{"as_of":"2026-08-09T18:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:051429e0644f6eaaf37dd30e6a9dab819c99cf128a266b7074667f013f39a9ef","coverage":[{"denominator":55,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":55,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-30T11:00:16.249792Z","state":"measured"},{"denominator":55,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":55,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2607.23835/citation-record","integrity":"/paper/2607.23835/integrity","json":"/paper/2607.23835/citation-record.json","paper":"/paper/2607.23835"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-30T11:00:15.929378Z","title":"Where mllms attend and what they rely on: Explaining autoregressive token generation,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:15.929378Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:efc5eadab81c144933d0c15e44efce991dbbd643c6c5cb613a585edd76802c30","observation_id":"66242aa2-9dab-4f25-bcdd-6e090d36bfbd","resolution":{"observed_at":"2026-07-30T11:00:15.929378Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.00470","last_updated":"2026-05-19T12:16:55Z","snapshot_observed_at":"2026-07-06T21:02:08.295333Z","submitted_at":"2025-04-01T06:58:15Z","title":"Less is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.00470","snapshot_observed_at":"2026-07-30T11:00:15.935227Z","title":"Less is more: Efficient black-box attribution via minimal interpretable subset selection,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:15.935227Z"},"links":{"cited_paper":"/paper/2504.00470","citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:c410e9a3a9d1eda5ab9ca4e5bbfe4e10a014b33dfc02dfd571d2ba3b4488af76","observation_id":"764eb823-7d08-4001-ba50-138e4841ce6a","resolution":{"observed_at":"2026-07-30T11:00:15.935227Z","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":"2026-07-30T11:00:15.941906Z","title":"Axiomatic attribution for deep networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:15.941906Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:c5a28660851bf08414338b1ffbcd5f907b371149ad27f82a2d6ced486f919a20","observation_id":"f941b623-cdaa-41aa-9c9f-426562ea409c","resolution":{"observed_at":"2026-07-30T11:00:15.941906Z","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":"2026-07-30T11:00:15.947690Z","title":"Ig 2: Integrated gradient on iterative gradient path for feature attribution,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:15.947690Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:d633c95ad30e1ca5f6d2c676a7ec7ca3ea511d5ae26a50b7ad0cc4bec9a91c74","observation_id":"44cee7dc-7aff-4f32-8a8d-94f236979a88","resolution":{"observed_at":"2026-07-30T11:00:15.947690Z","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":"2026-07-30T11:00:15.953061Z","title":"Path choice matters for clear attributions in path methods,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:15.953061Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:9d23a9295c1c6c2ff09d067e60f113f9c96f7ce44bb7599dd78342d513ce6b66","observation_id":"a09c5d05-86ca-410b-9690-239082ff84b4","resolution":{"observed_at":"2026-07-30T11:00:15.953061Z","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":"2026-07-30T11:00:15.958040Z","title":"Gradient-based visual explanation for transformer-based CLIP,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:15.958040Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:85113269462d929e99903551840a7ac05e88ca90c439456728cef446e278747a","observation_id":"a602ca7d-6d5a-434a-a839-8abaa7ff3268","resolution":{"observed_at":"2026-07-30T11:00:15.958040Z","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":"2026-07-30T11:00:15.963890Z","title":"A unified approach to interpreting model predictions,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:15.963890Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:0cb4af61a511e93288eeb93b4bf5c3e194c6361603066f6e278a26078afa3fb3","observation_id":"84647671-231f-4712-8dfa-8ae4a3d4e91d","resolution":{"observed_at":"2026-07-30T11:00:15.963890Z","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":"2026-07-30T11:00:15.968808Z","title":"Going beyond XAI: A systematic survey for explanation-guided learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:15.968808Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:a067bb648daa155a99e5b3fd9ad46fa6db97ba7a5586b0fbae4a38a32040a19c","observation_id":"3e0a03bf-c0a9-4124-88d1-d2323cb24dba","resolution":{"observed_at":"2026-07-30T11:00:15.968808Z","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":"2026-07-30T11:00:15.974132Z","title":"Generalized semantic contrastive