{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:I37ACXRGO764OC2Y45QXUXVUCT","short_pith_number":"pith:I37ACXRG","canonical_record":{"source":{"id":"2309.15535","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-27T09:53:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1bf610a71be7b9cb0ded6b44b3f3f15d844c79de8db579772d7bd215a72641eb","abstract_canon_sha256":"49ddb3e8b3e47e24f125ae5d15d7a5587df59d79efce632245d0416de8bc1711"},"schema_version":"1.0"},"canonical_sha256":"46fe015e2677fdc70b58e7617a5eb414d208f0f5048c2e73522ed80702ea7f96","source":{"kind":"arxiv","id":"2309.15535","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15535","created_at":"2026-07-05T07:23:29Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15535v1","created_at":"2026-07-05T07:23:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15535","created_at":"2026-07-05T07:23:29Z"},{"alias_kind":"pith_short_12","alias_value":"I37ACXRGO764","created_at":"2026-07-05T07:23:29Z"},{"alias_kind":"pith_short_16","alias_value":"I37ACXRGO764OC2Y","created_at":"2026-07-05T07:23:29Z"},{"alias_kind":"pith_short_8","alias_value":"I37ACXRG","created_at":"2026-07-05T07:23:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:I37ACXRGO764OC2Y45QXUXVUCT","target":"record","payload":{"canonical_record":{"source":{"id":"2309.15535","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-27T09:53:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1bf610a71be7b9cb0ded6b44b3f3f15d844c79de8db579772d7bd215a72641eb","abstract_canon_sha256":"49ddb3e8b3e47e24f125ae5d15d7a5587df59d79efce632245d0416de8bc1711"},"schema_version":"1.0"},"canonical_sha256":"46fe015e2677fdc70b58e7617a5eb414d208f0f5048c2e73522ed80702ea7f96","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:29.238823Z","signature_b64":"AceYXHTUPmIqoUCjQslk9qTRTJ51quR3LVcF/45YXSXY6E8yLXhGWsgyyDLLvnkMGFwUYZJvd7jUGU/xZOaXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46fe015e2677fdc70b58e7617a5eb414d208f0f5048c2e73522ed80702ea7f96","last_reissued_at":"2026-07-05T07:23:29.238359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:29.238359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.15535","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":"2026-07-05T07:23:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2LcJMaObGMop+Fgo+B4TaqlFYX5n45yrd5SAG8b4HvO6FXkJDKJSHzBbMQBXZEN74RQFBx47kSxVvULj4FQRDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:09:00.829934Z"},"content_sha256":"12605694f683d8f387cc03684cdae4a0594d6893c6876b282c2bc3b605434f38","schema_version":"1.0","event_id":"sha256:12605694f683d8f387cc03684cdae4a0594d6893c6876b282c2bc3b605434f38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:I37ACXRGO764OC2Y45QXUXVUCT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From LAION-5B to LAION-EO: Filtering Billions of Images Using Anchor Datasets for Satellite Image Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alistair Francis, Mikolaj Czerkawski","submitted_at":"2023-09-27T09:53:38Z","abstract_excerpt":"Large datasets, such as LAION-5B, contain a diverse distribution of images shared online. However, extraction of domain-specific subsets of large image corpora is challenging. The extraction approach based on an anchor dataset, combined with further filtering, is proposed here and demonstrated for the domain of satellite imagery. This results in the release of LAION-EO, a dataset sourced from the web containing pairs of text and satellite images in high (pixel-wise) resolution. The paper outlines the acquisition procedure as well as some of the features of the dataset."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15535","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/2309.15535/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":"2026-07-05T07:23:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BuCO1gy0sOk9DC6t2QGPe252UvXKP1EyaGHt2tFOrNZ6EYYlGKkatiMUJTh+Frt6QdGMageRCvtMLdpFY8SvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:09:00.830528Z"},"content_sha256":"13985940061f39dd2a9ab149a7c189c8941c0d65f6f65a84cc59b463d4bd0d30","schema_version":"1.0","event_id":"sha256:13985940061f39dd2a9ab149a7c189c8941c0d65f6f65a84cc59b463d4bd0d30"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I37ACXRGO764OC2Y45QXUXVUCT/bundle.json","state_url":"https://pith.science