{"as_of":"2026-08-23T14:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:df9912235c1c4ef084468a9ab8f9904e4786e0ba5044483fb01d120c73b6196f","coverage":[{"denominator":52,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":52,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T22:26:48.737161Z","state":"measured"},{"denominator":53,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":53,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T18:33:09.125847Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.07209","snapshot_observed_at":"2026-08-03T18:33:09.125847Z","title":"Discovering fine-grained visual-concept relations by disentangled optimal transport concept bottleneck models, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.05038","last_updated":"2026-05-29T17:42:38Z","snapshot_observed_at":"2026-08-20T01:40:11.341505Z","submitted_at":"2025-12-04T17:55:55Z","title":"The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-03T18:33:09.125847Z"},"links":{"cited_paper":"/paper/2505.07209","citing_paper":"/paper/2512.05038"},"observation_digest":"sha256:d583979838487d5fc73cadf8158fbc12856160af680c87aaf4c714f2d9b2576b","observation_id":"04974366-0115-44fe-9554-99f110885b9f","resolution":{"observed_at":"2026-08-03T18:33:09.125847Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2505.07209/citation-record","integrity":"/paper/2505.07209/integrity","json":"/paper/2505.07209/citation-record.json","paper":"/paper/2505.07209"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-16T09:25:53.087782Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-15T22:26:48.511367Z","title":"An image is worth 16x16 words: Trans- formers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.511367Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:eeb39de95726f2202befd621f9c6bc7f8e9ec3b61518dd6c4e23cd5079f0554b","observation_id":"eee37a5f-86ea-4266-af93-c16e674ec001","resolution":{"observed_at":"2026-08-15T22:26:48.511367Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.456435Z","title":"Interactive concept bottleneck models","venue":null,"work_id":"833fe8f6-be98-4ed0-939e-97c1306b7841","year":2023},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.516581Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:67cece708f7d079170dd973287338180ae603edd12b2bd9e9bb9d3950cbf5ad9","observation_id":"72a0fdbc-f715-4dd8-b769-0780701418e0","resolution":{"observed_at":"2026-08-15T22:26:49.461042Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.01253","last_updated":"2023-02-09T23:26:37Z","snapshot_observed_at":"2026-08-18T17:34:13.665750Z","submitted_at":"2022-10-03T22:21:07Z","title":"PLOT: Prompt Learning with Optimal Transport for Vision-Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.01253","snapshot_observed_at":"2026-08-15T22:26:48.521141Z","title":"Plot: Prompt learning with optimal transport for vision-language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.521141Z"},"links":{"cited_paper":"/paper/2210.01253","citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:f45122308baf939cb787c5715e89fed4634521fafb104267580c14faa4b99674","observation_id":"87ed5f87-e9e8-4668-a2e1-d8e49d043790","resolution":{"observed_at":"2026-08-15T22:26:48.521141Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.441914Z","title":"Graph optimal transport for cross-domain alignment","venue":null,"work_id":"634e9451-6d1d-4bee-bd42-78305030c110","year":2020},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.526499Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:60390f33e581cd23747bde9b353da086e01e923ea5a2a910e25c3ccc19980e60","observation_id":"7c6c56fa-c148-4213-bccb-20e21d7c8684","resolution":{"observed_at":"2026-08-15T22:26:49.446458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:26:48.531014Z","title":"Detect what you can: Detecting and representing objects using holistic mod- els and body parts","venue":null,"work_id":null,"year":1971},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.531014Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:5e5f09d911aeeb3fbb74f676d788f73c62221584cc2ec58bfdb68367e364648e","observation_id":"0381a0a6-471e-412b-aa07-693fdb119424","resolution":{"observed_at":"2026-08-15T22:26:48.531014Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.418048Z","title":"Interpretable machine learning: A guide for making black box models