{"as_of":"2026-08-08T04:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8d02e6f0c7bb509d0b7d985301104584983259ed7e687d6ebd6892dafa4c0c59","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":"2026-08-07T14:46:47.750597Z","state":"measured"},{"denominator":52,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":52,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2505.17666/citation-record","integrity":"/paper/2505.17666/integrity","json":"/paper/2505.17666/citation-record.json","paper":"/paper/2505.17666"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:46:54.968452Z","title":"Multi-view convolutional neural networks for 3d shape recognition","venue":null,"work_id":"74e781af-bd27-41d2-bb00-0438855bf16b","year":2015},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:42.238372Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:39455f27131adf98f2bf1095ca7cdd5672e47ec02a6bbffc6d01a70ccd37a156","observation_id":"64817a0e-75ad-4647-afaa-5ac27cde6772","resolution":{"observed_at":"2026-08-07T14:46:55.108343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:54.822856Z","title":"Gvcnn: Group-view convolutional neural networks for 3d shape recognition","venue":null,"work_id":"3b5ee734-61f2-4141-855e-34d24757f107","year":2018},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:42.394881Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:d836184f099f53ada42eb31d90b86653e529487da9430a48b4fe2bbb4d39e6b2","observation_id":"1a753005-dfcf-43a3-b55a-03af1aafa69a","resolution":{"observed_at":"2026-08-07T14:46:54.875021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:54.697717Z","title":"A deeper look at 3d shape classifiers","venue":null,"work_id":"f3259957-1de2-42d0-9618-c90f568b5f9c","year":2018},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:42.486480Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:a66425b9cfc1627ba9c784d15d4d16522c7ead8bd0b777fbc2482902a6fc96fc","observation_id":"4051b8ef-4e17-454d-973d-f7b155335020","resolution":{"observed_at":"2026-08-07T14:46:54.745548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:54.569209Z","title":"3d2seqviews: Aggregating sequential views for 3d global feature learning by cnn with hierarchical attention aggregation.IEEE Transactions on Image Processing, 28(8):3986–3999, 2019","venue":null,"work_id":"0a412df9-3396-41ac-95d8-bdd5dce1d54e","year":2019},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:42.562559Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:31c4a2a4528e59bb9450abe68dbfd4f730362d751c042a0653f53b60ee8bd3d2","observation_id":"37ffb56f-3415-49ee-ac94-6aa81f42173f","resolution":{"observed_at":"2026-08-07T14:46:54.632438Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:54.444442Z","title":"End-to-end learning local multi-view descriptors for 3d point clouds","venue":null,"work_id":"24a1e2ff-c014-4148-85ca-c5d2a3852171","year":1919},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:42.641842Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:06d68553272f19f28a9c47768eddb58a59b1876f66b0fdef38f54441ab57f4bb","observation_id":"0afea19f-0d80-4305-bd38-976e42a23816","resolution":{"observed_at":"2026-08-07T14:46:54.499126Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:54.335064Z","title":"Veram: View-enhanced recurrent attention model for 3d shape classification.IEEE transactions on visualization and computer graphics, 25(12):3244–3257, 2018","venue":null,"work_id":"a6844fdb-8734-4cdb-9964-786c7d3bf1ef","year":2018},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:42.757826Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:36473b3b4bbce5cc4775f7a9284e8b4c23e26b53f5298a2ad29af6110a17165e","observation_id":"69b70615-73aa-41ca-82ef-0efa8ed58c7e","resolution":{"observed_at":"2026-08-07T14:46:54.386708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:54.179768Z","title":"Seqviews2seqlabels: Learning 3d global features via aggregating sequential views by rnn with attention.IEEE Transactions on Image Processing, 28(2):658–672, 2018","venue":null,"work_id":"cbe608e3-701f-4caa-870c-3133b294ea03","year":2018},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:42.850903Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:3f06ae33f6cc6d41a2fa96657e288ba65d516135491c659acffee18007a25c00","observation_id":"9e51a08b-18ea-46fb-b135-7977fbf36260","resolution":{"observed_at":"2026-08-07T14:46:54.242711Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:54.042979Z","title":"Mlvcnn: Multi-loop-view convolutional neural network for 3d shape retrieval","venue":null,"work_id":"e603aea6-46d1-4972-8956-29a7215d8888","year":2019},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:42.949125Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:5d3488b1e5687edce2a92de268dd362b4495d1f63e79ddbaffc66873b8627c86","observation_id":"58a72475-17a2-4547-a922-0513fb85a379","resolution":{"observed_at":"2026-08-07T14:46:54.107168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:53.873357Z","title":"View-gcn: View-based graph convolutional network for 3d shape analysis","venue":null,"work_id":"ce0fbb17-3fbe-45da-a4b0-2bb31e0cdd08","year":2020},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:43.030102Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:b72bcf928f872f1f2454aab17ba4d34aa1cae89c848f07acd3d12a78b7004646","observation_id":"c6fffec2-be09-4fe3-9a30-8bed89112ae7","resolution":{"observed_at":"2026-08-07T14:46:53.957806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:53.702342Z","title":"Learning canonical view representation for 3d shape recognition with arbitrary views","venue":null,"work_id":"cb4d0058-b67c-4068-a5d7-d3725a837e9e","year":2021},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:43.099733Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:ec5c010877d9cf267633b2719fe83d2d7206a42bab52bb12a685935f12df538a","observation_id":"9ac79f6c-d82f-419b-8d9b-dd0a41192ba3","resolution":{"observed_at":"2026-08-07T14:46:53.779470Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:53.513297Z","title":"Mvt: Multi-view vision transformer for 3d object recognition","venue":null,"work_id":"7e7db5e2-fd29-4ebf-9902-fe7623fc8b9c","year":2021},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:43.162231Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:a0bb0f0aaf2cc1f45933e3ec70de5be04ee12f8a0dc63a32bfc5af1c487ffa5f","observation_id":"296cdf14-52e3-4fdc-8340-d7b8767a5d53","resolution":{"observed_at":"2026-08-07T14:46:53.616511Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:53.355543Z","title":"Vsformer: Mining correlations in flexible view set for multi-view 3d shape understanding.IEEE Transactions on Visualization and Computer Graphics, 2024","venue":null,"work_id":"cb2bc328-e6fb-4a6d-a1b6-f8c36254a367","year":2024},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:43.261041Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:a7c12d81a206444e0818fac5818907709945889cf93d8fb66aad7051ef8a7139","observation_id":"e4416bde-a6b3-46fc-9472-026001a3d0eb","resolution":{"observed_at":"2026-08-07T14:46:53.431684Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:53.214892Z","title":"Group multi-view transformer for 3d shape analysis with spatial encoding.IEEE Transactions on Multimedia, 2024","venue":null,"work_id":"3ca79694-6729-4299-8519-b90ada86041a","year":2024},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:43.391248Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:1d2e25b404304ad626ba359d8163e7d3d3df2044a610bc5840471a845a0b9e43","observation_id":"b88e30ae-9e0e-4762-a5e4-a5b112914a0d","resolution":{"observed_at":"2026-08-07T14:46:53.289184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6034","last_updated":"2014-04-19T11:54:52Z","snapshot_observed_at":"2026-07-06T03:31:30.452356Z","submitted_at":"2013-12-20T16:45:54Z","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6034","snapshot_observed_at":"2026-08-07T14:46:43.513235Z","title":"Deep inside convolutional networks: Visualising image classification models and saliency maps.arXiv preprint arXiv:1312.6034, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:43.513235Z"},"links":{"cited_paper":"/paper/1312.6034","citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:747abbb7094614454f4af0b83c2569549a03eb9942ceb329152846636ff5a8ab","observation_id":"02c31e9f-5f09-440f-b2f9-de216095c1d6","resolution":{"observed_at":"2026-08-07T14:46:43.513235Z","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":"2026-08-07T14:46:53.064133Z","title":"Synthesizing the preferred inputs for neurons in neural networks via deep generator