{"as_of":"2026-08-16T15:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:62cc4114c6b0e049ea1e561b92eb8cb831dfb7a9a34a408fae9d8b12e42063ea","coverage":[{"denominator":93,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":93,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T16:13:40.576352Z","state":"measured"},{"denominator":93,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":93,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.18092/citation-record","integrity":"/paper/2607.18092/integrity","json":"/paper/2607.18092/citation-record.json","paper":"/paper/2607.18092"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:29.553691Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:29.553691Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:b3ae1421b2a761dc7480bb9bb414bb1cdf9ada508a877f8af002393f0c604fea","observation_id":"fdd787a5-c03d-48f1-9b50-f4cb033d7a90","resolution":{"observed_at":"2026-08-01T16:13:29.553691Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:29.618322Z","title":"Uhrin, S","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:29.618322Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:d7da3429253d53a9a253a93f4045b06d74b96ae2714ce79fe1d29cdfbb8d6f4e","observation_id":"17eef625-3e38-48cf-95bb-ae97dc17dcac","resolution":{"observed_at":"2026-08-01T16:13:29.618322Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:29.716844Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:29.716844Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:d744d5acbc74e0d32ec4d5331d4735b9b20ab428374e587a4b96ccd6a876116a","observation_id":"e77a2f09-4473-4fac-95cf-9d24caeef7cf","resolution":{"observed_at":"2026-08-01T16:13:29.716844Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:29.825695Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:29.825695Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:27db4bd23fba92f5d4bc234ea20109553643f712dd32bc7add1e691c5670c7a0","observation_id":"750fbc25-755d-424f-855e-643079709f06","resolution":{"observed_at":"2026-08-01T16:13:29.825695Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:29.942863Z","title":"Mathew, J","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:29.942863Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:201d6d42a4cda2e481a15d73273d22b6bc2c18dbf44b7023f48357bb52343193","observation_id":"7e6e584b-6ae4-4889-896c-55c69954f5c7","resolution":{"observed_at":"2026-08-01T16:13:29.942863Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:30.054132Z","title":"Ganose, J","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:30.054132Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:69d315975d46bdb1685385d8b4c5a2277aa014e91d4248251a761559a43439a7","observation_id":"d032d7ff-b3f4-4e90-8485-46134893e3a1","resolution":{"observed_at":"2026-08-01T16:13:30.054132Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:30.179570Z","title":null,"venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:30.179570Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:b980e779cc852aa88aeafed21909db030ef956ae5f7543e484f022c642e24fa1","observation_id":"00d668e4-c81b-4ce0-9e4c-6d69d7f89335","resolution":{"observed_at":"2026-08-01T16:13:30.179570Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:30.319562Z","title":null,"venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:30.319562Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:45d9816194bbb3aa2ee3b765b99cf3a4b109a5d008663ef788ba907a599f4d4c","observation_id":"ec555bac-7d5d-40fe-99e9-4049a449e3b6","resolution":{"observed_at":"2026-08-01T16:13:30.319562Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:30.416658Z","title":null,"venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:30.416658Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:4b7fd851ee3b92180acbc0db4106091f38a27ed3ae7ff5643d579bbf6d67480c","observation_id":"8fb9184a-235f-4537-be1a-d82d5b237292","resolution":{"observed_at":"2026-08-01T16:13:30.416658Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:30.491798Z","title":"Kirklin, J","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:30.491798Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:9181261b3ecc57a6779146a9b1512181b41dfc92cac2f2d96a4e0fb3c6225d31","observation_id":"4ffb76bb-dd32-4ff7-993d-1ec336dcd329","resolution":{"observed_at":"2026-08-01T16:13:30.491798Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:30.613750Z","title":"Curtarolo, W","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:30.613750Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:a29944e783ec0b4279eb37e1cf97d8817f735bb99a33918910262e49989ea0db","observation_id":"73bbf003-bac7-412e-b4b6-796e92b1bcef","resolution":{"observed_at":"2026-08-01T16:13:30.613750Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:30.686356Z","title":"Curtarolo, W","