explainable","venue":null,"work_id":"2510eb62-a104-467c-9b81-7f54b674f936","year":2020},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.535646Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:45e64ed0ba0c3577ee08204902c320e8bb35842dba4956b04d5b8558467b9abe","observation_id":"3d8e719f-9cf2-4479-a7a7-cd81142cdfcb","resolution":{"observed_at":"2026-08-15T22:26:49.422785Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.403520Z","title":"Sinkhorn distances: Lightspeed computation of optimal transport","venue":null,"work_id":"585538a5-94c0-486d-ab9f-cff71f5de73a","year":2013},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.540573Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:84f7ea10dcb9d787d0cb150e1b46f22f932852ac8dbc0b942a7f27f089c75bfa","observation_id":"534bf46f-1055-400f-91e8-e9a6d829ef59","resolution":{"observed_at":"2026-08-15T22:26:49.408097Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.388691Z","title":"Decision trees","venue":null,"work_id":"3ac54356-1225-4725-aa5b-9bca2f3d8da5","year":2013},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.544836Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:ed2e02a095982f458b07d32f42b07cdbd319e6d540ee1e71695dab24cb19d26c","observation_id":"d23cf8a1-a7af-4eb2-8c9f-3482519d01f3","resolution":{"observed_at":"2026-08-15T22:26:49.393072Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:26:48.548997Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.548997Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:5c52dacb162773424613783da13b36fd9cd6e291ca84812a4488c4d3504927e8","observation_id":"a595433b-0364-41a3-91fe-e2ed22e87c0d","resolution":{"observed_at":"2026-08-15T22:26:48.548997Z","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":"2026-08-15T22:26:48.553562Z","title":"Concept embedding mod- els: Beyond the accuracy-explainability trade-off","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.553562Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:621564f4f9b694c1dd2005926ec989927695558247e0e865ec506d9fbb9acdfa","observation_id":"5c8c9299-b151-4e66-aeb6-7de4055027fd","resolution":{"observed_at":"2026-08-15T22:26:48.553562Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.356177Z","title":"Learning to receive help: Intervention-aware concept embedding models","venue":null,"work_id":"186d1869-9389-4ac9-a5ac-4eb166dea507","year":2024},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.558070Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:125d65514bf343b38086d17a3b757b149b828fd67a6ecaf35ab1446d9f7273fc","observation_id":"7cc5849c-dca3-4912-9e46-8c330fd480cc","resolution":{"observed_at":"2026-08-15T22:26:49.360985Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:26:48.562547Z","title":"Learning with a wasserstein loss","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.562547Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:e5471d588920aa8ec9654e443bca2fa04e1f32a4eaf95f818f96e0cd12702c82","observation_id":"c220ce56-da79-4cd9-9ba4-f6e6dd9505b3","resolution":{"observed_at":"2026-08-15T22:26:48.562547Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.332681Z","title":"Partimagenet: A large, high- quality dataset of parts","venue":null,"work_id":"ece88110-8ddb-4b06-aa79-4fe6864011d1","year":2022},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.566859Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:9df75f7d5828081cd03b7d2d8e9ea3ccb7dce6139864d7f1c81a07f64d529d39","observation_id":"4c97611a-70d2-45ad-a539-2b43d74e25ec","resolution":{"observed_at":"2026-08-15T22:26:49.337734Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.318136Z","title":"An empirical evaluation of the comprehensibility of decision table, tree and rule based predictive models","venue":null,"work_id":"f36461c6-ff15-48a1-84b0-4b49b1cdcf48","year":2011},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.571249Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:dfed47f9a7888f3f8621ace5cb6c974e19be23e25908a7295ad1e83dc9c4442a","observation_id":"ed90eb38-ce15-4035-b72a-33c0909de506","resolution":{"observed_at":"2026-08-15T22:26:49.322675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.303915Z","title":"Novel dataset for fine-grained image categorization","venue":null,"work_id":"e5df2ad7-302a-46bf-8bfc-48a8e7f070a7","year":2011},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.575523Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:9967c2b3cf44839e6cb02d6347843b72ad15546cff57f95e1da5578c018e494b","observation_id":"316a7b40-829c-416d-b048-475f246d5c35","resolution":{"observed_at":"2026-08-15T22:26:49.308761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:26:48.580013Z","title":"Segment