{"as_of":"2026-08-17T09:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:aa8e03887d06a4d525452c1956070232cfbd41fbbbdbd27f18fe25b16b7dd11c","coverage":[{"denominator":33,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":33,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:41:34.168674Z","state":"measured"},{"denominator":33,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":33,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2505.17919/citation-record","integrity":"/paper/2505.17919/integrity","json":"/paper/2505.17919/citation-record.json","paper":"/paper/2505.17919"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:41:38.433310Z","title":"Generalized scheme of the no-time-counter scheme for the dsmc in rarefied gas flow analysis.Computers & fluids, 22(2-3):253–257, 1993","venue":null,"work_id":"2b8a3ec1-8c6c-430e-9fee-3a647b0f9308","year":1993},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:29.246887Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:4ea3d020642d4bb06c852f2a63c6c052f162a9fc160e578f0f1dd9abb21871a1","observation_id":"f6c577a1-0946-42f4-a0b4-852888a339b6","resolution":{"observed_at":"2026-08-07T14:41:38.578308Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:29.387459Z","title":"Neural flows: Efficient alternative to neural odes.Advances in neural information processing systems, 34:21325–21337, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:29.387459Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:d6952b89c8a201f2533dd878ea7d5ae5d45ac5a8c6904b1d9696def8d34883f4","observation_id":"6d1bd26c-456b-4901-98b2-9e6a14b91d61","resolution":{"observed_at":"2026-08-07T14:41:29.387459Z","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":"2026-08-07T14:41:38.218884Z","title":"Approach to translational equilibrium in a rigid sphere gas.Phys","venue":null,"work_id":"a9df68ab-3d32-4d84-a54c-988f4e6c134e","year":1963},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:29.602776Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:a8afa8cbd667edf2bb23f6df03350da2be5870770a51748666037bb0b124de62","observation_id":"c6bb86de-7013-4209-90d5-2cfc7f6625a4","resolution":{"observed_at":"2026-08-07T14:41:38.322201Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:38.018561Z","title":null,"venue":null,"work_id":"20097c9a-ea0d-4802-8064-0dc16e675f6e","year":1971},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:29.798262Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:07cf0acd86c153e97f18997dbda21a1bd2b30ed72bd9b19220324798d3c2dd5e","observation_id":"9afdd19e-bb09-48a8-8fa2-8a458eef437b","resolution":{"observed_at":"2026-08-07T14:41:38.110948Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:37.863452Z","title":"Bowman, Gabor Angeli, Christopher Potts, and Christopher D","venue":null,"work_id":"cde2b47e-54c6-44f9-ac35-1acbfd2a4c40","year":2015},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:29.968081Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:496d63a8db9b58539eded4404229b2223e1ceacca270bc21062f141dabd19d5f","observation_id":"3c5f1ce7-6b78-40d4-9885-a4de5c4dd110","resolution":{"observed_at":"2026-08-07T14:41:37.931415Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:30.132358Z","title":"Neural ordinary differential equations.Advances in neural information processing systems, 31, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:30.132358Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:1e9156c914bfb3ae7b339244343968457e4f97423a8a67e4bc6958507e17e88a","observation_id":"80d82052-a0a8-4ee9-bd0c-d57a73e1271b","resolution":{"observed_at":"2026-08-07T14:41:30.132358Z","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":"2026-08-07T14:41:37.659684Z","title":"Efficient and flexible method for reducing moderate-size deep neural networks with condensation.Entropy, 26(7):567, 2024","venue":null,"work_id":"aae11234-6ab9-4616-b9fe-990e060eb875","year":2024},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:30.246878Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:53f8f21fb209ec03b983de757aa74946edb557e15b3f07c1584d8b19a929d963","observation_id":"694f55f0-3480-4944-9a8d-dcb1ddabab65","resolution":{"observed_at":"2026-08-07T14:41:37.741291Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:30.390804Z","title":"Imagenet: A large- scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:30.390804Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:597f7e3a0f78789d35db6d07c64be3e31b3d09d2b069652cd26f0aad9ec33c52","observation_id":"b6c0e4f3-f7d4-4f6b-98d8-6b6596eb79fd","resolution":{"observed_at":"2026-08-07T14:41:30.390804Z","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":"2026-08-07T14:41:37.435266Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":"6123e8bd-72cd-4a0b-bd64-fc88f1fa0637","year":2019},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:30.570251Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:4e61ec782661e07e8e48c069bef38d878b48b613a467e580329e6e72afabcf91","observation_id":"cf0c5296-70d9-4d5e-8764-c149d92f98f3","resolution":{"observed_at":"2026-08-07T14:41:37.553053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:37.251863Z","title":"Economon, Francisco Palacios, Sean R","venue":null,"work_id":"73450513-1090-400e-b97f-c37e0840da4a","year":2015},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:30.759547Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:c221b92d30d70a913d9661f3ab62a009d1b73252daadcc65a438c4bf4f9087b2","observation_id":"345a6b55-5080-46b1-9e09-5f4a2a3b1b32","resolution":{"observed_at":"2026-08-07T14:41:37.342151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:37.100650Z","title":"Pde-gcn: Novel architectures for graph neural networks motivated by partial differential equations.Advances in neural information processing systems, 34:3836–3849, 2021","venue":null,"work_id":"0f39e74d-92b7-4012-b43d-64f0e08a23cf","year":2021},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:30.910101Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:778d02ef297ee5ef78faa25a5f12b194d272b319f84b6b1cb0ee0b96051d666c","observation_id":"b97722ab-3a5a-4666-bdfd-64f64166f2f9","resolution":{"observed_at":"2026-08-07T14:41:37.170382Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:31.022918Z","title":"Hamiltonian neural networks.Advances in neural information processing systems, 32, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:31.022918Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:46fc330622f58c4198f94dd46f1be363ab99069d457dd2a5fdf8acb6ec970457","observation_id":"29230c23-d28f-45b7-a979-63b56a9038dd","resolution":{"observed_at":"2026-08-07T14:41:31.022918Z","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":"2026-08-07T14:41:31.119805Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:31.119805Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:08e722bfa067cb780fd592720dc6071b61003a1d06d0fc8f3cea7416493c323b","observation_id":"cac588de-62ec-4eb8-b71d-0ac13b3ad1f6","resolution":{"observed_at":"2026-08-07T14:41:31.119805Z","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":"2026-08-07T14:41:36.938948Z","title":"Molecular dynamics simulation for all.Neuron, 99(6):1129–1143, 2018","venue":null,"work_id":"e8baef1f-e4f6-44ef-ad2d-8751661ff826","year":2018},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:31.258476Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:c9dbd88e1220ae5f1ca536b1cff139a122eedf6f0357742cb83db2b11857b9b6","observation_id":"5f488eb2-2ca8-4e6c-b061-e627151beca8","resolution":{"observed_at":"2026-08-07T14:41:37.015889Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:31.386681Z","title":"Neural controlled differential equations for irregular time series.Advances in neural information processing systems, 33:6696– 6707, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:31.386681Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:5a751dec807d67223f212aa2b1c2c2f731bf7593c2e8929a94887af92dddd56c","observation_id":"f7bb6198-c624-4398-b1dc-0b6aa0e0defa","resolution":{"observed_at":"2026-08-07T14:41:31.386681Z","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":"2026-08-07T14:41:36.704930Z","title":"Transformer for partial differential equations’ operator learning, 2023","venue":null,"work_id":"6e0fe449-d67c-4413-a46a-e3a2b7bfab76","year":2023},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:31.549659Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:7d171e0d9eeb836f475f6bccf750d08f6cc5473952c4a39ea1e2693cf82d9921","observation_id":"6622fe7d-20aa-4fb6-8090-2dd259dd0351","resolution":{"observed_at":"2026-08-07T14:41:36.828387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:36.543543Z","title":"Fourier neural operator for parametric partial differen- tial equations, 2021","venue":null,"work_id":"728968a5-8ea5-424d-a736-73e816935e19","year":2021},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:31.694876Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:5e3396ef39c1532fbdface4ff8cd9f1526e3b8c0cd4fd1c904408bb10bd38835","observation_id":"90988771-55be-4fa9-a257-719f34e78611","resolution":{"observed_at":"2026-08-07T14:41:36.635185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:36.376219Z","title":"Dendritic