{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OJHV3TF6H2C5PME7Y4ZSLYUR25","short_pith_number":"pith:OJHV3TF6","canonical_record":{"source":{"id":"2309.01674","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-04T15:37:03Z","cross_cats_sorted":["cs.AI","cs.DL"],"title_canon_sha256":"c0b86d0e75019e9e78896447f7fdd285be27a7c3177282f1146ab69e245185f7","abstract_canon_sha256":"c0f08130b23ae22868a4dfd4cb0d74ec7065b222f5747118f909b9b94c890e8f"},"schema_version":"1.0"},"canonical_sha256":"724f5dccbe3e85d7b09fc73325e291d76db82ce2312986d0190a74386d6cd791","source":{"kind":"arxiv","id":"2309.01674","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.01674","created_at":"2026-07-05T06:47:41Z"},{"alias_kind":"arxiv_version","alias_value":"2309.01674v1","created_at":"2026-07-05T06:47:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01674","created_at":"2026-07-05T06:47:41Z"},{"alias_kind":"pith_short_12","alias_value":"OJHV3TF6H2C5","created_at":"2026-07-05T06:47:41Z"},{"alias_kind":"pith_short_16","alias_value":"OJHV3TF6H2C5PME7","created_at":"2026-07-05T06:47:41Z"},{"alias_kind":"pith_short_8","alias_value":"OJHV3TF6","created_at":"2026-07-05T06:47:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OJHV3TF6H2C5PME7Y4ZSLYUR25","target":"record","payload":{"canonical_record":{"source":{"id":"2309.01674","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-04T15:37:03Z","cross_cats_sorted":["cs.AI","cs.DL"],"title_canon_sha256":"c0b86d0e75019e9e78896447f7fdd285be27a7c3177282f1146ab69e245185f7","abstract_canon_sha256":"c0f08130b23ae22868a4dfd4cb0d74ec7065b222f5747118f909b9b94c890e8f"},"schema_version":"1.0"},"canonical_sha256":"724f5dccbe3e85d7b09fc73325e291d76db82ce2312986d0190a74386d6cd791","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:41.438066Z","signature_b64":"JxE5Fdem68zF1C72Y/wkCj4nBeLX8jl/sMr+8cYjFsTxBmAJhIPHzcLoFBpit3JrVn++jpRhBGSIHI4R7Ko1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"724f5dccbe3e85d7b09fc73325e291d76db82ce2312986d0190a74386d6cd791","last_reissued_at":"2026-07-05T06:47:41.437576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:41.437576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.01674","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":"2026-07-05T06:47:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"arICdP2UlN/wcO8adqz++j+Wurf35Wi/U7qsaA0IFNWRSJfqZouvH+tvCA3geJxiODPc01ecTf4GxdN6H7QmCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:23:46.057452Z"},"content_sha256":"dce1a55bba073a070fa845ea562f838e4963c53f83354b04bf4b1f493cef8f7c","schema_version":"1.0","event_id":"sha256:dce1a55bba073a070fa845ea562f838e4963c53f83354b04bf4b1f493cef8f7c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OJHV3TF6H2C5PME7Y4ZSLYUR25","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prompt me a Dataset: An investigation of text-image prompting for historical image dataset creation using foundation models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DL"],"primary_cat":"cs.CV","authors_text":"Hassan El-Hajj, Matteo Valleriani","submitted_at":"2023-09-04T15:37:03Z","abstract_excerpt":"In this paper, we present a pipeline for image extraction from historical documents using foundation models, and evaluate text-image prompts and their effectiveness on humanities datasets of varying levels of complexity. The motivation for this approach stems from the high interest of historians in visual elements printed alongside historical texts on the one hand, and from the relative lack of well-annotated datasets within the humanities when compared to other domains. We propose a sequential approach that relies on GroundDINO and Meta's Segment-Anything-Model (SAM) to retrieve a significant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01674","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/2309.01674/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":"2026-07-05T06:47:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qp/QcY/bwvBjqYBST/QrDgwsaa59VXr7pM3aN3z27HhNxMPTzNhP2j7JbmUUmnahYHmLZU+b8Oc2Z8JRlg+LAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:23:46.057871Z"},"content_sha256":"a2ad8147b2f92e460721fa135fe7fcf5ac1780042648fa517d28071100bdf1a1","schema_version":"1.0","event_id":"sha256:a2ad8147b2f92e460721fa135fe7fcf5ac1780042648fa517d28071100bdf1a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OJHV3TF6H2C5PME7Y4ZSLYUR25/bundle.json","state_url":"https://pith.science