networks.Advances in neural information processing systems, 29, 2016","venue":null,"work_id":"3a01aa14-7656-435f-ab01-0cdab0d5fd91","year":2016},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:43.685441Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:d23340fab5be3f07dcf85848913caa822302f372f6a2fa2c4bd6de6e4c620e4d","observation_id":"12680bb6-3b41-4db2-918a-da0a69435a4d","resolution":{"observed_at":"2026-08-07T14:46:53.129499Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:52.899273Z","title":"Activation atlas.Distill, 4(3):e15, 2019","venue":null,"work_id":"35dd7f0c-1358-4a2d-aed7-c21f14eea50a","year":2019},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:43.777139Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:813f7f6e6870eb24f7b7cef6fcee70e0317f7d2530ee2291dcb28305d2d3bfd1","observation_id":"cb236217-fff0-4318-b97a-4241e4876437","resolution":{"observed_at":"2026-08-07T14:46:53.012487Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:52.701598Z","title":"Hmtn: Hierarchical multi-scale transformer network for 3d shape recognition","venue":null,"work_id":"5d5b87e3-dbe0-4a0e-9824-e0dca565a9bf","year":2022},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:43.850247Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:32c5ad8928ddbc91d1e588ae57810c04b84d0f914db478e5db285ae574240416","observation_id":"a3efec01-c626-4e13-a0db-7d233b970560","resolution":{"observed_at":"2026-08-07T14:46:52.799567Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:52.508975Z","title":"Mhsan: Multi-view hierarchical self-attention network for 3d shape recognition.Pattern Recognition, 150:110315, 2024","venue":null,"work_id":"158638f2-ffe9-469e-ac72-52a644db3e35","year":2024},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:43.924040Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:bd5bae6d8640cefff14fd260e684343dcc2dcdb9406332270a4c33809cbb9732","observation_id":"9c1605bd-1552-4a28-8caa-5278ef1da939","resolution":{"observed_at":"2026-08-07T14:46:52.613662Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:52.303481Z","title":"Fine-grained 3d shape classification with hierarchical part-view attention.IEEE Transactions on Image Processing, 30:1744–1758, 2021","venue":null,"work_id":"0347e7c6-717c-4c1c-9e23-c14ac2185060","year":2021},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:44.031615Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:1a9b826660d7d375f869a9f72901380d117b8f6f4582669ddd5dcb170823b6b6","observation_id":"9ba0f506-03de-4d2c-9874-445b58f0e389","resolution":{"observed_at":"2026-08-07T14:46:52.403075Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:44.123047Z","title":"Steps toward artificial intelligence.Proceedings of the IRE, 49(1):8–30, 1961","venue":null,"work_id":null,"year":1961},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:44.123047Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:dbada88b8bc6e7e7331bb8f409a0f7a1956d2144c17409355cfa0f5cbbb056b3","observation_id":"897af508-5c4a-444c-b93a-07f7811fb667","resolution":{"observed_at":"2026-08-07T14:46:44.123047Z","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":"2026-08-07T14:46:52.131073Z","title":"Human problem solving.Upper Saddle River/Prentive Hall, 1972","venue":null,"work_id":"ab60df4b-9dbd-4e96-bdd2-9c10c1befc3d","year":1972},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:44.222624Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:b441227f6d31e8d22ea8e5917ddc00bbd0dc7d37c3836b68e237577154dd3816","observation_id":"594a81e0-0220-4ed4-8551-b29adfd4322a","resolution":{"observed_at":"2026-08-07T14:46:52.190731Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:44.317097Z","title":"Matching categorical object representations in inferior temporal cortex of man and monkey.Neuron, 60(6):1126–1141, 2008","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:44.317097Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:9e6173477930c6b020c8231a02d5096efb2a8224f7bd64aabfe369d104cb7586","observation_id":"d788c053-a73c-4ad4-b345-4f303ad90b8d","resolution":{"observed_at":"2026-08-07T14:46:44.317097Z","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":"2026-08-07T14:46:51.948696Z","title":"Improving generalization via scalable neighborhood component