integration inspired artificial neural networks capture data correlation.Advances in Neural Information Processing Systems, 37:79325–79349, 2024","venue":null,"work_id":"75de29ff-30bd-40ba-b740-76c60fd78a26","year":2024},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:31.903088Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:07a14936d8519d04b3fdc81f5af817deed1eca3a357d47d7880ec1782a51610d","observation_id":"7158dce6-d7e4-49d3-956f-6f8f963da0fe","resolution":{"observed_at":"2026-08-07T14:41:36.475284Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:36.232466Z","title":"Courier Corporation, 2004","venue":null,"work_id":"9a3bb723-8927-49c3-9278-6810c30d0d8e","year":2004},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:32.047523Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:88640fb84ec585435904fa6acf04adecdacfd634fbfc46e9c8985091c8c82427","observation_id":"5048d7cf-612a-4fad-af92-1b53c1940158","resolution":{"observed_at":"2026-08-07T14:41:36.292750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:36.038940Z","title":"Pde-net 2.0: Learning pdes from data with a numeric- symbolic hybrid deep network.Journal of Computational Physics, 399:108925, 2019","venue":null,"work_id":"904f3b43-0355-416d-8254-498e5675f080","year":2019},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:32.184749Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:4f20d6d9f0707fd406d62e6b385b5c03c78c0e15ca91a9eb41a65c4b3ec707e1","observation_id":"e8dc424a-eefe-4449-8172-21bc237d3b3f","resolution":{"observed_at":"2026-08-07T14:41:36.140637Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:35.864636Z","title":"Pde-net: Learning pdes from data","venue":null,"work_id":"cd5a6873-1fa7-43e8-a3e2-a5cf545ddf8d","year":2018},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:32.345782Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:baf37fb5de33b3c5eabe6b0f08c58dca55f0e01ee014e32a0e61c8e59a5866f1","observation_id":"4ed94f83-6f4e-42f4-8354-2f6d7183798e","resolution":{"observed_at":"2026-08-07T14:41:35.952697Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:35.661750Z","title":"Maas, Raymond E","venue":null,"work_id":"76c338b9-658f-4dff-80de-eeb212d48b45","year":2011},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:32.484378Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:4612a93b8bd73b7577c49d742daa85531b83264babab3af16eeb2adf805c3420","observation_id":"20356188-2be6-49df-9f75-61439b74a55b","resolution":{"observed_at":"2026-08-07T14:41:35.780325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:35.479454Z","title":"Neural ode processes","venue":null,"work_id":"809798ee-9496-41f5-937a-b905f5b0e2dd","year":2021},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:32.662944Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:e95ba3a7f51de34ad5d3cb407604d574479a30e4cd06b6b0957a0cb195c0b6ca","observation_id":"a01c6e79-e35e-437a-b0ee-16251ab07b47","resolution":{"observed_at":"2026-08-07T14:41:35.566048Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:35.297677Z","title":"On second order behaviour in augmented neural odes.Advances in neural information processing systems, 33:5911–5921, 2020","venue":null,"work_id":"25ae4bac-1931-4d42-94f5-9918740120b7","year":2020},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:32.805709Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:b93ef71c01cc489ad7b8e2686a72fdf9df6d424ec18195f267d16fa779b04caf","observation_id":"690e0980-5766-4d3d-b86b-3fb284c38a09","resolution":{"observed_at":"2026-08-07T14:41:35.380986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:35.105825Z","title":"Battaglia","venue":null,"work_id":"636d6a1b-551d-4965-86bb-47d4a26678e8","year":2021},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:32.935446Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:ed8faafa8d78ac248fa9ae2e5835a74d5635c38b75ed60ab961cc69de6c05306","observation_id":"88bb42d6-4305-45a3-b206-dc4b6cf07e7c","resolution":{"observed_at":"2026-08-07T14:41:35.205345Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:33.116353Z","title":"Latent ordinary differential equations for irregularly-sampled time series.Advances in neural information processing systems, 32, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:33.116353Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:66807707f8bf4a824faaf5f31a7d0b1fe478634905d869e5951fdc1c0be02c5c","observation_id":"d2f6f5a6-ea80-47ba-9fad-ea06a2813cc1","resolution":{"observed_at":"2026-08-07T14:41:33.116353Z","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":"2026-08-07T14:41:34.904016Z","title":"Combinatorial