/pith/I37ACXRGO764OC2Y45QXUXVUCT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I37ACXRGO764OC2Y45QXUXVUCT/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":"2026-08-09T05:09:00Z","links":{"resolver":"https://pith.science/pith/I37ACXRGO764OC2Y45QXUXVUCT","bundle":"https://pith.science/pith/I37ACXRGO764OC2Y45QXUXVUCT/bundle.json","state":"https://pith.science/pith/I37ACXRGO764OC2Y45QXUXVUCT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I37ACXRGO764OC2Y45QXUXVUCT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:I37ACXRGO764OC2Y45QXUXVUCT","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":"49ddb3e8b3e47e24f125ae5d15d7a5587df59d79efce632245d0416de8bc1711","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-27T09:53:38Z","title_canon_sha256":"1bf610a71be7b9cb0ded6b44b3f3f15d844c79de8db579772d7bd215a72641eb"},"schema_version":"1.0","source":{"id":"2309.15535","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15535","created_at":"2026-07-05T07:23:29Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15535v1","created_at":"2026-07-05T07:23:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15535","created_at":"2026-07-05T07:23:29Z"},{"alias_kind":"pith_short_12","alias_value":"I37ACXRGO764","created_at":"2026-07-05T07:23:29Z"},{"alias_kind":"pith_short_16","alias_value":"I37ACXRGO764OC2Y","created_at":"2026-07-05T07:23:29Z"},{"alias_kind":"pith_short_8","alias_value":"I37ACXRG","created_at":"2026-07-05T07:23:29Z"}],"graph_snapshots":[{"event_id":"sha256:13985940061f39dd2a9ab149a7c189c8941c0d65f6f65a84cc59b463d4bd0d30","target":"graph","created_at":"2026-07-05T07:23:29Z","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/2309.15535/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large datasets, such as LAION-5B, contain a diverse distribution of images shared online. However, extraction of domain-specific subsets of large image corpora is challenging. The extraction approach based on an anchor dataset, combined with further filtering, is proposed here and demonstrated for the domain of satellite imagery. This results in the release of LAION-EO, a dataset sourced from the web containing pairs of text and satellite images in high (pixel-wise) resolution. The paper outlines the acquisition procedure as well as some of the features of the dataset.","authors_text":"Alistair Francis, Mikolaj Czerkawski","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-27T09:53:38Z","title":"From LAION-5B to LAION-EO: Filtering Billions of Images Using Anchor Datasets for Satellite Image Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15535","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":"sha256:12605694f683d8f387cc03684cdae4a0594d6893c6876b282c2bc3b605434f38","target":"record","created_at":"2026-07-05T07:23:29Z","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":"49ddb3e8b3e47e24f125ae5d15d7a5587df59d79efce632245d0416de8bc1711","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-27T09:53:38Z","title_canon_sha256":"1bf610a71be7b9cb0ded6b44b3f3f15d844c79de8db579772d7bd215a72641eb"},"schema_version":"1.0","source":{"id":"2309.15535","kind":"arxiv","version":1}},"canonical_sha256":"46fe015e2677fdc70b58e7617a5eb414d208f0f5048c2e73522ed80702ea7f96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46fe015e2677fdc70b58e7617a5eb414d208f0f5048c2e73522ed80702ea7f96","first_computed_at":"2026-07-05T07:23:29.238359Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:23:29.238359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AceYXHTUPmIqoUCjQslk9qTRTJ51quR3LVcF/45YXSXY6E8yLXhGWsgyyDLLvnkMGFwUYZJvd7jUGU/xZOaXAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:23:29.238823Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.15535","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12605694f683d8f387cc03684cdae4a0594d6893c6876b282c2bc3b605434f38","sha256:13985940061f39dd2a9ab149a7c189c8941c0d65f6f65a84cc59b463d4bd0d30"],"state_sha256":"d0eeca9412289cebe9c6d03e6cf9fc9460024c15628ee5a1b25fae5c33ade2d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ykO1LxGJn9vbdzNfPoXuNvueG6c++vbcj+agNswpbo0LjMLXL/SG4AqkKYhIMfI9Hj7IuH3O+JDMYjwysZFPCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:09:00.834673Z","bundle_sha256":"94deeb7cb1e3864bbadd5c291acabed37a50bfb888e1561569020bdac20ffd94"}}