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:30.686356Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:e0bcbf1d1e77a905ad565e01d6a665cbd7a1ac3dca0041a657351bc7e7273b5b","observation_id":"f15c9ac5-195c-4951-b4e0-1f81ab931dfb","resolution":{"observed_at":"2026-08-01T16:13:30.686356Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:30.802683Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:30.802683Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:13c38288a29765f320983f9ab82dad48cbc1b7896e9077616cf5b146e6c1a893","observation_id":"3db5f286-8f05-417b-b2de-db8a5800504f","resolution":{"observed_at":"2026-08-01T16:13:30.802683Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:30.875041Z","title":"Schmidt, N","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:30.875041Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:db6ebc4d502d609286db34b80c5f59bea28bfc472c99b0d5f21f65ccdfb2e25c","observation_id":"eb7eef38-acba-4a71-ab65-07da56c5df49","resolution":{"observed_at":"2026-08-01T16:13:30.875041Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:31.056788Z","title":"Schmidt, H.-C","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:31.056788Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:7e850f68d8608417c6333c24193ae2536f619d94012aa1a98d6f57098c4afa30","observation_id":"4315c9a2-438c-4392-a335-dbb28feef8b9","resolution":{"observed_at":"2026-08-01T16:13:31.056788Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:31.155743Z","title":"Schmidt, T","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:31.155743Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:550ceab85b15ea1f7f06fd77092dc6130045caeb494a80f5fa99688715dea745","observation_id":"14695022-ec23-49e0-85a2-1a5f4ed37f41","resolution":{"observed_at":"2026-08-01T16:13:31.155743Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:31.309652Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:31.309652Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:01a35ae0b032824f56a390d313cdcbd6ed92c446b55cd2725bc3c4a8ec185a4a","observation_id":"12917186-576b-43c5-942a-3d872c59cd0a","resolution":{"observed_at":"2026-08-01T16:13:31.309652Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:31.446834Z","title":"Talirz, S","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:31.446834Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:4c67c843da3e3096e8b9c9fe4a3ea3a86ee6f1acbb7230ddbecff4593a8d5970","observation_id":"680d1129-576a-40f6-b374-eb9baf7b3535","resolution":{"observed_at":"2026-08-01T16:13:31.446834Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:31.564728Z","title":"Hohenberg and W","venue":null,"work_id":null,"year":1964},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:31.564728Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:fb427f35ab4f5b1eb48df626fdcf23f8b455e4ec2930044cc7ea09c7053f1d09","observation_id":"d7109ac6-8029-4b43-8dba-ec7d14c204a0","resolution":{"observed_at":"2026-08-01T16:13:31.564728Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:31.691122Z","title":"Kohn and L","venue":null,"work_id":null,"year":1965},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:31.691122Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:eadd42449105b2e62336f1bf88e46e2d48966a2d3e907cd231e2674cf86d9d8b","observation_id":"1265acea-d494-4cca-8eb7-18fda1cfb335","resolution":{"observed_at":"2026-08-01T16:13:31.691122Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2512.09169","last_updated":"2026-05-01T14:32:43Z","snapshot_observed_at":"2026-07-06T22:38:35.387503Z","submitted_at":"2025-12-09T22:31:17Z","title":"AI-Driven Expansion and Application of the Alexandria Database","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2512.09169","snapshot_observed_at":"2026-08-01T16:13:31.831740Z","title":"Cavignac, J","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:31.831740Z"},"links":{"cited_paper":"/paper/2512.09169","citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:33cec343f310c8865b96cc713c7520d9c2878c133a554a319c5647c39d2e055e","observation_id":"82e33854-eae6-44d4-a304-1c5688c66691","resolution":{"observed_at":"2026-08-01T16:13:31.831740Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:31.892146Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:31.892146Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:ba3ef86df453fdbf5dcfb80aa319ae9384cb8dfdc6ca6bedb5bbfd5df11db155","observation_id":"c84f5078-be45-4694-bf86-21ccebebf2f7","resolution":{"observed_at":"2026-08-01T16:13:31.892146Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:31.954797Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:31.954797Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:8f45bf0074eb75242c6b22de0cad3bb4686c374077cba602017a9e50777c7da6","observation_id":"8a557db5-64f6-43bb-b722-2a82c6026889","resolution":{"observed_at":"2026-08-01T16:13