{"as_of":"2026-08-21T02:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:59a80885d8638a20e0d3d66020aa9d1c52cb350ca5061e95dc54fa16afa17f8d","coverage":[{"denominator":18,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":18,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T02:13:36.575974Z","state":"measured"},{"denominator":18,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":18,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+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/2607.25546/citation-record","integrity":"/paper/2607.25546/integrity","json":"/paper/2607.25546/citation-record.json","paper":"/paper/2607.25546"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T02:13:36.456549Z","title":"Advances in Neural Information Processing Systems (","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.25546","last_updated":"2026-07-28T10:26:09Z","snapshot_observed_at":"2026-08-05T08:14:48.734365Z","submitted_at":"2026-07-28T10:26:09Z","title":"From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-01T02:13:36.456549Z"},"links":{"citing_paper":"/paper/2607.25546"},"observation_digest":"sha256:9827df2b263d9a83d0e169827e6ce88241aceef9e99f5a0b3236bf454396c6fb","observation_id":"fcba9d0b-8acb-4a6e-99fd-76f09241231e","resolution":{"observed_at":"2026-08-01T02:13:36.456549Z","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":"2026-08-01T02:13:36.469684Z","title":"International Conference on Learning Representations (","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.25546","last_updated":"2026-07-28T10:26:09Z","snapshot_observed_at":"2026-08-05T08:14:48.734365Z","submitted_at":"2026-07-28T10:26:09Z","title":"From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-01T02:13:36.469684Z"},"links":{"citing_paper":"/paper/2607.25546"},"observation_digest":"sha256:80109c10982fcd0b29be6450b607244379aaddfacd3b593d7b6c40050d2c4af5","observation_id":"d4ce313e-27e4-4ad4-b71a-9c97054a6e22","resolution":{"observed_at":"2026-08-01T02:13:36.469684Z","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":"2026-08-01T02:13:36.482342Z","title":"Transformers Can Do","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.25546","last_updated":"2026-07-28T10:26:09Z","snapshot_observed_at":"2026-08-05T08:14:48.734365Z","submitted_at":"2026-07-28T10:26:09Z","title":"From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-01T02:13:36.482342Z"},"links":{"citing_paper":"/paper/2607.25546"},"observation_digest":"sha256:158e356cabbed988964af55c07ab547dcf2f8e26dd5e55c2cfce5c137be9972a","observation_id":"3685093f-b40a-4273-b779-41cbe6322bce","resolution":{"observed_at":"2026-08-01T02:13:36.482342Z","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":"2026-08-01T02:13:36.491406Z","title":"What Learning Algorithm Is In-Context Learning?","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.25546","last_updated":"2026-07-28T10:26:09Z","snapshot_observed_at":"2026-08-05T08:14:48.734365Z","submitted_at":"2026-07-28T10:26:09Z","title":"From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-01T02:13:36.491406Z"},"links":{"citing_paper":"/paper/2607.25546"},"observation_digest":"sha256:0c1f0d0331965a3e96e3e2c7396fbe66822fe730955b9ff9d1213bc87be0ee20","observation_id":"56416d84-b7c9-47b7-a86b-21cbfff9875d","resolution":{"observed_at":"2026-08-01T02:13:36.491406Z","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":"2026-08-01T02:13:36.506613Z","title":"Transformers Learn In-Context by Gradient Descent , booktitle =","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.25546","last_updated":"2026-07-28T10:26:09Z","snapshot_observed_at":"2026-08-05T08:14:48.734365Z","submitted_at":"2026-07-28T10:26:09Z","title":"From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-01T02:13:36.506613Z"},"links":{"citing_paper":"/paper/2607.25546"},"observation_digest":"sha256:3b89aaec2c459f1594f50ef1d5767fca023f058e58d700190f71069b7431e8a2","observation_id":"431fb819-82a9-4702-8670-42a3332d5882","resolution":{"observed_at":"2026-08-01T02:13:36.506613Z","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":"2026-08-01T02:13:36.518708Z","title":"The Eleventh International Conference on Learning Representations (","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.25546","last_updated":"2026-07-28T10:26:09Z","snapshot_observed_at":"2026-08-05T08:14:48.734365Z","submitted_at":"2026-07-28T10:26:09Z","title":"From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-01T02:13:36.518708Z"},"links":{"citing_paper":"/paper/2607.25546"},"observation_digest":"sha256:eb10bbb02441bfbaf118c0a74c3e853fe1a3da761efb0c301d89c07a87c8e650","observation_id":"eedb1ca8-2837-41ad-a9ae-bcda42053059","resolution":{"observed_at":"2026-08-01T02:13:36.518708Z","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":"2026-08-01T02:13:36.534452Z","title":"Invariant Risk Minimization , journal =","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.25546","last_updated":"2026-07-28T10:26:09Z","snapshot_observed_at":"2026-08-05T08:14:48.734365Z","submitted_at":"2026-07-28T10:26:09Z","title":"From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-01T02:13:36.534452Z"},"links":{"citing_paper":"/paper/2607.25546"},"observation_digest":"sha256:91b530fa55bda2449f254e6452568957ee3ca016e6e866111761f2f17dd6d2b2","observation_id":"122e3637-4601-43f8-ad23-6fbb30e35f3c","resolution":{"observed_at":"2026-08-01T02:13:36.534452Z","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":"2026-08-01T02:13:36.538433Z","title":"Causal Inference by Using Invariant Prediction: Identification and Confidence Intervals , journal =","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.25546","last_updated":"2026-07-28T10:26:09Z","snapshot_observed_at":"2026-08-05T08:14:48.734365Z","submitted_at":"2026-07-28T10:26:09Z","title":"From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-01T02:13:36.538433Z"},"links":{"citing_paper":"/paper/2607.25546"},"observation_digest":"sha256:b5355f6470e90fee46f98882238487f3a7da178ce8a43df1e51e7fd7a3040dd9","observation_id":"63d93743-b76c-430f-836f-2ba3aaaa4f55","resolution":{"observed_at":"2026-08-01T02:13:36.538433Z","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":"2026-08-01T02:13:36.542318Z","title":"and Liang, Percy , title =","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.25546","last_updated":"2026-07-28T10:26:09Z","snapshot_observed_at":"2026-08-05T08:14:48.734365Z","submitted_at":"2026-07-28T10:26:09Z","title":"From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-01T02:13:36.542318Z"},"links":{"citing_paper":"/paper/2607.25546"},"observation_digest":"sha256:8d933ddb815d4b7b30092bb047a7de4bbaaadb9870f8ca20cf724fba5800138c","observation_id":"67d62dd3-331f-40da-82a3-29f26c808609","resolution":{"observed_at":"2026-08-01T02:13:36.542318Z","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":"2026-08-01T02:13:36.546074Z","title":"Out-of-Distribution Generalization via Risk Extrapolation (","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.25546","last_updated":"2026-07-28T10:26:09Z","snapshot_observed_at":"2026-08-05T08:14:48.734365Z","submitted_at":"2026-07-28T10:26:09Z","title":"From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-01T02:13:36.546074Z"},"links":{"citing_paper":"/paper/2607.25546"},"observation_digest":"sha256:3d05660bf05ea56c6c054c593aa7aa4302fd8dffb751caa7f69a3ddca88b6505","observation_id":"6b879004-7127-4c53-ad87-90e9526b0b73","resolution":{"observed_at":"2026-08-01T02:13:36.546074Z","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":"2026-08-01T02:13:36.549763Z","title":"arXiv preprint , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.25546","last_updated":"2026-07-28T10:26:09Z","snapshot_observed_at":"2026-08-05T08:14:48.734365Z","submitted_at":"2026-07-28T10:26:09Z","title":"From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-01T02:13:36.549763Z"},"links":{"citing_paper":"/paper/2607.25546"},"observation_digest":"sha256:277da6facefbc9481a8820591b6a704133f8f0967b625934d913f28bc61889da","observation_id":"c76f4079-43c8-43e5-b212-728e1a7e009e","resolution":{"observed_at":"2026-08-01T02:13:36.549763Z","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":"2026-08-01T02:13:36.553853Z","title":", title =","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.25546","last_updated":"2026-07-28T10:26:09Z","snapshot_observed_at":"2026-08-05T08:14:48.734365Z","submitted_at":"2026-07-28T10:26:09Z","title":"From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-01T02:13:36.553853Z"},"links":{"citing_paper":"/paper/2607.25546"},"observation_digest":"sha256:2b281934502be4ac618ac323cdb7732aa9259c708c30fa50e9863a65a013764d","observation_id":"48ffc101-aad4-48ee-8155-7e09aaff4ebe","resolution":{"observed_at":"2026-08-01T02:13:36.553853Z","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":"2026-08-01T02:13:36.557576Z","title":"Logic, Language, Information, and