any- thing","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.580013Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:ff1d0530c04e43be1ec94e47405403c535a0f25f796b11774affe0d0f32ac644","observation_id":"b97f774f-250b-4dc1-95e0-8e2bef64d568","resolution":{"observed_at":"2026-08-15T22:26:48.580013Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.281516Z","title":"Concept bottleneck models","venue":null,"work_id":"bbc3d3aa-2e0e-406b-8b05-1827d85906d5","year":2020},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.584211Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:d7e5bb0ba6ec0c45d6e3c553ec3edbf565fc952e4ba5ab4d2fe902a1f7b33291","observation_id":"fc13761c-397f-4ee7-9e11-33aa50f0482f","resolution":{"observed_at":"2026-08-15T22:26:49.285793Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.14726","last_updated":"2024-02-22T17:33:49Z","snapshot_observed_at":"2026-08-18T17:33:36.914329Z","submitted_at":"2024-02-22T17:33:49Z","title":"Incorporating Expert Rules into Neural Networks in the Framework of Concept-Based Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.14726","snapshot_observed_at":"2026-08-15T22:26:48.588488Z","title":"Incorporating ex- pert rules into neural networks in the framework of concept- based learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.588488Z"},"links":{"cited_paper":"/paper/2402.14726","citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:82225fe4c4d60bacc3e04cbeb7845bb8cf8fa45cc5394422a0f03844a5aa782f","observation_id":"e8d94d63-ea66-4e5e-a42a-c5ead4b56eef","resolution":{"observed_at":"2026-08-15T22:26:48.588488Z","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":"2026-08-15T22:26:48.593260Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.593260Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:a05d36445e34dd7533d07ccaa3074c12ea66975fc28bcf8b0031c905d2b833fb","observation_id":"158aa7aa-5f11-4baa-b521-977c7e25af89","resolution":{"observed_at":"2026-08-15T22:26:48.593260Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.258512Z","title":"Hierarchical optimal transport for multimodal distribution alignment","venue":null,"work_id":"ef572b9f-dc35-4796-bed3-c155fed98092","year":2019},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.597440Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:3c868dbefcb2001b7ef6a44c01098fa8fec22a91e784d081d35607cc03bd7a3c","observation_id":"912922b9-9156-48e7-b1c2-098c6134fbc9","resolution":{"observed_at":"2026-08-15T22:26:49.262853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.244257Z","title":"Patchct: Align- ing patch set and label set with conditional transport for multi-label image classification","venue":null,"work_id":"f588bae8-1279-43b0-be10-a906310b6f0e","year":2023},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.601593Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:60dff867fa1f6b52cad0f40afae2d2961df2cac29ddafa8bd9306a6c7cacddad","observation_id":"2cc9d82e-3912-4707-bf74-b86373a5a186","resolution":{"observed_at":"2026-08-15T22:26:49.249213Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.229186Z","title":"Deal: Disentan- gle and localize concept-level explanations for vlms","venue":null,"work_id":"08abcf9e-4a4a-40da-924a-a84866945b6d","year":2025},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.605760Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:0a7e667d8e3d3acf23570474472f063fa2cde83b3b6b7e9980cddb6ae2d3e6b7","observation_id":"08b1df82-b52a-45f0-8357-f3e44d7df1b5","resolution":{"observed_at":"2026-08-15T22:26:49.233903Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.16702","last_updated":"2024-01-30T03:03:26Z","snapshot_observed_at":"2026-08-18T17:29:43.069900Z","submitted_at":"2024-01-30T03:03:26Z","title":"Multi-granularity Correspondence Learning from Long-term Noisy Videos","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.16702","snapshot_observed_at":"2026-08-15T22:26:48.609927Z","title":"Multi-granularity correspondence learning from long-term noisy