:31.954797Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:32.066633Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:32.066633Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:7b5158f4b5bf1f59991f38af3d92282e61183efec5e5126f296328394b3dfa5d","observation_id":"ffac871d-199c-4883-936d-289886a3b108","resolution":{"observed_at":"2026-08-01T16:13:32.066633Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:32.155657Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:32.155657Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:4f5d7adf4daa6029988ba40e6d4313e3782c66c46e6dac78eaf73cecd36fc508","observation_id":"b3f92742-6cb5-46b5-ab9d-c2ffe375a58e","resolution":{"observed_at":"2026-08-01T16:13:32.155657Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:32.309831Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:32.309831Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:69e2d8479f69667637083a27352ccb54f0b66cb4b76a48cf1dd3ecaca781b76f","observation_id":"d0f94bec-bd27-4c9a-af7e-c58e5f063330","resolution":{"observed_at":"2026-08-01T16:13:32.309831Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:32.467813Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:32.467813Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:d7aad7d7a794de800b0eaacc3c26b21c12a28240d01c6abe3e09253fa6608ccd","observation_id":"d2b69dc3-f56a-43c0-b0c1-2f4434f5c118","resolution":{"observed_at":"2026-08-01T16:13:32.467813Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:32.507003Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:32.507003Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:82dfc025b39f2cb1308d5425adbc445c09cbe52981607ec526ee684d6a34a23f","observation_id":"ca1be785-2ba1-49df-a92a-1afc43888a26","resolution":{"observed_at":"2026-08-01T16:13:32.507003Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:32.600794Z","title":"Zhang, D","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:32.600794Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:6ff8cdce97db45d3447ad29268006b4493234427c0fa0cbc9677eedc50f049a7","observation_id":"f558cf51-60fd-4bde-bea7-4e1f39feb1a3","resolution":{"observed_at":"2026-08-01T16:13:32.600794Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:32.752369Z","title":"Kingsbury, A","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:32.752369Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:fc116732cc2d7dd4dca21cb2eb4dbab3ad5149296d30595875a28a503bcfeb38","observation_id":"06929a2b-59bf-4b6a-96a2-4e3dd6c8f5d5","resolution":{"observed_at":"2026-08-01T16:13:32.752369Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:32.873269Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:32.873269Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:33f9a7fde7485c4e0998d16e00aa3a4d236c9d104bf7eaa75ebf81539d188d0a","observation_id":"4b0dead3-74b2-4407-a866-1afd3ecdf98a","resolution":{"observed_at":"2026-08-01T16:13:32.873269Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:33.008198Z","title":null,"venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:33.008198Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:a146bdd620470d220a01a09750903acec0b397b7e9f4b82c3dfc352cc56d0b11","observation_id":"aa32d78d-85d3-4095-8bac-c27ab6dd5765","resolution":{"observed_at":"2026-08-01T16:13:33.008198Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:33.135162Z","title":null,"venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:33.135162Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:23d5e108475b5067434ea935be56619c4c6fb6963fd28ca5b835441702cb7fcb","observation_id":"a1256304-cb91-4f14-bc0a-ff93c9e00662","resolution":{"observed_at":"2026-08-01T16:13:33.135162Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:33.236854Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:33.236854Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:30e42ed71d3cd597e6f7c3f2711e5cd01d0d7abdd9c408c683bc4a2a25c932f2","observation_id":"12dd433c-c872-4dbb-933a-dbf60eee3bb4","resolution":{"observed_at":"2026-08-01T16:13:33.236854Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:33.342225Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:33.342225Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:c1076fe6c3f737343568c57335094908a647e3726b7da590969d295908ac0214","observation_id":"ef67e0d0-7d9f-4410-9e4a-2cc68fccfddb","resolution":{"observed_at":"2026-08-01T16:13:33.342225Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:33.474076Z","title":"Malosso, F","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:33.474076Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:85d3ed1546232a45ada91d50c98efd85b71343ede881c7ad301ce986bf143d2b","observation_id":"a6501911-3297-4e39-b04e-093100585219","resolution":{"observed_at":"2026-08-01T16:13:33.474076Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