analysis","venue":null,"work_id":"c4c3db0f-9d26-417f-9197-e727d13c368b","year":2018},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:44.430887Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:e2e2c94416b3acaccd76feba77bc41e5161ac87d40c0449b80ff51ed1d1df44a","observation_id":"13a01cc7-7dce-4f52-adcb-4e01aca8c6b8","resolution":{"observed_at":"2026-08-07T14:46:52.021786Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:51.743819Z","title":"Robust classification with convolutional prototype learning","venue":null,"work_id":"3663810d-43a5-40c8-aaea-389d37cb466a","year":2018},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:44.520275Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:3052eb58da6ec817431552a38f3f77b3c6e32c82323f63c7a724d5a2bf2f7498","observation_id":"8400473a-40c2-4a26-b0f5-35f4e1a00472","resolution":{"observed_at":"2026-08-07T14:46:51.857585Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.07383","last_updated":"2023-03-14T16:15:21Z","snapshot_observed_at":"2026-07-06T13:52:39.607638Z","submitted_at":"2022-09-15T15:47:31Z","title":"Visual Recognition with Deep Nearest Centroids","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.07383","snapshot_observed_at":"2026-08-07T14:46:44.587065Z","title":"Visual recognition with deep nearest centroids","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:44.587065Z"},"links":{"cited_paper":"/paper/2209.07383","citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:815569c1bea27a582a33a64e1d02d1280823a3d1485cba77462de4874186c9d7","observation_id":"23b0dfdc-cc2a-430e-abf7-9836c202f28b","resolution":{"observed_at":"2026-08-07T14:46:44.587065Z","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":"2026-08-07T14:46:51.532748Z","title":"Prototypical networks for few-shot learning.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":"71ee142b-9dbb-491b-8853-c4c0af8f7ee1","year":2017},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:44.702699Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:5be3121d935df9c286d1b4946e53e45d379365144734794544ee0cad6ed51e32","observation_id":"6e381832-3063-4b94-bcb4-3504c8e8949e","resolution":{"observed_at":"2026-08-07T14:46:51.642270Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:51.353945Z","title":"Hyperspherical prototype networks.Advances in neural information processing systems, 32, 2019","venue":null,"work_id":"6cb83285-f3a2-402f-9e50-fe5ae9d3e35c","year":2019},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:44.786553Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:ef8c5a48cc2b242ba3ff3a4203de06c380648d1c04c7d33cb6acd74c967f7855","observation_id":"ea69e600-f616-48a6-be75-ef174e7e93c7","resolution":{"observed_at":"2026-08-07T14:46:51.446811Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:51.099435Z","title":null,"venue":null,"work_id":"e2f1980e-6545-4109-bc7b-7fae1032d1db","year":2020},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:44.885358Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:6fd8140ceb5dd02f7656a56c1aa7a6116f48192f3026df40cd2e0badffa4791e","observation_id":"5fd4c346-830e-45cd-b030-89efbb42f4ef","resolution":{"observed_at":"2026-08-07T14:46:51.223746Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1512.01192","last_updated":"2018-04-25T13:40:35Z","snapshot_observed_at":"2026-07-06T04:38:41.080265Z","submitted_at":"2015-12-03T19:06:16Z","title":"Prototypical Priors: From Improving Classification to Zero-Shot Learning","version":2},"cited_work":{"arxiv_id":"1512.01192","doi":null,"metadata_source":"pith","pith_arxiv_id":"1512.01192","snapshot_observed_at":"2026-08-07T14:46:47.901946Z","title":"Prototypical Priors: From Improving Classification to Zero-Shot Learning","venue":"cs.CV","work_id":"1c2903e8-b958-46b1-976c-b438c4de6044","year":2015},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:45.006216Z"},"links":{"cited_paper":"/paper/1512.01192","citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:eaba0b762b9785783226e01a65ae01ce7647fa8758b58d2e6634006803856080","observation_id":"13c0ea09-8e60-40aa-8a54-ffcf56091935","resolution":{"observed_at":"2026-08-07T14:46:48.019015Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:50.912386Z","title":"Attribute prototype network for zero-shot learning.Advances in Neural Information Processing Systems, 33:21969–21980, 