/pith/OJHV3TF6H2C5PME7Y4ZSLYUR25/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OJHV3TF6H2C5PME7Y4ZSLYUR25/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":"2026-08-05T17:23:46Z","links":{"resolver":"https://pith.science/pith/OJHV3TF6H2C5PME7Y4ZSLYUR25","bundle":"https://pith.science/pith/OJHV3TF6H2C5PME7Y4ZSLYUR25/bundle.json","state":"https://pith.science/pith/OJHV3TF6H2C5PME7Y4ZSLYUR25/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OJHV3TF6H2C5PME7Y4ZSLYUR25/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OJHV3TF6H2C5PME7Y4ZSLYUR25","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":"c0f08130b23ae22868a4dfd4cb0d74ec7065b222f5747118f909b9b94c890e8f","cross_cats_sorted":["cs.AI","cs.DL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-04T15:37:03Z","title_canon_sha256":"c0b86d0e75019e9e78896447f7fdd285be27a7c3177282f1146ab69e245185f7"},"schema_version":"1.0","source":{"id":"2309.01674","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.01674","created_at":"2026-07-05T06:47:41Z"},{"alias_kind":"arxiv_version","alias_value":"2309.01674v1","created_at":"2026-07-05T06:47:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01674","created_at":"2026-07-05T06:47:41Z"},{"alias_kind":"pith_short_12","alias_value":"OJHV3TF6H2C5","created_at":"2026-07-05T06:47:41Z"},{"alias_kind":"pith_short_16","alias_value":"OJHV3TF6H2C5PME7","created_at":"2026-07-05T06:47:41Z"},{"alias_kind":"pith_short_8","alias_value":"OJHV3TF6","created_at":"2026-07-05T06:47:41Z"}],"graph_snapshots":[{"event_id":"sha256:a2ad8147b2f92e460721fa135fe7fcf5ac1780042648fa517d28071100bdf1a1","target":"graph","created_at":"2026-07-05T06:47:41Z","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/2309.01674/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present a pipeline for image extraction from historical documents using foundation models, and evaluate text-image prompts and their effectiveness on humanities datasets of varying levels of complexity. The motivation for this approach stems from the high interest of historians in visual elements printed alongside historical texts on the one hand, and from the relative lack of well-annotated datasets within the humanities when compared to other domains. We propose a sequential approach that relies on GroundDINO and Meta's Segment-Anything-Model (SAM) to retrieve a significant","authors_text":"Hassan El-Hajj, Matteo Valleriani","cross_cats":["cs.AI","cs.DL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-04T15:37:03Z","title":"Prompt me a Dataset: An investigation of text-image prompting for historical image dataset creation using foundation models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01674","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:dce1a55bba073a070fa845ea562f838e4963c53f83354b04bf4b1f493cef8f7c","target":"record","created_at":"2026-07-05T06:47:41Z","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":"c0f08130b23ae22868a4dfd4cb0d74ec7065b222f5747118f909b9b94c890e8f","cross_cats_sorted":["cs.AI","cs.DL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-04T15:37:03Z","title_canon_sha256":"c0b86d0e75019e9e78896447f7fdd285be27a7c3177282f1146ab69e245185f7"},"schema_version":"1.0","source":{"id":"2309.01674","kind":"arxiv","version":1}},"canonical_sha256":"724f5dccbe3e85d7b09fc73325e291d76db82ce2312986d0190a74386d6cd791","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"724f5dccbe3e85d7b09fc73325e291d76db82ce2312986d0190a74386d6cd791","first_computed_at":"2026-07-05T06:47:41.437576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:47:41.437576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JxE5Fdem68zF1C72Y/wkCj4nBeLX8jl/sMr+8cYjFsTxBmAJhIPHzcLoFBpit3JrVn++jpRhBGSIHI4R7Ko1Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:47:41.438066Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.01674","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dce1a55bba073a070fa845ea562f838e4963c53f83354b04bf4b1f493cef8f7c","sha256:a2ad8147b2f92e460721fa135fe7fcf5ac1780042648fa517d28071100bdf1a1"],"state_sha256":"454fa921216c96f2e90550c1a7808a453dfc8673b49cf3fd20e9d473609af385"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tAl0SdoaASoZNsePRv/G0KHd3nNXfFGsj5sBbMbMjf7uua8AKfVqZSLEugnChfkWUam1ahStFhG8RV/qLaikBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:23:46.061691Z","bundle_sha256":"7efcb8ec0d7b4fc0fa856aed2379bf4dd1a66efe2acc02ddc7ef4b9643e7c3ae"}}