05T08:42:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GRILUJbexZQFNbc2sDGQyQjyJ7xVol5fAcc8L4wpvB88IuRyhHBXQmNgv245yZak5g2sKvxupOubtlTBc4ZNBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:03:08.092104Z"},"content_sha256":"5375a0f9d8084ffbdebc18f35e88040b3a76cd17f2e446d52708897a28b191e2","schema_version":"1.0","event_id":"sha256:5375a0f9d8084ffbdebc18f35e88040b3a76cd17f2e446d52708897a28b191e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GHPYH7DZAPQYW4VVIBUPO42HTR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extracting Training Data from Document-Based VQA Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Federico Tombari, Florian Tram\\`er, Francesco Pinto, Nathalie Rauschmayr, Philip Torr","submitted_at":"2024-07-11T17:44:41Z","abstract_excerpt":"Vision-Language Models (VLMs) have made remarkable progress in document-based Visual Question Answering (i.e., responding to queries about the contents of an input document provided as an image). In this work, we show these models can memorize responses for training samples and regurgitate them even when the relevant visual information has been removed. This includes Personal Identifiable Information (PII) repeated once in the training set, indicating these models could divulge memorised sensitive information and therefore pose a privacy risk. We quantitatively measure the extractability of in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08707","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/2407.08707/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":"2026-07-05T08:42:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g1eWfUFk6VWViA6fVcIhok12maFjUIhI+WGiIDfSPMxAD+8ouF8U4YociRn7aTFq+HznSB2/hY4lD2Dns6pUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:03:08.092797Z"},"content_sha256":"d32e01ae6a7fa37fd49ae0446e7104e182e393ea1900e5a4743f50a2e0b02ad1","schema_version":"1.0","event_id":"sha256:d32e01ae6a7fa37fd49ae0446e7104e182e393ea1900e5a4743f50a2e0b02ad1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GHPYH7DZAPQYW4VVIBUPO42HTR/bundle.json","state_url":"https://pith.science/pith/GHPYH7DZAPQYW4VVIBUPO42HTR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GHPYH7DZAPQYW4VVIBUPO42HTR/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":"2026-08-10T12:03:08Z","links":{"resolver":"https://pith.science/pith/GHPYH7DZAPQYW4VVIBUPO42HTR","bundle":"https://pith.science/pith/GHPYH7DZAPQYW4VVIBUPO42HTR/bundle.json","state":"https://pith.science/pith/GHPYH7DZAPQYW4VVIBUPO42HTR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GHPYH7DZAPQYW4VVIBUPO42HTR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GHPYH7DZAPQYW4VVIBUPO42HTR","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":"ee14b9f66a11437b07fb43f9cc6ae379a9bc4921a3f5ccb40a16943d199a5a78","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T17:44:41Z","title_canon_sha256":"f3c3762c8c88397fefb329d99b33898c3fd68885018e1c730ae86b838f09788a"},"schema_version":"1.0","source":{"id":"2407.08707","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08707","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08707v1","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08707","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"pith_short_12","alias_value":"GHPYH7DZAPQY","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"pith_short_16","alias_value":"GHPYH7DZAPQYW4VV","created_at":"2026-07-05T08:42:51Z"},{"alias_kind":"pith_short_8","alias_value":"GHPYH7DZ","created_at":"2026-07-05T08:42:51Z"}],"graph_snapshots":[{"event_id":"sha256:d32e01ae6a7fa37fd49ae0446e7104e182e393ea1900e5a4743f50a2e0b02ad1","target":"graph","created_at":"2026-07-05T08:42:51Z","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/2407.08707/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) have made remarkable progress in document-based Visual Question Answering (i.e., responding to queries about the contents of an input document provided as an image). In this work, we show these models can memorize responses for training samples and regurgitate them even when the relevant visual information has been removed. This includes Personal Identifiable Information (PII) repeated once in the training set, indicating these models could divulge memorised sensitive information and therefore pose a privacy risk. We quantitatively measure the extractability of in","authors_text":"Federico Tombari, Florian Tram\\`er, Francesco Pinto, Nathalie Rauschmayr, Philip Torr","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T17:44:41Z","title":"Extracting Training Data from Document-Based VQA Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08707","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":"sha256:5375a0f9d8084ffbdebc18f35e88040b3a76cd17f2e446d52708897a28b191e2","target":"record","created_at":"2026-07-05T08:42:51Z","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":"ee14b9f66a11437b07fb43f9cc6ae379a9bc4921a3f5ccb40a16943d199a5a78","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T17:44:41Z","title_canon_sha256":"f3c3762c8c88397fefb329d99b33898c3fd68885018e1c730ae86b838f09788a"},"schema_version":"1.0","source":{"id":"2407.08707","kind":"arxiv","version":1}},"canonical_sha256":"31df83fc7903e18b72b54068f773479c56379abeefcb035c231176ec3814bc3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31df83fc7903e18b72b54068f773479c56379abeefcb035c231176ec3814bc3d","first_computed_at":"2026-07-05T08:42:51.913982Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:51.913982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rty3Zk5PBYBlWaEXrnBOSs8u/HKKf7wGySrcPBcIzh+rcfaINEhH+l7njkyEvouQpjns4iVQKfGAqVIX0c83CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:51.914396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.08707","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5375a0f9d8084ffbdebc18f35e88040b3a76cd17f2e446d52708897a28b191e2","sha256:d32e01ae6a7fa37fd49ae0446e7104e182e393ea1900e5a4743f50a2e0b02ad1"],"state_sha256":"c16dc0b097ef6ce77788caf31711be0bd56e7f52ed548a3c63509c054635c127"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5qbsfHRvoKAup7TES8UrZFvXKTCL7/MFZwjnxVmGHrOk0GbmugB2tFRe1dg9kBOCqZEF5lTORtNE2M6VpefQDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:03:08.098790Z","bundle_sha256":"3481ea44e537df1af74c8a26f00fa0acbc7e841da57588b0628bd071dd60a3cf"}}