{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:44BBWI6PAN3CXUSR5TSMJ6IWOT","short_pith_number":"pith:44BBWI6P","schema_version":"1.0","canonical_sha256":"e7021b23cf03762bd251ece4c4f91674ecb36a3f0937210b7086ae0be1f3b2e8","source":{"kind":"arxiv","id":"2605.16783","version":1},"attestation_state":"computed","paper":{"title":"Pretrain-to-alignment learning paradigm to improve geophysical AI applicability under scarce field labels and synthetic-to-field gaps: A case study of relative geologic time estimation in global shelf-edge clinothems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A pretrain-to-alignment paradigm enables accurate geophysical AI despite scarce labels and synthetic-to-field gaps.","cross_cats":[],"primary_cat":"physics.geo-ph","authors_text":"Hui Gao, Jiarun Yang, Xinming Wu, Yimin Dou, Zhixiang Gao","submitted_at":"2026-05-16T03:34:51Z","abstract_excerpt":"Artificial intelligence (AI) has been increasingly applied to various geophysical scenarios, yet its practical deployment remains limited by scarce field labels, pronounced synthetic-to-field domain gaps, and insufficient physical consistency under complex and variable field conditions. To address these challenges, we propose a pretrain-to-alignment learning paradigm that systematically integrates self-supervised pretraining, synthetic supervision, prior-driven refinement, and domain-adaptation fine-tuning into a unified progressive learning workflow. In this paradigm, geophysical AI models ar"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.16783","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.geo-ph","submitted_at":"2026-05-16T03:34:51Z","cross_cats_sorted":[],"title_canon_sha256":"b972b04b531983c372809e9e5ed44374986d990b402ba431b664e12f7004f841","abstract_canon_sha256":"c21f2971de6006b133bf6ab7a3246b10a39ef3180a08e87aa8d02f9165461a81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:21.776236Z","signature_b64":"ZgSnpe5myAwW1H66vIe0bAxbRSLRF5tELvXmvauKwhh38oPNjiLRj1tzZVeEjvYsa43jNXRGeOyV6NkGDo+cBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7021b23cf03762bd251ece4c4f91674ecb36a3f0937210b7086ae0be1f3b2e8","last_reissued_at":"2026-05-20T00:03:21.775305Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:21.775305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pretrain-to-alignment learning paradigm to improve geophysical AI applicability under scarce field labels and synthetic-to-field gaps: A case study of relative geologic time estimation in global shelf-edge clinothems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A pretrain-to-alignment paradigm enables accurate geophysical AI despite scarce labels and synthetic-to-field gaps.","cross_cats":[],"primary_cat":"physics.geo-ph","authors_text":"Hui Gao, Jiarun Yang, Xinming Wu, Yimin Dou, Zhixiang Gao","submitted_at":"2026-05-16T03:34:51Z","abstract_excerpt":"Artificial intelligence (AI) has been increasingly applied to various geophysical scenarios, yet its practical deployment remains limited by scarce field labels, pronounced synthetic-to-field domain gaps, and insufficient physical consistency under complex and variable field conditions. To address these challenges, we propose a pretrain-to-alignment learning paradigm that systematically integrates self-supervised pretraining, synthetic supervision, prior-driven refinement, and domain-adaptation fine-tuning into a unified progressive learning workflow. In this paradigm, geophysical AI models ar"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Results from 3,000 field datasets spanning multiple sedimentary basins demonstrate that the proposed paradigm achieves accurate, robust, and well-generalized performance across diverse field surveys, while significantly improving fine-scale stratigraphic and structural details.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That sequential integration of self-supervised pretraining, synthetic supervision, prior-driven refinement, and domain-adaptation fine-tuning will progressively build field-relevant representations and task-specific mapping without introducing inconsistencies or overfitting to the synthetic domain.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Introduces a staged pretrain-to-alignment workflow for geophysical AI that improves relative geologic time estimation across global field surveys despite limited labels and domain gaps.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A pretrain-to-alignment paradigm enables accurate geophysical AI despite scarce labels and synthetic-to-field gaps.