Computation , pages =","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.25546","last_updated":"2026-07-28T10:26:09Z","snapshot_observed_at":"2026-08-05T08:14:48.734365Z","submitted_at":"2026-07-28T10:26:09Z","title":"From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-01T02:13:36.557576Z"},"links":{"citing_paper":"/paper/2607.25546"},"observation_digest":"sha256:96443996f331726f9b41063d15a3a207d74bfc2e8453f3b95187aa5898c9ee8e","observation_id":"7bb0a015-122e-4b59-b6f1-89a06271e2f8","resolution":{"observed_at":"2026-08-01T02:13:36.557576Z","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":"2026-08-01T02:13:36.561229Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.25546","last_updated":"2026-07-28T10:26:09Z","snapshot_observed_at":"2026-08-05T08:14:48.734365Z","submitted_at":"2026-07-28T10:26:09Z","title":"From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-01T02:13:36.561229Z"},"links":{"citing_paper":"/paper/2607.25546"},"observation_digest":"sha256:c104358c92e6871fa15cd212e8ecb0d14e4eef9934fa248dffbcb195f4de5430","observation_id":"0fec7257-f069-4d7f-b1ad-44aba20ded91","resolution":{"observed_at":"2026-08-01T02:13:36.561229Z","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":"2026-08-01T02:13:36.564881Z","title":"and Horlbeck, Max A","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.25546","last_updated":"2026-07-28T10:26:09Z","snapshot_observed_at":"2026-08-05T08:14:48.734365Z","submitted_at":"2026-07-28T10:26:09Z","title":"From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-01T02:13:36.564881Z"},"links":{"citing_paper":"/paper/2607.25546"},"observation_digest":"sha256:a5632af5432aa71519a64ed45b0a90a8041cdf6d3a33038e12727506a40794d3","observation_id":"e0498f07-0fa8-4380-b277-f6bd4834ca2a","resolution":{"observed_at":"2026-08-01T02:13:36.564881Z","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":"2026-08-01T02:13:36.568375Z","title":", title =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25546","last_updated":"2026-07-28T10:26:09Z","snapshot_observed_at":"2026-08-05T08:14:48.734365Z","submitted_at":"2026-07-28T10:26:09Z","title":"From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-01T02:13:36.568375Z"},"links":{"citing_paper":"/paper/2607.25546"},"observation_digest":"sha256:b4573ddda551079e14ff714f7aa65017023d4ef58682f341cccfa29f9b71094f","observation_id":"50d27829-7621-4f46-af06-a162137c9d6b","resolution":{"observed_at":"2026-08-01T02:13:36.568375Z","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":"2026-08-01T02:13:36.572226Z","title":"Event labeling combining ensemble detectors and background knowledge , howpublished =","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.25546","last_updated":"2026-07-28T10:26:09Z","snapshot_observed_at":"2026-08-05T08:14:48.734365Z","submitted_at":"2026-07-28T10:26:09Z","title":"From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-01T02:13:36.572226Z"},"links":{"citing_paper":"/paper/2607.25546"},"observation_digest":"sha256:a6f89c6b9a4ddcb2559913c17be1a2827839df99f57fd22b43fea084c73b0200","observation_id":"6b95f7d4-3ec0-4588-a753-b0ad56418149","resolution":{"observed_at":"2026-08-01T02:13:36.572226Z","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":"2026-08-01T02:13:36.575974Z","title":"Modeling wine preferences by data mining from physicochemical properties , howpublished =","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.25546","last_updated":"2026-07-28T10:26:09Z","snapshot_observed_at":"2026-08-05T08:14:48.734365Z","submitted_at":"2026-07-28T10:26:09Z","title":"From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-01T02:13:36.575974Z"},"links":{"citing_paper":"/paper/2607.25546"},"observation_digest":"sha256:4c33869657064ae13fb32ca823f5054d9c8da45c3bde6e99c9e8b9a3e3eb5483","observation_id":"ea97ad41-eac7-4169-b23c-525fd17df654","resolution":{"observed_at":"2026-08-01T02:13:36.575974Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.25546","last_updated":"2026-07-28T10:26:09Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-05T08:14:48.734365Z","submitted_at":"2026-07-28T10:26:09Z","title":"From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios"},"reference_resolution":{"displayed":18,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":18,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":18},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2607.25546."}