2020","venue":null,"work_id":"aff4ad54-9acb-4cd7-a8ee-fe05ab8d9c4b","year":2020},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:45.135277Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:88cd0b21bf9e618625b31302926ca194861a99a5805a43bd987ddc10a60e6cf8","observation_id":"ebf2801b-6772-4705-bb0c-2379f25da26c","resolution":{"observed_at":"2026-08-07T14:46:51.004974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:50.754919Z","title":"Panet: Few-shot image semantic segmentation with prototype alignment","venue":null,"work_id":"cd501c90-73be-4036-a3d4-dce1c38718d0","year":2019},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:45.279739Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:b2ae505cf2af8e2eda453165b5fa847ec5a0130f647761ade2cedc53057fe5b1","observation_id":"31976784-89a9-4f47-96be-0d87757d844c","resolution":{"observed_at":"2026-08-07T14:46:50.822973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:50.605680Z","title":"Adaptive prototype learning and allocation for few-shot segmentation","venue":null,"work_id":"2d3cfca2-31e7-44f2-9e05-d1f3b5b6aa7f","year":2021},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:45.463700Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:f05839bf343a81b35963f5f56786f9a65f2456c86c415e6b88bda550abf27cbc","observation_id":"9661c2d4-3aeb-494e-bdff-d849bdc22748","resolution":{"observed_at":"2026-08-07T14:46:50.674604Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:50.404004Z","title":"Clustering based point cloud represen- tation learning for 3d analysis","venue":null,"work_id":"12a43b09-4642-409a-a798-dc5e45dc9204","year":2023},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:45.575523Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:370a4749f3567c790a1fe4e185978e220cf603c7dbb4354ad16cf028512ab6ff","observation_id":"24dd4d3d-83aa-4c54-8523-4e313da16d76","resolution":{"observed_at":"2026-08-07T14:46:50.499402Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:50.202444Z","title":"Prototype-based semantic segmentation.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024","venue":null,"work_id":"9eb1355a-1a95-41db-ba49-ac80bb74ba35","year":2024},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:45.724662Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:50df550f76a5b32093d289ae3b46c83b968bb6e7bb76685057eeeec50925d2a3","observation_id":"8d855425-3591-4415-a60f-d6474bc739af","resolution":{"observed_at":"2026-08-07T14:46:50.277909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:45.903407Z","title":"Unsupervised feature learning via non-parametric instance discrimination","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:45.903407Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:9395b929a5e221e4ec5c149dfd4e6ff4a2f9280a5f598cb916495b8ee05eab24","observation_id":"4fdfba4d-25c9-4e6f-b744-10ad5f1f1874","resolution":{"observed_at":"2026-08-07T14:46:45.903407Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.04966","last_updated":"2021-03-30T04:07:54Z","snapshot_observed_at":"2026-07-06T09:19:17.009625Z","submitted_at":"2020-05-11T09:53:36Z","title":"Prototypical Contrastive Learning of Unsupervised Representations","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.04966","snapshot_observed_at":"2026-08-07T14:46:46.081622Z","title":"Prototypical contrastive learning of unsupervised representations.arXiv preprint arXiv:2005.04966, 2020","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:46.081622Z"},"links":{"cited_paper":"/paper/2005.04966","citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:1f10396e7d9104c711418d703e8ed81afa61ad6f2b1df3a6c996cbfd5d579589","observation_id":"59427fb1-cc98-4a1a-b525-5d490985e10b","resolution":{"observed_at":"2026-08-07T14:46:46.081622Z","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":"2026-08-07T14:46:50.009944Z","title":"Augmentation invariant and instance spreading feature for softmax embedding.IEEE transactions on pattern analysis and machine intelligence, 44(2):924–939, 2020","venue":null,"work_id":"9f2f512f-6469-4696-b284-7d3b4289a07d","year":2020},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:46.256433Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:7097d784e76f96219fa382608e16148e51cddcc906b549ff8d86212133fcfab6","observation_id":"6fd84abb-f129-4fed-af42-401fbbf85108","resolution":{"observed_at":"2026-08-07T14:46:50.103082Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:49.780593Z","title":"Deep