:33.580307Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:33.580307Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:e20427df9953b0487b67975a13f59c7a13b7bdb4acab9d167eb182f1528448d4","observation_id":"61ff3d1d-7f8b-4fe7-873a-e10adf03981d","resolution":{"observed_at":"2026-08-01T16:13:33.580307Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:33.717226Z","title":"Bosoni, L","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:33.717226Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:c86ce0a1047158b84f24bd17de71425328f50c216b590061a9eb1d322d097f7b","observation_id":"144f388a-877e-433d-a96d-0650208c9c36","resolution":{"observed_at":"2026-08-01T16:13:33.717226Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:33.886524Z","title":"Prandini, A","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:33.886524Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:9b50eaa32a3e0c980528a16313e85719abf866cde7472d6591215f59522508c0","observation_id":"c15a4dae-9607-4d8a-ac25-0f85bbd9de25","resolution":{"observed_at":"2026-08-01T16:13:33.886524Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:34.037407Z","title":"Grindy, B","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:34.037407Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:6cb779dacfb7fba7b0d7940551632f7afb6060d0917bc139fb1c550803f80dca","observation_id":"5d2b8f4a-a3e1-49f1-bb79-c13d4ac025fb","resolution":{"observed_at":"2026-08-01T16:13:34.037407Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:34.190040Z","title":null,"venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:34.190040Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:ff2849fb5ebe63a593643fd437d70fda5ace0868b75976d7d42655278831a575","observation_id":"86d3520d-7119-4e54-a55a-fbf70fa82201","resolution":{"observed_at":"2026-08-01T16:13:34.190040Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:34.397136Z","title":"Stevanovi´ c, S","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:34.397136Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:d6b5b71c4b74f8e001a7de333854f57fa3e969c5b4d932e8593d202921a318f7","observation_id":"d11c346e-2ab6-460d-b186-e2287f6c0015","resolution":{"observed_at":"2026-08-01T16:13:34.397136Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:34.558818Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:34.558818Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:25fc31c62348d6c85878a37f669aec813a9412a3bc9e37e71f66f4a3bebeebb9","observation_id":"1237ef74-636e-4f13-b17c-67dcae8e7d81","resolution":{"observed_at":"2026-08-01T16:13:34.558818Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:34.732473Z","title":"Friedrich, D","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:34.732473Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:c41856f8dee188de159a3e29e8278285961ea6925a8f559755080d121180db28","observation_id":"7a331fb7-dba8-4711-98e0-b3fbe8eef183","resolution":{"observed_at":"2026-08-01T16:13:34.732473Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:34.848713Z","title":"Friedrich and S","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:34.848713Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:7a7c097edc7a4e21c17e2b6848be248af26083889294d9476488020d20af7add","observation_id":"1943188d-38fb-4b53-8d53-d2856a8376d1","resolution":{"observed_at":"2026-08-01T16:13:34.848713Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:34.973946Z","title":"Hautier, S","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:34.973946Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:040ea2fc6145e565d2fa22065e439f6b652249e41e45b9a33f57d5bbec36cbc4","observation_id":"fcbdcfb8-73d5-40db-b46c-f63fd33986e9","resolution":{"observed_at":"2026-08-01T16:13:34.973946Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:35.152592Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:35.152592Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:dfff26108dd91531ac5deed75b260dc4bdcfbf6f2bf877d1d626340d4cf55aec","observation_id":"80df137a-f750-4240-b49d-805a4af134b2","resolution":{"observed_at":"2026-08-01T16:13:35.152592Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:35.249922Z","title":null,"venue":null,"work_id":null,"year":1964},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:35.249922Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:9e359c86ea8a550e6d017a8aad238c29cfe61ccac9fcddabdaab714f2bf6c7ea","observation_id":"68cd1238-648e-4007-bcf6-636803c0a01f","resolution":{"observed_at":"2026-08-01T16:13:35.249922Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:35.371240Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:35.371240Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:43bfe485e4ca5801dcace10db20271badb3d2d05ac105633d87718d0f0ef4d71","observation_id":"81d4a79f-8fc7-4085-9101-65e938a1364a","resolution":{"observed_at":"2026-08-01T16:13:35.371240Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:35.555551Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:35.555551Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:cd8f64f5642f4d3c7bfc731e9cfa23e67522ef2d4fc840bac62e73a2af67d1b0","observation_id":"3b7dda2f-09b9-4c68-99e7-d5de10c7a928","resolution":{"observed_at":"2026-08-01T16:13:35.555551Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:35.682222Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:35.682222Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:53ff65952be0b4cae69153e0e9ab1fbc1ce49874622709893ef285ff9fd3f909","observation_id":"6cd7a6ab-a63b-40a7-9af0-1fc316342799","resolution":{"observed_at":"2026-08-01T16:13:35.682222Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:35.797055Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:35.797055Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:770f2bffce099b7372ebe15d87be37fa0607df1934b94ac3e5bbda9cb4ea1ed8","observation_id":"fae50c1c-4821-46a4-810b-b43b7121fa63","resolution":{"observed_at":"2026-08-01T16:13:35.797055Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.07609","last_updated":"2023-07-14T20:09:12Z","snapshot_observed_at":"2026-08-13T10:55:13.946851Z","submitted_at":"2023-07-14T20:09:12Z","title":"Interpretable machine learning to understand the performance of semi local density functionals for materials thermochemistry","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.07609","snapshot_observed_at":"2026-08-01T16:13:35.930981Z","title":"Adhikari, C","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:35.930981Z"},"links":{"cited_paper":"/paper/2307.07609","citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:0b5199e48bc0b02174772f998793ceb73143ad28574927b8d958dc7c1d8cdb3e","observation_id":"71262025-aa2c-4ab7-9f65-8f093731c8dd","resolution":{"observed_at":"2026-08-01T16:13:35.930981Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:36.058491Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:36.058491Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:f756f31a8fb389593797e4e59c16cec7f850a850784ac57f4024f3b085911c4f","observation_id":"9ebdf7f0-1b52-4e75-9449-a9dca681f02e","resolution":{"observed_at":"2026-08-01T16:13:36.058491Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:36.201360Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:36.201360Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:26a68a0b727a5d8b5c285a3a02ffd1534bd4b46f96d771d80823ea8fc15f29b9","observation_id":"595bf28f-e44c-4113-a62c-b57be0ec40e5","resolution":{"observed_at":"2026-08-01T16:13:36.201360Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:36.301063Z","title":"Priya and N","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:36.301063Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:27e91d2fdfaef4979d895b005caeb134a970c39fadd196aa964f77f0c3ce85e6","observation_id":"aaa0852b-1c89-4667-a76a-049ceb5c6151","resolution":{"observed_at":"2026-08-01T16:13:36.301063Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:36.413114Z","title":"Woods-Robinson, D","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:36.413114Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:fcb2ebddc2cba65609cd20bf4fb5c523525b656a32244b3043b8b0b2153eaca5","observation_id":"8c7c8947-c992-40c4-805f-e42f3b02aa89","resolution":{"observed_at":"2026-08-01T16:13:36.413114Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:36.534766Z","title":"Mueller, G","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:36.534766Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:38311e531f3aa37630dea601cbabdb388a7860062989082956ccadfe19ca3a18","observation_id":"c32aacc3-47a7-4e9c-be5f-c18f9a023288","resolution":{"observed_at":"2026-08-01T16:13:36.534766Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:36.647621Z","title":"Kirklin, J","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:36.647621Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:f219cf43ab4d918ac8f6cdf29f58042ddd23ffcc8e882d62b2ad0b96e2e3ab4f","observation_id":"93d73c60-e09a-41ab-b6b9-1efa19755b9b","resolution":{"observed_at":"2026-08-01T16:13:36.647621Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:36.744648Z","title":"Aykol, S","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:36.744648Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:bc8c07f359864dcf61582a6769ede13426c792eb611f21c225634d7389752419","observation_id":"51ef7bfb-477a-47a0-81a6-9d931672d9e3","resolution":{"observed_at":"2026-08-01T16:13:36.744648Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:36.858567Z","title":"Warford, F","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:36.858567Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:bc4a39a80bba7e059099099b617ef7e86c01d8dfb26a1153ab528b3fd402626d","observation_id":"b1cc26fd-4207-40a9-8415-e55819baf210","resolution":{"observed_at":"2026-08-01T16:13:36.858567Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:37.027727Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:37.027727Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:cec414933c721e01822cb02b8312bf45e87bf9b45be0ed0f995927959cc793ca","observation_id":"73682b09-ca52-49e3-9cc7-f1bf96a951af","resolution":{"observed_at":"2026-08-01T16:13:37.027727Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.19302","last_updated":"2024-02-06T13:14:35Z","snapshot_observed_at":"2026-08-13T11:29:20.752993Z","submitted_at":"2023-05-30T15:26:43Z","title":"Smooth, exact