videos","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.609927Z"},"links":{"cited_paper":"/paper/2401.16702","citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:2f822fb14be28c3192f3189f022304b7ff707b6c7832a33d9349d1b0a964ab93","observation_id":"6f0f4545-9a17-41e2-8fca-1f9c657f9787","resolution":{"observed_at":"2026-08-15T22:26:48.609927Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.213740Z","title":"Mode: Clip data experts via clustering","venue":null,"work_id":"b95e00d2-0b27-4497-9198-6553b1cdd85b","year":2024},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.614781Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:41588f61c97ea32092955f3619133837aa2e92b82494cf26f8abb95c60e4cc1b","observation_id":"44c0be30-cc2c-4457-8c02-3e43455a47ce","resolution":{"observed_at":"2026-08-15T22:26:49.218545Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.199776Z","title":"Joint wasserstein autoencoders for aligning multi- modal embeddings","venue":null,"work_id":"c77f969c-00b6-4ccf-b755-8e6a44a94b61","year":2019},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.618913Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:0a18f57a559198187b388bcacbc1d700066970a494335ed6c1a1f6725c0521a7","observation_id":"89848d56-5d4b-40f4-8cb3-8dec50ef2ba0","resolution":{"observed_at":"2026-08-15T22:26:49.204310Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.04289","last_updated":"2021-05-10T12:00:52Z","snapshot_observed_at":"2026-08-18T17:29:09.178876Z","submitted_at":"2021-05-10T12:00:52Z","title":"Do Concept Bottleneck Models Learn as Intended?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.04289","snapshot_observed_at":"2026-08-15T22:26:48.623281Z","title":"Do concept bottleneck models learn as intended? arXiv preprint arXiv:2105.04289, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.623281Z"},"links":{"cited_paper":"/paper/2105.04289","citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:8b08ec7d38134a98b0bcbb504826d4bfee0184e0f477cde83526515cdcf5519f","observation_id":"07e86a38-793b-4887-b26a-94737aff4b36","resolution":{"observed_at":"2026-08-15T22:26:48.623281Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.185077Z","title":"[re] on the reproducibil- ity of post-hoc concept bottleneck models","venue":null,"work_id":"30e8f332-a7a8-4458-9917-787857259e67","year":null},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.628319Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:fe721e938a52aaa88c33a565721aa2d8adc2ebb5bf5cbdecbb630e5cebee0c3a","observation_id":"7dc08a2d-2817-4b4a-9825-24308ed947ef","resolution":{"observed_at":"2026-08-15T22:26:49.189743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.170507Z","title":"A comprehensive study of image classification model sensitivity to foregrounds, backgrounds, and visual attributes","venue":null,"work_id":"e95d5837-1906-4007-a5b3-155d10057451","year":2022},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.632570Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:c53ce080d9d32163432bb64b492cc2f5a474605412f5104fc58ba5faaa9ca6b9","observation_id":"7d470b91-865e-4911-aa9d-6696bd5f7c44","resolution":{"observed_at":"2026-08-15T22:26:49.175239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.155992Z","title":"Text2concept: Concept activation vectors di- rectly from text","venue":null,"work_id":"4f31bc41-752b-4388-a4d5-81db68049ecd","year":2023},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.636765Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:84cda683ef584730938090e6359905be1ece790c3ef05a97ff8252e03b9ddf02","observation_id":"51e46017-5258-43f3-b39a-0d7d5c13db8f","resolution":{"observed_at":"2026-08-15T22:26:49.160574Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.02419","last_updated":"2020-07-05T18:54:10Z","snapshot_observed_at":"2026-08-18T23:37:31.270386Z","submitted_at":"2020-07-05T18:54:10Z","title":"Attention-based Joint Detection of Object and Semantic Part","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.02419","snapshot_observed_at":"2026-08-15T22:26:48.641056Z","title":"Attention- based joint detection of object and semantic part","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.641056Z"},"links":{"cited_paper":"/paper/2007.02419","citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:cba22ae4d140d3d6ce96e29092cdb1a3d8db2d535b69aaafa602e99ec6e81340","observation_id":"82d9ca40-f113-4f9b-aef1-02cdf97cca54","resolution":{"observed_at":"2026-08-15T22:26:48.641056Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06129","last_updated":"2023-06-05T17:33:43Z","snapshot_observed_at":"2026-08-18T17:14:12.197904Z","submitted_at":"2023-04-12T19:27:09Z","title":"Label-Free