{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:K2SAHSXCJCBLKBINDXSIVAFJ6M","short_pith_number":"pith:K2SAHSXC","schema_version":"1.0","canonical_sha256":"56a403cae24882b5050d1de48a80a9f333d9074b38cf8344eed68c606d2ab601","source":{"kind":"arxiv","id":"2607.14486","version":1},"attestation_state":"computed","paper":{"title":"Full-data accuracy with fewer labels for training and fine-tuning machine-learning force fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"Jun Cheng, Sheng Bi, Yi-Ze Wang","submitted_at":"2026-07-16T01:59:47Z","abstract_excerpt":"Machine-learning force fields (MLFFs) are reliable only near their training distribution, making efficient construction of diverse training sets a major bottleneck for both train-from-scratch and foundation fine-tuning workflows. Active learning can reduce this cost, but standard model-committee uncertainty is impractical for foundation MLFFs because each committee member requires a separate fine-tuning run. We present an active-learning workflow based on last-layer-projection regression (LLPR), a forward-pass-cheap per-configuration uncertainty estimator. Across molecular, condensed-phase, an"},"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":"2607.14486","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2026-07-16T01:59:47Z","cross_cats_sorted":["cond-mat.mtrl-sci","cs.LG"],"title_canon_sha256":"453e02b6a741566aaa890f18ec834704a004a96e8e41183c5ca5411346b0012a","abstract_canon_sha256":"d0acb832f32faaf07e7fa4b0a5b1446da28c62c1928e71a8b8c2216af17880f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:21:14.977683Z","signature_b64":"j7G7N0qEy9H56RWvgOIC9u6e4PwOr8dF5bn1sJJFHkIKnxmvxw3ZeMT+D8z1S7+QAcL5+JeHFwlb5b+OfdezBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56a403cae24882b5050d1de48a80a9f333d9074b38cf8344eed68c606d2ab601","last_reissued_at":"2026-07-17T00:21:14.976833Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:21:14.976833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Full-data accuracy with fewer labels for training and fine-tuning machine-learning force fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"Jun Cheng, Sheng Bi, Yi-Ze Wang","submitted_at":"2026-07-16T01:59:47Z","abstract_excerpt":"Machine-learning force fields (MLFFs) are reliable only near their training distribution, making efficient construction of diverse training sets a major bottleneck for both train-from-scratch and foundation fine-tuning workflows. Active learning can reduce this cost, but standard model-committee uncertainty is impractical for foundation MLFFs because each committee member requires a separate fine-tuning run. We present an active-learning workflow based on last-layer-projection regression (LLPR), a forward-pass-cheap per-configuration uncertainty estimator. Across molecular, condensed-phase, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14486","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/2607.14486/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":"2607.14486","created_at":"2026-07-17T00:21:14.977264+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14486v1","created_at":"2026-07-17T00:21:14.977264+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14486","created_at":"2026-07-17T00:21:14.977264+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2SAHSXCJCBL","created_at":"2026-07-17T00:21:14.977264+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2SAHSXCJCBLKBIN","created_at":"2026-07-17T00:21:14.977264+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2SAHSXC","created_at":"2026-07-17T00:21:14.977264+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/K2SAHSXCJCBLKBINDXSIVAFJ6M","json":"https://pith.science/pith/K2SAHSXCJCBLKBINDXSIVAFJ6M.json","graph_json":"https://pith.science/api/pith-number/K2SAHSXCJCBLKBINDXSIVAFJ6M/graph.json","events_json":"https://pith.science/api/pith-number/K2SAHSXCJCBLKBINDXSIVAFJ6M/events.json","paper":"https://pith.science/paper/K2SAHSXC"},"agent_actions":{"view_html":"https://pith.science/pith/K2SAHSXCJCBLKBINDXSIVAFJ6M","download_json":"https://pith.science/pith/K2SAHSXCJCBLKBINDXSIVAFJ6M.json","view_paper":"https://pith.science/paper/K2SAHSXC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14486&json=true","fetch_graph":"https://pith.science/api/pith-number/K2SAHSXCJCBLKBINDXSIVAFJ6M/graph.json","fetch_events":"https://pith.science/api/pith-number/K2SAHSXCJCBLKBINDXSIVAFJ6M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2SAHSXCJCBLKBINDXSIVAFJ6M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2SAHSXCJCBLKBINDXSIVAFJ6M/action/storage_attestation","attest_author":"https://pith.science/pith/K2SAHSXCJCBLKBINDXSIVAFJ6M/action/author_attestation","sign_citation":"https://pith.science/pith/K2SAHSXCJCBLKBINDXSIVAFJ6M/action/citation_signature","submit_replication":"https://pith.science/pith/K2SAHSXCJCBLKBINDXSIVAFJ6M/action/replication_record"}},"created_at":"2026-07-17T00:21:14.977264+00:00","updated_at":"2026-07-17T00:21:14.977264+00:00"}