learning via embedding side information for few- shot object detection,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:15.974132Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:8fbad685ef03118aeced3e5ef53c9f46aa007582d4d582119a0057f65b2c707f","observation_id":"de8ff9a2-b48d-416c-ab34-5bea4882ff4a","resolution":{"observed_at":"2026-07-30T11:00:15.974132Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2602.07008","last_updated":"2026-07-20T11:10:30Z","snapshot_observed_at":"2026-08-03T23:15:33.062867Z","submitted_at":"2026-01-30T10:29:27Z","title":"Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints for Reliable Decision-Making","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2602.07008","snapshot_observed_at":"2026-07-30T11:00:15.979071Z","title":"Where not to learn: Prior-aligned training with subset-based attribution constraints for reliable decision-making,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:15.979071Z"},"links":{"cited_paper":"/paper/2602.07008","citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:46997c0cbe7f414a181e2fc2998c4e5a90dd480fa2b92107b29b4f29f8c98cc5","observation_id":"1cd6afef-5da0-43cc-93ba-654b1e848313","resolution":{"observed_at":"2026-07-30T11:00:15.979071Z","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":"2026-07-30T11:00:15.984804Z","title":"Underspec- ification presents challenges for credibility in modern machine learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:15.984804Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:8725683f6ee9d97a89acc2e216b5264e9c38f36e1e0d459f776cc9758c14e208","observation_id":"6fc860be-c25e-4bcf-8931-f007fdc68744","resolution":{"observed_at":"2026-07-30T11:00:15.984804Z","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":"2026-07-30T11:00:15.990220Z","title":"Imagenet-trained cnns are biased towards texture; in- creasing shape bias improves accuracy and robustness,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:15.990220Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:4c2b2a3af53b3fe3eb069b57a1faae7894a20b2c014a8927b2c13439e32dc77b","observation_id":"22293379-50e5-41e9-ba94-b853f0b0c24a","resolution":{"observed_at":"2026-07-30T11:00:15.990220Z","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":"2026-07-30T11:00:15.995826Z","title":"Evaluating the robustness of inter- pretability methods through explanation invariance and equivariance,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:15.995826Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:62d1bd0abb7342efa4d59ac7c72a270092de73d17fd66976df4d1a5877a6b5d0","observation_id":"c143e242-57d3-4216-a1b1-4d78e389c4fd","resolution":{"observed_at":"2026-07-30T11:00:15.995826Z","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":"2026-07-30T11:00:16.008105Z","title":"Hive: Evaluating the human interpretability of visual explanations,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.008105Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:559fd50097892d5ad95ab899f8d2c5e6c8f18ed769663f149956d5818ae591e9","observation_id":"cc598a7f-4520-4fe2-a5d3-eb8ba17dad29","resolution":{"observed_at":"2026-07-30T11:00:16.008105Z","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":"2026-07-30T11:00:16.013676Z","title":"Making deep neural networks right for the right scientific reasons by interacting with their explanations,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.013676Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:04b18da17d5c42feef484d4f4bb9942a3cb61b2839448b7b51c8cb0e857f2cfe","observation_id":"618e3f80-f389-492a-adc4-6e78d761f294","resolution":{"observed_at":"2026-07-30T11:00:16.013676Z","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":"2026-07-30T11:00:16.020208Z","title":"Right for the right rea- sons: Training differentiable models by constraining their explanations,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.020208Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:40bcd60b717f2e6991e8b23a0d1545fbc20a9c7217f78d5b0e3b0e50dcde3195","observation_id":"191c3891-904e-43cc-9ce3-15285c0161c9","resolution":{"observed_at":"2026-07-30T11:00:16.020208Z","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":"2026-07-30T11:00:16.026430Z","title":"Taking a HINT: leveraging explanations to make vision and language models more grounded,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.026430Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:2fa542a04016501e3b04fc3f93958a22a1df969b90d43f745680dba65ae73e35","observation_id":"1465c17c-0443-4de3-8300-44696e8483ac","resolution":{"observed_at":"2026-07-30T11:00:16.026430Z","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":"2026-07-30T11:00:16.031532Z","title":"Improving