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4311ff57bfc3a1109e2bd1da34735f26b002571eecf809e7493503b49aacdd3b"},"source":{"id":"2605.16783","kind":"arxiv","version":1},"verdict":{"id":"ddfb657d-4ffb-464d-97c9-6eb4dcbcacb3","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T19:30:36.028819Z","strongest_claim":"Results from 3,000 field datasets spanning multiple sedimentary basins demonstrate that the proposed paradigm achieves accurate, robust, and well-generalized performance across diverse field surveys, while significantly improving fine-scale stratigraphic and structural details.","one_line_summary":"Introduces a staged pretrain-to-alignment workflow for geophysical AI that improves relative geologic time estimation across global field surveys despite limited labels and domain gaps.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That sequential integration of self-supervised pretraining, synthetic supervision, prior-driven refinement, and domain-adaptation fine-tuning will progressively build field-relevant representations and task-specific mapping without introducing inconsistencies or overfitting to the synthetic domain.","pith_extraction_headline":"A pretrain-to-alignment paradigm enables accurate geophysical AI despite scarce labels and synthetic-to-field gaps."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16783/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T20:01:19.079814Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T19:40:54.361088Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.300620Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.436405Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"723b8199f852a080f6f50cd6cd10986351a66883d59263f6caa6ecfe9551182e"},"references":{"count":147,"sample":[{"doi":"","year":2021,"title":"Deep learning for seismic inverse problems: Toward the acceleration of geophysical analysis workflows","work_id":"1a714ea6-c469-4114-a6c5-c1d74567fb88","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2013,"title":"Basin analysis: Principles and application to petroleum play assessment","work_id":"9d713939-2478-4c75-8a33-1c3b8d49e86d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Current state and future directions for deep learning based automatic seismic fault interpretation: A systematic review","work_id":"9aa3b091-95bd-467b-bb1c-d45c46d25a3d","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"The quantifiable clinothem--types, shapes and geometric relationships in the plio-pleistocene giant foresets formation, taranaki basin, new zealand","work_id":"c4788ae1-634c-4c3a-ae28-e8297c19fbda","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Machine learning in microseismic monitoring","work_id":"131b8748-9667-45b0-8218-fce5ed277967","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":147,"snapshot_sha256":"289a5f440a6addda3cc063f63b74517d4cd86912389f92574a7d342b9e279487","internal_anchors":2},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5d467a26cf7a46c132eaca3c77a93c36ec73fb4cf214be1d0974c31e941c151f"},"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":"2605.16783","created_at":"2026-05-20T00:03:21.775501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16783v1","created_at":"2026-05-20T00:03:21.775501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16783","created_at":"2026-05-20T00:03:21.775501+00:00"},{"alias_kind":"pith_short_12","alias_value":"44BBWI6PAN3C","created_at":"2026-05-20T00:03:21.775501+00:00"},{"alias_kind":"pith_short_16","alias_value":"44BBWI6PAN3CXUSR","created_at":"2026-05-20T00:03:21.775501+00:00"},{"alias_kind":"pith_short_8","alias_value":"44BBWI6P","created_at":"2026-05-20T00:03:21.775501+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/44BBWI6PAN3CXUSR5TSMJ6IWOT","json":"https://pith.science/pith/44BBWI6PAN3CXUSR5TSMJ6IWOT.json","graph_json":"https://pith.science/api/pith-number/44BBWI6PAN3CXUSR5TSMJ6IWOT/graph.json","events_json":"https://pith.science/api/pith-number/44BBWI6PAN3CXUSR5TSMJ6IWOT/events.json","paper":"https://pith.science/paper/44BBWI6P"},"agent_actions":{"view_html":"https://pith.science/pith/44BBWI6PAN3CXUSR5TSMJ6IWOT","download_json":"https://pith.science/pith/44BBWI6PAN3CXUSR5TSMJ6IWOT.json","view_paper":"https://pith.science/paper/44BBWI6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16783&json=true","fetch_graph":"https://pith.science/api/pith-number/44BBWI6PAN3CXUSR5TSMJ6IWOT/graph.json","fetch_events":"https://pith.science/api/pith-number/44BBWI6PAN3CXUSR5TSMJ6IWOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/44BBWI6PAN3CXUSR5TSMJ6IWOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/44BBWI6PAN3CXUSR5TSMJ6IWOT/action/storage_attestation","attest_author":"https://pith.science/pith/44BBWI6PAN3CXUSR5TSMJ6IWOT/action/author_attestation","sign_citation":"https://pith.science/pith/44BBWI6PAN3CXUSR5TSMJ6IWOT/action/citation_signature","submit_replication":"https://pith.science/pith/44BBWI6PAN3CXUSR5TSMJ6IWOT/action/replication_record"}},"created_at":"2026-05-20T00:03:21.775501+00:00","updated_at":"2026-05-20T00:03:21.775501+00:00"}