rotational symmetrization for deep learning on point clouds","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.19302","snapshot_observed_at":"2026-08-01T16:13:37.210404Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:37.210404Z"},"links":{"cited_paper":"/paper/2305.19302","citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:61f3062eaa0cf97ec3cd2dfc91bf129e48710e9763e591852cbc57fd8375fa5b","observation_id":"03346160-a477-4aa4-b0c6-1b58a48ed8f0","resolution":{"observed_at":"2026-08-01T16:13:37.210404Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.16195","last_updated":"2026-06-04T09:53:42Z","snapshot_observed_at":"2026-08-03T08:46:36.608036Z","submitted_at":"2026-01-22T18:46:58Z","title":"Pushing the limits of unconstrained machine-learned interatomic potentials","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.16195","snapshot_observed_at":"2026-08-01T16:13:37.324630Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:37.324630Z"},"links":{"cited_paper":"/paper/2601.16195","citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:eccb20e5b8ecb9294e51416256101eea39d6bbeedb0d98cf9750f0062699ab75","observation_id":"60b6195f-75e8-4372-8f9e-ac8a39f529e5","resolution":{"observed_at":"2026-08-01T16:13:37.324630Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:37.495466Z","title":"Riebesell, R","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:37.495466Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:c01d334770d934f365473bf8dc38a6fb5fab2ec19cb3c01901607792dc80507c","observation_id":"63157853-594b-48d7-935b-ff53e03ff555","resolution":{"observed_at":"2026-08-01T16:13:37.495466Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.12771","last_updated":"2026-05-20T00:46:02Z","snapshot_observed_at":"2026-08-15T03:47:51.196617Z","submitted_at":"2024-10-16T17:48:34Z","title":"Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.12771","snapshot_observed_at":"2026-08-01T16:13:37.670300Z","title":"Barroso-Luque, M","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:37.670300Z"},"links":{"cited_paper":"/paper/2410.12771","citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:1f65ae3eab66ca3971a0f297438b952489846dfdd4e0f0c82e7bb1e189a432cc","observation_id":"dbdc95e7-6a74-492b-bb57-f8483768a740","resolution":{"observed_at":"2026-08-01T16:13:37.670300Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:37.826540Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:37.826540Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:bd77912b374bffcf3d3bb0275eb8671d35676049cacd819cf25f26ca90f0cf89","observation_id":"cd23d93e-7b2c-4796-9ed6-cdbe6905d3f4","resolution":{"observed_at":"2026-08-01T16:13:37.826540Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1002/aisy.202501497","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Chorna, D","venue":"Advanced Intelligent Systems","work_id":"3afb9bdf-28dd-456d-8c8d-8f2ee69929d3","year":2026},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:38.011913Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:05f76ec371bf103cd67deadc7cb2d9062179449c289fb6b0b33a1e7e7e1077c1","observation_id":"ca18d280-81c7-4f2c-b50a-ba5a03108aa8","resolution":{"observed_at":"2026-08-01T16:19:08.321490Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:38.139728Z","title":"Breiman, Machine Learning45, 5 (2001)","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:38.139728Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:a328fa07c0728f3fd4571bf11f67fdf84df374ba950faf79aba92012dc810d76","observation_id":"26ac3d36-50fd-4c6e-b08e-866e654ddbfa","resolution":{"observed_at":"2026-08-01T16:13:38.139728Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:38.267834Z","title":null,"venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:38.267834Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:e52eeef050ad34bb3b933ecaf089d484db88672f4ac06b48920fe4d809cf13e3","observation_id":"7ba24896-f17b-4baf-89c1-0eec39a77936","resolution":{"observed_at":"2026-08-01T16:13:38.267834Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:38.386047Z","title":null,"venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:38.386047Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:b7dc6bc7228579984ff6cbef7ff484c5af3c542d325b960b1d1fb7821ac97ac5","observation_id":"eb8a79cf-a1a2-4756-aa81-41a7202fe8e3","resolution":{"observed_at":"2026-08-01T16:13:38.386047Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:38.520873Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:38.520873Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:60ec30e2ad59a985ee8d14b9c4719269a7658b730bbb7a11c90ae3e54b73171f","observation_id":"ad735d63-d706-40e0-8a7f-f7b7b496f914","resolution":{"observed_at":"2026-08-01T16:13:38.520873Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:38.644394Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:38.644394Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:f5795356db3d86de838775b92646e3e7afd26cf66aa4a27ec39142d30c3e0ea9","observation_id":"13fa4cec-9ffd-4cbe-8d07-b28839a36d4f","resolution":{"observed_at":"2026-08-01T16:13:38.644394Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:38.851064Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:38.851064Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:4e38e27f4c4e740baf825bc58a323647538e4d7477b629afdc981851f23b5baa","observation_id":"8b44861d-c18c-4d85-a7ce-cb5b4215eda0","resolution":{"observed_at":"2026-08-01T16:13:38.851064Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:39.047286Z","title":"Lejaeghere, G","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:39.047286Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:fbbad82e063d5613d48da2ccf31d85a30a27db78a61443f6c3d5643c39e69051","observation_id":"8fea11f5-7542-4c02-95b6-bd69c8922eb3","resolution":{"observed_at":"2026-08-01T16:13:39.047286Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:39.155868Z","title":"Kozhevnikov, M","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:39.155868Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:d73e7dfe6d0abd7e50963e87f70b317c28d6902de8ed0b798cd188de2ee2edc3","observation_id":"8e5a9d40-e065-4c9d-b683-c62b04a048f2","resolution":{"observed_at":"2026-08-01T16:13:39.155868Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:39.260092Z","title":"Giannozzi, S","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:39.260092Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:d39474a4213277cb5e81081f15d9fc5cce10c528d598bcbb9b082465345be0df","observation_id":"fcad3186-2a59-4638-832c-d546d2053866","resolution":{"observed_at":"2026-08-01T16:13:39.260092Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:39.378951Z","title":"Giannozzi, O","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:39.378951Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:d9f2f95ca3878afed53c84e7c0e7c91669c658c74f51be801f08232d76b80c4e","observation_id":"c2628a1a-b3e3-44fe-b1da-2b49b3932c16","resolution":{"observed_at":"2026-08-01T16:13:39.378951Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:39.553041Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:39.553041Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:404adb8b357f0b5c71dec503095baaa4cc9bbd36caeb19ff161c844a85692d54","observation_id":"cde203b3-78ce-4aa7-b5a1-89d48c26a915","resolution":{"observed_at":"2026-08-01T16:13:39.553041Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1038/s41524-026-02097-8","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"de Miranda Nascimento, F","venue":"npj Computational Materials","work_id":"ecaf4e42-96d3-4416-9dcf-758bfbbb169d","year":2026},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:39.661743Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:90adbf1bb38c44e7d03275b30704553daae2fb46c451059b3c5b071cfa651dd5","observation_id":"201267d6-5bf8-4994-bd55-74a0e16408c9","resolution":{"observed_at":"2026-08-01T16:19:08.308519Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1038/sdata.2017.162","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"Scientific Data","work_id":"6ac1d474-7a7b-4063-b9c6-1c41f1637d9e","year":2017},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:39.744772Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:61a891855371b3e47b95d2a33a53da1c7bee65d9d622ef7b9b70c800bbc5ee02","observation_id":"34042e2e-d57a-43d8-b2bd-a733a07a5ff6","resolution":{"observed_at":"2026-08-01T16:19:08.297054Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:39.801782Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:39.801782Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:f0ad01c9b788721706a3663198e23cb92149df98918e29a610bf8b93b2adbfd9","observation_id":"7492975d-f255-4b83-8305-08810d7a7c98","resolution":{"observed_at":"2026-08-01T16:13:39.801782Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:39.849613Z","title":"Kubaschewski, C","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:39.849613Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