visual grounding by encouraging consistent gradient-based explanations,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.031532Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:13da53f5f938a5e3aeb62cce20bc73a725a82630e848da7120cf902f780574dd","observation_id":"971a3bbe-d412-42d9-a748-053b238335c7","resolution":{"observed_at":"2026-07-30T11:00:16.031532Z","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":"2026-07-30T11:00:16.036309Z","title":"Explainable models with consistent inter- pretations,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.036309Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:18bfb8b2b4700628a60f8b0b6dc31bdb095acde00ce86a02cf7333fec21422f0","observation_id":"926e83ac-e709-4f05-a2ac-fe38907fd6b2","resolution":{"observed_at":"2026-07-30T11:00:16.036309Z","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":"2026-07-30T11:00:16.041393Z","title":"Consistent explanations by contrastive learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.041393Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:4b8359799bbad93a8b8f91b04597d15c1bc60dda014dd6448d8155f05319add1","observation_id":"af086037-9e48-4683-bc83-8653d8a9a4b8","resolution":{"observed_at":"2026-07-30T11:00:16.041393Z","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":"2026-07-30T11:00:16.046791Z","title":"Are data-driven explanations robust against out-of-distribution data?","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.046791Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:954fc8749df8aa2bed241d07c6879d42bbc5cdf44e037b6469cefb3d61e44b9e","observation_id":"62aa879c-0c3a-4c02-8d13-80bdb8e61c1a","resolution":{"observed_at":"2026-07-30T11:00:16.046791Z","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":"2026-07-30T11:00:16.052106Z","title":"ICEL: learning with inconsistent expla- nations,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.052106Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:7001ea8e10f9f0bb8d003694bc245e2721a3ce4e7108efb99fcdbdfd23e86d53","observation_id":"02a2467c-79b8-487e-9b92-24355f9b7fc4","resolution":{"observed_at":"2026-07-30T11:00:16.052106Z","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":"2026-07-30T11:00:16.057377Z","title":"Grad-cam: Visual explanations from deep networks via gradient-based localization,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.057377Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:bb88ff57ed64ed5077e397207721e66cb78e2b377c6c726ea653f2bf1ae91132","observation_id":"eb0a8e36-9af5-46e3-841b-0b1bb0279dcb","resolution":{"observed_at":"2026-07-30T11:00:16.057377Z","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":"2026-07-30T11:00:16.063968Z","title":"Sanity checks for saliency maps,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.063968Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:7abdbd27f31645ca1f019dc1f1ff5061d333240a3d1fb4c1482f883772c5c993","observation_id":"f06a3cf1-bdf6-4774-b621-0016c438e8af","resolution":{"observed_at":"2026-07-30T11:00:16.063968Z","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":"2026-07-30T11:00:16.070817Z","title":"On the relationship between explanation and prediction: A causal view,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.070817Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:cafff46c27ba80480f3750f64da31dea2a1d1fb07b4ae1b25f3e9f35beff4ea2","observation_id":"ee42f2a0-f08b-42a9-91ea-d3ca37886bea","resolution":{"observed_at":"2026-07-30T11:00:16.070817Z","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":"2026-07-30T11:00:16.076276Z","title":"Less is more: Fewer interpretable region via submodular subset selection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.076276Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:9a9cc3d6f9ccca70f60cea5509b2b89b4c163d22bcc97dd48905607ce3b3481e","observation_id":"5a7081f7-71cb-4644-9ef2-2311d9c9e1a7","resolution":{"observed_at":"2026-07-30T11:00:16.076276Z","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":"2026-07-30T11:00:16.082905Z","title":"One explanation is not enough: structured attention graphs for image classification,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.082905Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:9032f73d3889e5dec7b4042de96c2244e5f9bb059dd05e55887b6836a364c223","observation_id":"f668ef24-6f20-4058-aec4-247362474570","resolution":{"observed_at":"2026-07-30T11:00:16.082905Z","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":"2026-07-30T11:00:16.088526Z","title":"Identifying important group of pixels using