Concept Bottleneck Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06129","snapshot_observed_at":"2026-08-15T22:26:48.645604Z","title":"Label-free concept bottleneck models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.645604Z"},"links":{"cited_paper":"/paper/2304.06129","citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:2af098f75d27e330b3a6b8d894f368557c8c7f552c7ba47a1819d4bf5204e682","observation_id":"ba25ccf0-834b-4f30-935e-eaae06c00bd4","resolution":{"observed_at":"2026-08-15T22:26:48.645604Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07193","last_updated":"2024-02-02T10:24:09Z","snapshot_observed_at":"2026-08-17T13:03:40.359628Z","submitted_at":"2023-04-14T15:12:19Z","title":"DINOv2: Learning Robust Visual Features without Supervision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07193","snapshot_observed_at":"2026-08-15T22:26:48.649890Z","title":"Dinov2: Learning robust visual features without supervision","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.649890Z"},"links":{"cited_paper":"/paper/2304.07193","citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:761fa61d616569a933f1e466c4322a2e75551aae62f387589c5bc30d262927dd","observation_id":"c95f525a-4e73-4bdd-90da-7025e6d2b785","resolution":{"observed_at":"2026-08-15T22:26:48.649890Z","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":"2026-08-15T22:26:48.654172Z","title":"Learning transferable visual models from natural language supervi- sion","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.654172Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:8ed3d08621e5921258f14168c53263216420c6b05d2f2f1dbbca59ad208e9138","observation_id":"cc03f435-58dc-45b7-82fe-55241cfa8501","resolution":{"observed_at":"2026-08-15T22:26:48.654172Z","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":"2026-08-15T22:26:48.658409Z","title":"Do vision trans- formers see like convolutional neural networks? Advances in neural information processing systems, 34:12116–12128,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.658409Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:b7b4e3cb292ed9bea2d8abd235ab82e83fe710f89e499268bccaa6d8d6461672","observation_id":"b7839590-1c02-4989-bf04-ccaa29ccac3f","resolution":{"observed_at":"2026-08-15T22:26:48.658409Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.123790Z","title":"Do concept bottleneck models obey locality? In XAI in Action: Past, Present, and Future Applications ,","venue":null,"work_id":"205577d3-8381-4eb1-b9ed-cf19a002442d","year":null},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.663105Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:ad66575e2345f2e1879812b2341b00bc9826ba2445f7ba2c7f914e82570a3fc1","observation_id":"756d3f66-46f0-4383-bf8c-2d3f7151345b","resolution":{"observed_at":"2026-08-15T22:26:49.128738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.109387Z","title":"Optimal transport for multi-source domain adaptation under target shift","venue":null,"work_id":"fff1ac05-3b6b-478a-8081-0f79fedf3195","year":null},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.667835Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:92a6ab95a66985a95945761850485057e3657d68c94a29be081f1c6c799fa412","observation_id":"ca2d2c85-9141-43fe-b4f5-34bb94408f7d","resolution":{"observed_at":"2026-08-15T22:26:49.113948Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:26:48.672132Z","title":"Grad-cam: Visual explanations from deep networks via gradient-based localization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.672132Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:98dc7869c8c074f7e031211e6965419a6baf375a1d95b39e153aa2d04d9a5f32","observation_id":"6141e6fa-7e53-4468-82c8-86385d2284e2","resolution":{"observed_at":"2026-08-15T22:26:48.672132Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.03323","last_updated":"2024-04-04T09:43:43Z","snapshot_observed_at":"2026-08-18T17:14:38.584632Z","submitted_at":"2024-04-04T09:43:43Z","title":"Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.03323","snapshot_observed_at":"2026-08-15T22:26:48.676447Z","title":"Sparse concept bottleneck mod- els: Gumbel tricks in contrastive learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.676447Z"},"links":{"cited_paper":"/paper/2404.03323","citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:eda44bf6c8f19f4dc329700e34cb8e1e65f3a025c7dd299e29aa02368593795e","observation_id":"40f7363f-50d2-49fe-bf24-ef3e21e0dcca","resolution":{"observed_at":"2026-08-15T22:26:48.676447Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.085491Z","title":"Auxiliary losses for learning generalizable concept-based models","venue":null,"work_id":"5a4c5e75-7845-4ef7-9574-7dc4fc017778","year":2024},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.680791Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:a4c76aa65aea5d5161624df81db1512e83e7829f69dd60a26d669b19063ed122","observation_id":"fa9a89c9-9c50-47f3-9ee7-95c656be9807","resolution":{"observed_at":"2026-08-15T22:26:49.090072Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.071185Z","title":"A closer look at the intervention procedure of concept bot- tleneck models","venue":null,"work_id":"ef624e6e-af5d-4cd2-9690-1615b2da3dc6","year":2023},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.684851Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:e80be304f42f103646e3e542d8b23c393678c50a875167aa9d1f0d6509f2bd85","observation_id":"f87998e7-dac1-40f3-ba84-067152e4ab3c","resolution":{"observed_at":"2026-08-15T22:26:49.075805Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.057045Z","title":"The caltech-ucsd birds-200-2011 dataset","venue":null,"work_id":"f7fe067c-b7d3-4481-93f8-4af009332840","year":2011},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.688958Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:0b72bb406389edfb4ae6c3a2d4c757560b2a345b08cd55d02e0420d8918d0376","observation_id":"fe02ca7a-d6c6-4835-b4cb-388d202ea55a","resolution":{"observed_at":"2026-08-15T22:26:49.061761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.01776","last_updated":"2025-05-20T02:32:33Z","snapshot_observed_at":"2026-08-18T17:14:36.293568Z","submitted_at":"2025-03-03T17:59:48Z","title":"Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.01776","snapshot_observed_at":"2026-08-15T22:26:48.693139Z","title":"Beyond matryoshka: Revisit- ing sparse coding for adaptive representation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.693139Z"},"links":{"cited_paper":"/paper/2503.01776","citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:6a7c4f373f77f8dbd95eac402e990abb115563240e194d91a68fd3bf34e7e81b","observation_id":"610b952f-3507-4273-aca7-296ebedaa541","resolution":{"observed_at":"2026-08-15T22:26:48.693139Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.042510Z","title":"Zero-shot learning—a comprehensive eval- uation of the good, the bad and the ugly","venue":null,"work_id":"72b0db2f-4800-4872-a1a1-dd43d77d4c94","year":2018},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.697981Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:bbf5350d08693edfce122d33eb8a7ea1131306259d48f8d93fabe4f86e132f78","observation_id":"20aed098-ab8f-4b8e-8dbb-eaeb808c140a","resolution":{"observed_at":"2026-08-15T22:26:49.047328Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:26:48.702157Z","title":"Attribute prototype network for zero-shot learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.702157Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:e43a36198ef903713b3fe6eff4a998254c547c0c95bf56bf5ba345efaffe4858","observation_id":"1ec7eb32-97d5-4561-8b08-e943956c87de","resolution":{"observed_at":"2026-08-15T22:26:48.702157Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.016519Z","title":"Language in a bottle: Language model guided concept bottlenecks for interpretable image classification","venue":null,"work_id":"fcf9fc89-d1a7-4d5e-bdb8-fcc16a6e3809","year":2023},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.706302Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:9cbe96533cff12ef9e278a6d2fad49bc2a47f54dc628feb32ffaeeb7a1808d2c","observation_id":"193f19f7-5e79-40b0-8098-ce8d02c04f50","resolution":{"observed_at":"2026-08-15T22:26:49.021436Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.15480","last_updated":"2023-02-01T22:26:15Z","snapshot_observed_at":"2026-08-18T17:31:25.939959Z","submitted_at":"2022-05-31T00:29:26Z","title":"Post-hoc Concept Bottleneck Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.15480","snapshot_observed_at":"2026-08-15T22:26:48.710577Z","title":"Post-hoc concept bottleneck