{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EBOUXKN5TD63C6NKQLMKRDHNV5","short_pith_number":"pith:EBOUXKN5","schema_version":"1.0","canonical_sha256":"205d4ba9bd98fdb179aa82d8a88cedaf6081a13c611b5539fe1c2f81bcba6a10","source":{"kind":"arxiv","id":"2605.20539","version":1},"attestation_state":"computed","paper":{"title":"OpenSeisML: Open Large-Scale Real Seismic and well-log Dataset for Generative AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Charles Jones, Felix J. Herrmann, Huseyin Tuna Erdinc, Ipsita Bhar, Thales Souza","submitted_at":"2026-05-19T22:22:46Z","abstract_excerpt":"The advent of machine learning (ML) and computer vision has significantly accelerated seismic inversion workflows by reducing the computational cost of traditionally expensive iterative methods. However, the development and evaluation of ML methods remain limited by the scarcity of realistic velocity models, as most high-quality data are privately owned by oil and gas companies. To address this gap, we present OpenSeisML, a collection of real seismic datasets designed to support generative AI (Gen-AI) workflows for seismic inversion. The datasets are curated from publicly available surveys in "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.20539","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T22:22:46Z","cross_cats_sorted":[],"title_canon_sha256":"fa71aba7d94bc2ac0951cf8d95083910899afd7e494454ee3e158ef8fd6890d1","abstract_canon_sha256":"69b604a273739cbd15ff51e627f363ec4c7faa04b1897f24d99efed72df77770"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:41.668689Z","signature_b64":"n5wK/7+Jy1OrOwgqxsqL3bWvuxTnffm+xc2ZemY9YOkX0DWBImS3FVWSqFSKRjGbzUpJCnWP8j22c6Yne4PqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"205d4ba9bd98fdb179aa82d8a88cedaf6081a13c611b5539fe1c2f81bcba6a10","last_reissued_at":"2026-05-21T01:04:41.667958Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:41.667958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenSeisML: Open Large-Scale Real Seismic and well-log Dataset for Generative AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Charles Jones, Felix J. Herrmann, Huseyin Tuna Erdinc, Ipsita Bhar, Thales Souza","submitted_at":"2026-05-19T22:22:46Z","abstract_excerpt":"The advent of machine learning (ML) and computer vision has significantly accelerated seismic inversion workflows by reducing the computational cost of traditionally expensive iterative methods. However, the development and evaluation of ML methods remain limited by the scarcity of realistic velocity models, as most high-quality data are privately owned by oil and gas companies. To address this gap, we present OpenSeisML, a collection of real seismic datasets designed to support generative AI (Gen-AI) workflows for seismic inversion. The datasets are curated from publicly available surveys in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20539","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/2605.20539/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.20539","created_at":"2026-05-21T01:04:41.668070+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20539v1","created_at":"2026-05-21T01:04:41.668070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20539","created_at":"2026-05-21T01:04:41.668070+00:00"},{"alias_kind":"pith_short_12","alias_value":"EBOUXKN5TD63","created_at":"2026-05-21T01:04:41.668070+00:00"},{"alias_kind":"pith_short_16","alias_value":"EBOUXKN5TD63C6NK","created_at":"2026-05-21T01:04:41.668070+00:00"},{"alias_kind":"pith_short_8","alias_value":"EBOUXKN5","created_at":"2026-05-21T01:04:41.668070+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EBOUXKN5TD63C6NKQLMKRDHNV5","json":"https://pith.science/pith/EBOUXKN5TD63C6NKQLMKRDHNV5.json","graph_json":"https://pith.science/api/pith-number/EBOUXKN5TD63C6NKQLMKRDHNV5/graph.json","events_json":"https://pith.science/api/pith-number/EBOUXKN5TD63C6NKQLMKRDHNV5/events.json","paper":"https://pith.science/paper/EBOUXKN5"},"agent_actions":{"view_html":"https://pith.science/pith/EBOUXKN5TD63C6NKQLMKRDHNV5","download_json":"https://pith.science/pith/EBOUXKN5TD63C6NKQLMKRDHNV5.json","view_paper":"https://pith.science/paper/EBOUXKN5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20539&json=true","fetch_graph":"https://pith.science/api/pith-number/EBOUXKN5TD63C6NKQLMKRDHNV5/graph.json","fetch_events":"https://pith.science/api/pith-number/EBOUXKN5TD63C6NKQLMKRDHNV5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EBOUXKN5TD63C6NKQLMKRDHNV5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EBOUXKN5TD63C6NKQLMKRDHNV5/action/storage_attestation","attest_author":"https://pith.science/pith/EBOUXKN5TD63C6NKQLMKRDHNV5/action/author_attestation","sign_citation":"https://pith.science/pith/EBOUXKN5TD63C6NKQLMKRDHNV5/action/citation_signature","submit_replication":"https://pith.science/pith/EBOUXKN5TD63C6NKQLMKRDHNV5/action/replication_record"}},"created_at":"2026-05-21T01:04:41.668070+00:00","updated_at":"2026-05-21T01:04:41.668070+00:00"}