interactions,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.088526Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:f03c36da75fe03d235b07c8efb5977d3b3bca6258e69fff2ff2e258f7e5089d4","observation_id":"af776886-e16b-49f2-a118-42098b8892c1","resolution":{"observed_at":"2026-07-30T11:00:16.088526Z","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":"2026-07-30T11:00:16.094509Z","title":"Interpreting object-level foundation models via visual precision search,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.094509Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:dc1337e9ade8e0c7ed5aaa1b725e5e589cdadaadfae93bd9f08d0e004746941a","observation_id":"d6705c0d-77cf-4dde-95d1-e548ebaed401","resolution":{"observed_at":"2026-07-30T11:00:16.094509Z","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":"2026-07-30T11:00:16.100864Z","title":"Grounding DINO: marrying DINO with grounded pre-training for open-set object detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.100864Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:a9b563d4af9aa6e3c7eade4064e7a82d5b70024aad0f1155ce6f7e7927810b56","observation_id":"a179055b-59e7-41c1-85c9-acafe09f13fe","resolution":{"observed_at":"2026-07-30T11:00:16.100864Z","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":"2026-07-30T11:00:16.106179Z","title":"Florence-2: Advancing a unified representation for a variety of vision tasks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.106179Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:651a16a60e9b70e40561c6b147c8dacde81d800a68a1b776c6f9ab54b86e4988","observation_id":"5545c046-960f-4b89-bd38-c111478a2a89","resolution":{"observed_at":"2026-07-30T11:00:16.106179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.08049","last_updated":"2018-06-21T02:33:44Z","snapshot_observed_at":"2026-07-06T06:46:01.245927Z","submitted_at":"2018-06-21T02:33:44Z","title":"On the Robustness of Interpretability Methods","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.08049","snapshot_observed_at":"2026-07-30T11:00:16.112270Z","title":"On the robustness of interpretabil- ity methods,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.112270Z"},"links":{"cited_paper":"/paper/1806.08049","citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:235c18725e3c57e62ecb24bb0258c5c16c622ac983b1e4c13f544d58c3521401","observation_id":"1fad4a30-d5d4-467a-b537-9873f52c0f51","resolution":{"observed_at":"2026-07-30T11:00:16.112270Z","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":"2026-07-30T11:00:16.117467Z","title":"Interpretation of neural networks is fragile,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.117467Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:1006acff12f13f63170ba4177ea701c2b1dc082c99c00139694fadba1aca6187","observation_id":"45f3dd0f-b8bf-432a-997d-3d9d921c5569","resolution":{"observed_at":"2026-07-30T11:00:16.117467Z","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":"2026-07-30T11:00:16.122580Z","title":"Evaluating the robustness of inter- pretability methods through explanation invariance and equivariance,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.122580Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:5fc52e976320895c16063522625fb9129a6ac853de8e33c02412b63b3c839a7f","observation_id":"171c5263-19cc-4952-9283-18fff446bead","resolution":{"observed_at":"2026-07-30T11:00:16.122580Z","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":"2026-07-30T11:00:16.130548Z","title":"An analysis of approximations for maximizing submodular set functions - I,","venue":null,"work_id":null,"year":1978},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.130548Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:e818132232e89b6c342c0c0af45e02697a0905782cce8e9d42a36c2fc6df15de","observation_id":"322be3b0-438e-40d2-91c0-05bc26e6c48c","resolution":{"observed_at":"2026-07-30T11:00:16.130548Z","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":"2026-07-30T11:00:16.137447Z","title":"Boosting the visual interpretability of CLIP via adversarial fine-tuning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.137447Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:2c0f0c72634454953dd6c3b6c486e273014c3baba9e3bb6f8795c5d8543143bb","observation_id":"1b5f7823-9540-4935-9092-62ec25610ce0","resolution":{"observed_at":"2026-07-30T11:00:16.137447Z","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":"2026-07-30T11:00:16.143978Z","title":"Imagenet: A large-scale hierarchical image database,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.143978Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:cfc7f512e7cf23443d656666019fe89f082ce55c5bb42bac67b79190a9e44dd2","observation_id":"0bce00c9-1a66-40df-8302-adfcc0169b1c","resolution":{"observed_at":"2026-07-30T11:00:16.143978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.07159","last_updated":"2020-06-12T13:17:25Z","snapshot_observed_at":"2026-08-07T08:01:08.867333Z","submitted_at":"2020-06-12T13:17:25Z","title":"Are we done with ImageNet?