models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.710577Z"},"links":{"cited_paper":"/paper/2205.15480","citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:00b26bbbe0a79fd43fd124883d06a626f9e84e384b5b66d725c2dd2b22367955","observation_id":"3d6e8304-cafa-4da8-9736-0b70a91ced40","resolution":{"observed_at":"2026-08-15T22:26:48.710577Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.12652","last_updated":"2025-01-13T21:59:56Z","snapshot_observed_at":"2026-08-18T17:14:37.489161Z","submitted_at":"2024-04-19T06:41:32Z","title":"Pre-trained Vision-Language Models Learn Discoverable Visual Concepts","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.12652","snapshot_observed_at":"2026-08-15T22:26:48.715544Z","title":"Pre-trained vision-language models learn discoverable visual concepts","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.715544Z"},"links":{"cited_paper":"/paper/2404.12652","citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:e7b7d076831e74528388f392b25273d77519ee9f485624a0cafa1f9b56474e47","observation_id":"f91494a2-e1cb-4a1b-b322-717f1e586f27","resolution":{"observed_at":"2026-08-15T22:26:48.715544Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.09056","last_updated":"2022-12-05T22:29:46Z","snapshot_observed_at":"2026-08-18T17:35:29.399130Z","submitted_at":"2022-09-19T14:49:36Z","title":"Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.09056","snapshot_observed_at":"2026-08-15T22:26:48.720019Z","title":"Concept embedding models: Beyond the accuracy-explainability trade-off","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.720019Z"},"links":{"cited_paper":"/paper/2209.09056","citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:0fae83828db0fa73df207e6af9cd6284239626a300428265641860d958e240d5","observation_id":"f12b70f3-9109-4379-abc5-582decd690e9","resolution":{"observed_at":"2026-08-15T22:26:48.720019Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:49.000954Z","title":"Conzic: Controllable zero-shot image captioning by sampling-based polishing","venue":null,"work_id":"f16499a0-6d3f-4a92-a84b-c85976604b7c","year":2023},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.724478Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:f68ac3824bf2711da167ca661c8c811f2017ab8ced5133704398a760af1e68c8","observation_id":"de938dcf-d837-48fd-ab33-5e75e9d0b7d7","resolution":{"observed_at":"2026-08-15T22:26:49.006379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:48.985652Z","title":"Meacap: Memory-augmented zero- shot image captioning","venue":null,"work_id":"a885cf80-47ba-450a-aff9-5ed65a5bff90","year":2024},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.728601Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:7c5d9177e53b48099178f302d1d96ed8e6d9524c8ef429c9c97bb29e2b6ba924","observation_id":"1921e50a-bc34-4a31-bf41-de4bfdc13c28","resolution":{"observed_at":"2026-08-15T22:26:48.990928Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:48.970521Z","title":"Spda-cnn: Unifying semantic part detection and abstraction for fine-grained recognition","venue":null,"work_id":"fa269ddf-ab86-4c67-aba7-6c409424303f","year":2016},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.733083Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:03e0c6f3a2c55fad701c38f5862c373b56fcd366716a0549e9e7337f4721bddc","observation_id":"6b26975c-755b-415f-95a1-2ede30390d14","resolution":{"observed_at":"2026-08-15T22:26:48.975265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:26:48.953787Z","title":"Label distribution learning by optimal transport","venue":null,"work_id":"00d00c90-7ac3-4f14-95a4-afca3d7b57d4","year":2018},"citing_paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T22:26:48.737161Z"},"links":{"citing_paper":"/paper/2505.07209"},"observation_digest":"sha256:79ca4f41c77b7f35f2ba00b84c58f83d667dd3e8f19e0482e89caab333f40829","observation_id":"dd9d49a7-f5a8-48e3-a14c-4ea687817366","resolution":{"observed_at":"2026-08-15T22:26:48.960199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.07209","last_updated":"2025-05-12T03:31:57Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-20T20:26:23.357931Z","submitted_at":"2025-05-12T03:31:57Z","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models"},"reference_resolution":{"displayed":52,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":23,"verified_exact":0,"verified_fuzzy":29},"total_outbound_references":52},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 1 inbound Pith citation observation for arXiv:2505.07209."}