learning for case-based reasoning through prototypes: A neural network that explains its predictions","venue":null,"work_id":"2a0458bf-76ca-4bb8-9038-62a8de04ec7e","year":2018},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:46.374273Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:c55befe31088bd3aa95500ac454fd4832e070c76ad14da97d8aa649b632aee29","observation_id":"1fee2e39-d766-4d61-9454-132168f2fa6c","resolution":{"observed_at":"2026-08-07T14:46:49.890762Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:49.517598Z","title":"Interpretable3d: An ad-hoc interpretable classifier for 3d point clouds","venue":null,"work_id":"01daaee9-d246-4a76-a117-3dd9f6d0b154","year":2024},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:46.498966Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:cdc26913f7691d5cc70d2b0d57aaee52f2b5d0e17306df3f74dfdb7ca5e959bb","observation_id":"eabfbe99-7940-49cf-baef-2ab7124b9a8d","resolution":{"observed_at":"2026-08-07T14:46:49.642637Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:46.614266Z","title":"Learning deep features for discriminative localization","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:46.614266Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:641139b8740507f15d04dca23ed327e552454810322ef0e8f10646a3c5f969cc","observation_id":"cb78c39f-91f7-44d1-b5fa-cd721c3477d5","resolution":{"observed_at":"2026-08-07T14:46:46.614266Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.07450","last_updated":"2017-01-25T16:33:29Z","snapshot_observed_at":"2026-08-07T01:29:08.076157Z","submitted_at":"2016-11-22T18:34:36Z","title":"Grad-CAM: Why did you say that?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.07450","snapshot_observed_at":"2026-08-07T14:46:46.719029Z","title":"Grad-cam: Why did you say that?arXiv preprint arXiv:1611.07450, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:46.719029Z"},"links":{"cited_paper":"/paper/1611.07450","citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:fb8d7d51aca9b5fa5293810c7654d8b5d4350a9818235006415aa7f1f8aefdf9","observation_id":"f1a65098-1e24-42a9-bfda-9dc31ef84aee","resolution":{"observed_at":"2026-08-07T14:46:46.719029Z","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":"2026-08-07T14:46:46.800511Z","title":"Transformer interpretability beyond attention visualization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:46.800511Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:843dd97ff1b70894e459601fd3eb10024e510cc013c8ae2224faf38c1759647a","observation_id":"aed1b878-5b52-4f51-9b81-61c2da228d45","resolution":{"observed_at":"2026-08-07T14:46:46.800511Z","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":"2026-08-07T14:46:46.888366Z","title":"Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study.PLoS medicine, 15(11):e1002683, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:46.888366Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:7342c7c17e0162fb7b6e42afa51ebc320906e52d9b35c6cba8503545c0f922b6","observation_id":"1ead808d-a4f0-46da-9229-924a31784a47","resolution":{"observed_at":"2026-08-07T14:46:46.888366Z","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":"2026-08-07T14:46:49.301206Z","title":"Dan: Deep-attention network for 3d shape recognition.IEEE Transactions on Image Processing, 30:4371–4383, 2021","venue":null,"work_id":"9363dd85-647b-43ec-a298-d4b9e69e0491","year":2021},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:46.991359Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:d4589320e7958268858a791707340437a593ed49604cb521a95ea98259abf8eb","observation_id":"4780aee9-981d-4e36-b55f-8ecfce4bd1fd","resolution":{"observed_at":"2026-08-07T14:46:49.416459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:49.119088Z","title":"Multi-view classification using hybrid fusion and mutual distillation","venue":null,"work_id":"6f41e3b3-8b55-4996-8c6d-62cc051af061","year":2024},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:47.050045Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:0045a26e4227852cc50673fa6fc1ab0e3d89e52b9e3317b5b3e72ab213e125c2","observation_id":"cb8edc03-3585-4cca-8f5f-594cf9b77b28","resolution":{"observed_at":"2026-08-07T14:46:49.194797Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:47.117662Z","title":"This