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.07159","snapshot_observed_at":"2026-07-30T11:00:16.150623Z","title":"Are we done with imagenet?","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.150623Z"},"links":{"cited_paper":"/paper/2006.07159","citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:d91abb02290ffdb8d9d45c5dd92da6aa81463d999ac29d3a553299fea5c4b547","observation_id":"102db97d-c0fb-4f68-ac02-554b4a632b0c","resolution":{"observed_at":"2026-07-30T11:00:16.150623Z","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":"2026-07-30T11:00:16.157337Z","title":"Do imagenet classifiers generalize to imagenet?","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.157337Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:ad757eda1b564c9ff69bd10743825c9493aa4dce89ad88b5bf3acb6016d1344a","observation_id":"7d63b7f7-724e-4c75-b3ce-3ddfa877bf86","resolution":{"observed_at":"2026-07-30T11:00:16.157337Z","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":"2026-07-30T11:00:16.162815Z","title":"Benchmarking neural network robustness to common corrup- tions and perturbations,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.162815Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:67794f76ff3d7f4bc070d9f28ea4a8c9b43cea2367bc2ae5b4dbdedbf1dac292","observation_id":"e4c774a0-79ef-43d2-8eba-526b7b455977","resolution":{"observed_at":"2026-07-30T11:00:16.162815Z","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":"2026-07-30T11:00:16.168136Z","title":"Objectnet: A large-scale bias-controlled dataset for pushing the limits of object recognition models,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.168136Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:59213971552f365708e9b5f07f13deea008f556883e5d3ebd82e17ccbfcdaabb","observation_id":"bd7b3110-d30b-43f3-bb1f-211d0da2a86a","resolution":{"observed_at":"2026-07-30T11:00:16.168136Z","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":"2026-07-30T11:00:16.174506Z","title":"Learning robust global representations by penalizing local predictive power,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.174506Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:0c1a15a7cc8eb4daa7140603900c710b35b4d57392adeb685f21b7ec8d46149f","observation_id":"22a7893e-ec89-48ea-a294-242fae88076b","resolution":{"observed_at":"2026-07-30T11:00:16.174506Z","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":"2026-07-30T11:00:16.181728Z","title":"The many faces of robustness: A critical analysis of out-of-distribution generalization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.181728Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:1a5fd0ca8d13b20eecfe5ece4397ccd1f917d05789ceb0d00a02f843afe5f582","observation_id":"f43ec780-0b51-4c8f-becd-2919149f5c45","resolution":{"observed_at":"2026-07-30T11:00:16.181728Z","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":"2026-07-30T11:00:16.188044Z","title":"Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.188044Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:0c71097085f44c5d9e68ed733c826da5013dc551e2f2ebdca0b654d838f59e3f","observation_id":"fbdf54c0-e51c-4a80-97a3-7ebc07eba202","resolution":{"observed_at":"2026-07-30T11:00:16.188044Z","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":"2026-07-30T11:00:16.195195Z","title":"Natural adversarial examples,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.195195Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:e8d0a9a63f2343e6eeb71e06011d02121cf7a1721ade5a0764a2c29f0bdf157a","observation_id":"c2af901c-54b9-4ed8-8f27-6d03d30d77c6","resolution":{"observed_at":"2026-07-30T11:00:16.195195Z","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":"2026-07-30T11:00:16.200240Z","title":"Leaving reality to imagination: Robust classification via generated datasets,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.200240Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:6c81c2c0a9852a2fccdb75ea3cfb736200219409aaf68878813f4c686645ddb4","observation_id":"b23a7995-2ff7-4496-856f-0ca208f4568e","resolution":{"observed_at":"2026-07-30T11:00:16.200240Z","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":"2026-07-30T11:00:16.205345Z","title":"Are data-driven explanations robust against out-of-distribution