{"as_of":"2026-08-16T17:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6bdd263c7eda008a927df5cf4d16aa4829bfe107b680a860b5a6e1550f8f091f","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T16:56:45.804865Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T15:09:55.438344Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2106.10044","last_updated":"2021-06-18T10:31:00Z","snapshot_observed_at":"2026-08-16T12:09:03.662449Z","submitted_at":"2021-06-18T10:31:00Z","title":"Training or Architecture? How to Incorporate Invariance in Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.10044","snapshot_observed_at":"2026-08-15T16:56:45.804865Z","title":"Training or architecture? how to incorporate invariance in neural networks.arXiv preprint arXiv:2106.10044, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.19593","last_updated":"2025-08-27T06:06:18Z","snapshot_observed_at":"2026-08-16T12:37:30.146432Z","submitted_at":"2025-08-27T06:06:18Z","title":"Generalizing Monocular 3D Object Detection","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T16:56:45.804865Z"},"links":{"cited_paper":"/paper/2106.10044","citing_paper":"/paper/2508.19593"},"observation_digest":"sha256:173495da27717ea03f368af96dd412db8b642e92df72fceae8a92472734a0f23","observation_id":"93cd73fd-5fb6-4914-b2fd-819fef221054","resolution":{"observed_at":"2026-08-15T16:56:45.804865Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.10044","last_updated":"2021-06-18T10:31:00Z","snapshot_observed_at":"2026-08-16T12:09:03.662449Z","submitted_at":"2021-06-18T10:31:00Z","title":"Training or Architecture? How to Incorporate Invariance in Neural Networks","version":1},"cited_work":{"arxiv_id":"2106.10044","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.10044","snapshot_observed_at":"2026-07-04T15:09:55.438344Z","title":"Training or Architecture? How to Incorporate Invariance in Neural Networks","venue":null,"work_id":"a4a6f4b5-1430-4792-9f59-af251477c060","year":2021},"citing_paper":{"arxiv_id":"2606.26273","last_updated":"2026-06-24T18:12:58Z","snapshot_observed_at":"2026-08-15T02:59:03.297310Z","submitted_at":"2026-06-24T18:12:58Z","title":"Equivariance and Augmentation for Bayesian Neural Networks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-26T01:49:17.138893Z"},"links":{"cited_paper":"/paper/2106.10044","citing_paper":"/paper/2606.26273"},"observation_digest":"sha256:e0bf933ef0fc8465a95efdcc632bd62b1f47eefa5467da0b2ce07a1bb372de6d","observation_id":"0020d51e-cb80-4b5b-a6ae-78f0f18e1c10","resolution":{"observed_at":"2026-07-04T15:09:55.440783Z","resolver_source":"arxiv_id","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"}}],"links":{"evidence":"/evidence","html":"/paper/2106.10044/citation-record","integrity":"/paper/2106.10044/integrity","json":"/paper/2106.10044/citation-record.json","paper":"/paper/2106.10044"},"outbound":[],"paper":{"arxiv_id":"2106.10044","last_updated":"2021-06-18T10:31:00Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T12:09:03.662449Z","submitted_at":"2021-06-18T10:31:00Z","title":"Training or Architecture? How to Incorporate Invariance in Neural Networks"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2106.10044."}