looks like that: deep learning for interpretable image recognition.Advances in neural information processing systems, 32, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:47.117662Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:d2d9723552321e5312e18821229795221882ee8d3c0049b5d2ce6ae74f876ad4","observation_id":"fc49c1cd-4452-4cfc-af7e-95ef5fce5cff","resolution":{"observed_at":"2026-08-07T14:46:47.117662Z","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":"2026-08-07T14:46:48.864651Z","title":"Protopformer: concentrating on prototypical parts in vision transformers for interpretable image recognition","venue":null,"work_id":"c8d3adb3-441a-40d7-a557-5808a8b46d3b","year":2024},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:47.194395Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:208626e49ece6930d93de24435cd7ecaf1de867b655de8c136fcd0b62f7d0bb0","observation_id":"2e2f9eb7-bf89-4ea0-9529-764a6413e651","resolution":{"observed_at":"2026-08-07T14:46:48.937014Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:48.699428Z","title":"Protopshare: Prototypical parts sharing for similarity discovery in interpretable image classification","venue":null,"work_id":"3965636a-0516-484a-b8b9-605a7de80512","year":2021},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:47.325252Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:3e1eada44cbc3793eed3e2978ad3762a7f7c3c1223af2897e321ed73497a8c89","observation_id":"160ac9f8-b752-4dbe-bd4d-908daf3c4d5d","resolution":{"observed_at":"2026-08-07T14:46:48.783836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:47.420310Z","title":"Neural prototype trees for interpretable fine-grained image recognition","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:47.420310Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:bc0bbeb308aa4c680b53e7530255b93382c10e98554c67f02ce452a238d8fbe2","observation_id":"d10904cc-a3db-4e53-ac1f-6f56c96e81e8","resolution":{"observed_at":"2026-08-07T14:46:47.420310Z","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":"2026-08-07T14:46:48.506631Z","title":"Lightspeed computation of optimal transport.Advances in neural information processing systems, 26:2292–2300, 2013","venue":null,"work_id":"c7199427-d379-4765-9247-0b0a6440f0a9","year":2013},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:47.538281Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:c7f50d8fd0a67473aed9abbda6819197d7e20fdbfcf1923a266d01eb98414324","observation_id":"f0caead9-f1c5-420e-815f-04051db1399d","resolution":{"observed_at":"2026-08-07T14:46:48.589257Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:48.318080Z","title":"On efficient optimal transport: An analysis of greedy and accelerated mirror descent algorithms","venue":null,"work_id":"76ab8676-439b-437a-bfb5-c24133e6c336","year":2019},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:47.643716Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:0b79c16fdf89cb7658fc91b6f151437cdbd81709e980054ecf783a84c2691074","observation_id":"b90d16d4-647a-48d9-a138-e853fb048c8a","resolution":{"observed_at":"2026-08-07T14:46:48.397811Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T14:46:48.143740Z","title":"3d shapenets: A deep representation for volumetric shapes","venue":null,"work_id":"f774f086-6bf2-45ad-8481-98d2735cc126","year":1912},"citing_paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:47.750597Z"},"links":{"citing_paper":"/paper/2505.17666"},"observation_digest":"sha256:fdf3a682375f86f1842dd1544610e16df8f77d490f746c1d4b2ea05ff80b81fb","observation_id":"44b3400c-e53c-470e-904b-5edb8d943c7c","resolution":{"observed_at":"2026-08-07T14:46:48.237150Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.17666","last_updated":"2025-05-23T09:31:02Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T14:40:37.810774Z","submitted_at":"2025-05-23T09:31:02Z","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification"},"reference_resolution":{"displayed":52,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":1,"verified_fuzzy":38},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 0 inbound Pith citation observations for arXiv:2505.17666."}