data?","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.205345Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:f37ee74d3c9ceda942466ced058985ee2aabbaf22ec43b00a801dd7b9766f717","observation_id":"f76f55e5-87ae-4cd9-975d-e53a5cb33c97","resolution":{"observed_at":"2026-07-30T11:00:16.205345Z","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":"2026-07-30T11:00:16.210452Z","title":"Training for stable explanation for free,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.210452Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:a5f4c30de1a62a6a155696a940be4b9716807e0f7e2bdec00f662381f9276e16","observation_id":"67cc6300-4d94-4897-b3c5-c03a3431054d","resolution":{"observed_at":"2026-07-30T11:00:16.210452Z","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":"2026-07-30T11:00:16.216519Z","title":"Explanation-guided adversarial training for robust and interpretable models,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.216519Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:55e9bbffe4cfb42d241631c2ce68eec0dd69aa724d2f7422ad859bd4289b37b4","observation_id":"1c381a15-87de-4c65-8973-1c7449c0b893","resolution":{"observed_at":"2026-07-30T11:00:16.216519Z","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":"2026-07-30T11:00:16.221754Z","title":"Rise: Randomized input sampling for explanation of black-box models,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.221754Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:3b3c8c4058da8df111b25dabd3259bacb75f81583741d5952b8e85d9825bef07","observation_id":"6366721f-b22b-4b41-98f7-99c71beca20e","resolution":{"observed_at":"2026-07-30T11:00:16.221754Z","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":"2026-07-30T11:00:16.228040Z","title":"Benchmarking deletion metrics with the principled explanations,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.228040Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:0c82fc5c65e1057b304ba1a2721ecf1bccec2846b22dbb8c4ea4878c43cc075e","observation_id":"2b064219-a334-43d3-93dc-0ca4861f7ef0","resolution":{"observed_at":"2026-07-30T11:00:16.228040Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.03400","last_updated":"2023-06-06T04:30:18Z","snapshot_observed_at":"2026-08-09T18:45:33.691987Z","submitted_at":"2023-06-06T04:30:18Z","title":"G-CAME: Gaussian-Class Activation Mapping Explainer for Object Detectors","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.03400","snapshot_observed_at":"2026-07-30T11:00:16.233206Z","title":"G-CAME: gaussian-class activation mapping explainer for object detectors,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.233206Z"},"links":{"cited_paper":"/paper/2306.03400","citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:6501d827aef12840be4ee316bc282d0862aef030cccd581cc1e00eaf29f7d636","observation_id":"6f2ac21d-77d0-46c8-9eaa-dc1349471228","resolution":{"observed_at":"2026-07-30T11:00:16.233206Z","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":"2026-07-30T11:00:16.239108Z","title":"How to probe: Simple yet effective techniques for improving post-hoc explanations,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.239108Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:816462972da9c18c5e51dbd5c54e361702aba4b7694d5c17bbc2c6a8d395e7d2","observation_id":"6a1e82b3-7582-47ff-8160-b0c8fa1c48f1","resolution":{"observed_at":"2026-07-30T11:00:16.239108Z","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":"2026-07-30T11:00:16.244554Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.244554Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:fb8c2ca7e9563a15623149164be99e017edfdab10d77927e736cd7b0d240dc28","observation_id":"aaec3e5d-e262-4bf8-8991-fb73ae216a23","resolution":{"observed_at":"2026-07-30T11:00:16.244554Z","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":"2026-07-30T11:00:16.249792Z","title":"A convnet for the 2020s,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:16.249792Z"},"links":{"citing_paper":"/paper/2607.23835"},"observation_digest":"sha256:9601c6849cb4ede1d0b18c249c691d03b78e5b24738fdf1343e3770614e46420","observation_id":"23a6002d-aa33-4182-b31e-b03bfb5cba29","resolution":{"observed_at":"2026-07-30T11:00:16.249792Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.23835","last_updated":"2026-07-26T20:41:38Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T22:16:02.381223Z","submitted_at":"2026-07-26T20:41:38Z","title":"Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations"},"reference_resolution":{"displayed":55,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":55,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":55},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 0 inbound Pith citation observations for arXiv:2607.23835."}