:37b8449b3e74495605469322d952983fc66b49919f7226b565158e7d0843477f","observation_id":"522db53a-25ca-45a0-aab6-089c89e23f16","resolution":{"observed_at":"2026-08-01T16:13:39.849613Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:39.921487Z","title":null,"venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:39.921487Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:e5b4e6a0820b71c02682933c6f3afc42cf20864913f2576f0973908b3e2f6463","observation_id":"e0b32dc4-2639-4779-b8d2-d40e33b16413","resolution":{"observed_at":"2026-08-01T16:13:39.921487Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:40.007714Z","title":"Rzyman, Z","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:40.007714Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:57020495be982e77ba0d7cf5981efb8e0497b9d28c45003019de662eb7e10a39","observation_id":"6d41e140-8136-48b6-8b0e-5f515bd4bf4d","resolution":{"observed_at":"2026-08-01T16:13:40.007714Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:40.086353Z","title":"(CRC Press, 2007)","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:40.086353Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:679f88d7aca0236c1fc1f61853180dccb29d84c966c3ba09795cb19fa1c4b7af","observation_id":"2eeb6e17-83a9-4744-a880-2830652d960c","resolution":{"observed_at":"2026-08-01T16:13:40.086353Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:40.172302Z","title":"Grindy, B","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:40.172302Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:6632e5d35496fcdae1bb46437fd5067e54434127f6eb138df3338932491fbd33","observation_id":"46e40ddf-e0ce-438f-ae63-093992a7e850","resolution":{"observed_at":"2026-08-01T16:13:40.172302Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:40.240057Z","title":"Kresse and J","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:40.240057Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:760c804a9e6e5b5f2bcc356c859e7eaac81f1a0754dedc8c55a857021695e931","observation_id":"c55c9c64-db15-46f9-830e-f9f931b26c46","resolution":{"observed_at":"2026-08-01T16:13:40.240057Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:40.310985Z","title":"Kresse and J","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:40.310985Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:fae1720237d5d78a0bd7bb4538f22538fbc1d6cfaa5c6a4b9362286aab0afb3e","observation_id":"01769c0f-3e53-42a5-8473-1f4683ce5839","resolution":{"observed_at":"2026-08-01T16:13:40.310985Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:40.386471Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:40.386471Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:1ec2e59a3c42f37261417f61130d32cb57386642ff23611120c8d14072ff5962","observation_id":"b2742c80-871b-4541-ab03-6167d14f0421","resolution":{"observed_at":"2026-08-01T16:13:40.386471Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:40.466932Z","title":null,"venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:40.466932Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:6d4c828f2ef24338c569aa9ce03da538ae8c1fc1547ed246cac171fe97cd0249","observation_id":"eb94768c-6c0b-4598-8847-9f8c58339ce4","resolution":{"observed_at":"2026-08-01T16:13:40.466932Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:40.523244Z","title":"In contrast to these constant cutoffs, the MC3D follows the SSSP [39] protocol where a set of recommended cutoffs for each element were established","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:40.523244Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:f8fcada5d3929e5a08f28eb818cc43897c3d96ceb920b7346adbb40ff007a7cc","observation_id":"cd591f9a-e5e0-4a15-a5a1-3496f84ea2e3","resolution":{"observed_at":"2026-08-01T16:13:40.523244Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:13:40.576352Z","title":"calc” to calculate formation energies are “Pure DFT","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-01T16:13:40.576352Z"},"links":{"citing_paper":"/paper/2607.18092"},"observation_digest":"sha256:aab8d2939da4fce1972f0c80425c4ea99b8d22d34a473128a86f76e2defc8c7e","observation_id":"ffeb69ef-3185-4bc8-9c25-0d08b9b44749","resolution":{"observed_at":"2026-08-01T16:13:40.576352Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.18092","last_updated":"2026-07-20T15:55:37Z","latest_version":1,"primary_category":"cond-mat.mtrl-sci","snapshot_observed_at":"2026-08-13T03:22:10.367695Z","submitted_at":"2026-07-20T15:55:37Z","title":"Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning"},"reference_resolution":{"displayed":93,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":90,"verified_exact":3,"verified_fuzzy":0},"total_outbound_references":93},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 93 of 93 outbound references and 0 inbound Pith citation observations for arXiv:2607.18092."}