optimization with physics-inspired graph neural networks.Nature Machine Intelligence, 4(4):367–377, 2022","venue":null,"work_id":"35c9ba59-95cf-4daf-a428-0499233891e2","year":2022},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:33.271804Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:0ac9a5b9712fee014976085ecf54fbd81830d3e84362b28206d90ef41706620f","observation_id":"748956d4-2b94-404b-b1d9-9186a3b4a98d","resolution":{"observed_at":"2026-08-07T14:41:34.995417Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.13789","last_updated":"2020-02-14T12:00:47Z","snapshot_observed_at":"2026-08-16T10:41:34.078340Z","submitted_at":"2019-09-30T15:32:52Z","title":"Hamiltonian Generative Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.13789","snapshot_observed_at":"2026-08-07T14:41:33.400067Z","title":"Hamiltonian generative networks.arXiv preprint arXiv:1909.13789, 2019","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:33.400067Z"},"links":{"cited_paper":"/paper/1909.13789","citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:2adc2c2dcf26f8ed99ad0d0e33a1ed359bd7c0cec69a74c3708d8880d9ded3e6","observation_id":"357d7999-0fa4-4cbf-b11c-3bb73496695a","resolution":{"observed_at":"2026-08-07T14:41:33.400067Z","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":"2026-08-07T14:41:33.607758Z","title":"Attention is all you need.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:33.607758Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:3975550f2eea612a3841194c9267683df355841a54b30a52ef41a52e0b4d8d17","observation_id":"1b4192fc-dd5a-432f-b8ea-cfd88b33713b","resolution":{"observed_at":"2026-08-07T14:41:33.607758Z","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":"2026-08-07T14:41:34.717832Z","title":"Convection-diffusion equation: a theoret- ically certified framework for neural networks.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025","venue":null,"work_id":"e3afa8b4-5407-4f09-ac4f-0290f9cf266c","year":2025},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:33.769609Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:cb4beb1fba705e2412a89dfadca13220aefda60325943b21778ed61b7c5e123e","observation_id":"27eb286a-5626-40ff-9220-0a11cd576af1","resolution":{"observed_at":"2026-08-07T14:41:34.803781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.09484","last_updated":"2026-04-12T13:30:14Z","snapshot_observed_at":"2026-07-06T21:08:33.353144Z","submitted_at":"2025-04-13T08:50:24Z","title":"An overview of condensation phenomenon in deep learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.09484","snapshot_observed_at":"2026-08-07T14:41:33.904594Z","title":"An overview of condensation phe- nomenon in deep learning.arXiv preprint arXiv:2504.09484, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:33.904594Z"},"links":{"cited_paper":"/paper/2504.09484","citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:4c4d0e7ad840a6a87c48c1953666aeded61acd452472e0482283c269b8f25279","observation_id":"5f989c28-a3bb-48a3-a3d6-a1dcb8ddebd0","resolution":{"observed_at":"2026-08-07T14:41:33.904594Z","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":"2026-08-07T14:41:34.522542Z","title":"Embedding principle of loss landscape of deep neural networks.Advances in Neural Information Processing Systems, 34:14848–14859, 2021","venue":null,"work_id":"8f058be5-eb8f-4778-afbd-2565c874ff50","year":2021},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:34.071799Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:e2beb98dca89f8847eff89bb731c44413febf3aa3a4ca1775c93bed434eb02d6","observation_id":"5c3f32c0-8b48-4486-aeca-6b067fc29393","resolution":{"observed_at":"2026-08-07T14:41:34.617659Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:41:34.287591Z","title":"Towards understanding the condensation of neural networks at initial training.Advances in Neural Information Processing Systems, 35:2184–2196, 2022","venue":null,"work_id":"e9196cea-801e-47d7-ab7f-05660980307a","year":2022},"citing_paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:34.168674Z"},"links":{"citing_paper":"/paper/2505.17919"},"observation_digest":"sha256:e22a88c49fefef4d27fadd866ef70c08d0e625e644285d4b0b7dd440eec7ac01","observation_id":"f9fcb913-89b7-43e7-903b-7323283636f1","resolution":{"observed_at":"2026-08-07T14:41:34.405227Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.17919","last_updated":"2025-05-23T13:58:29Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T10:43:36.222578Z","submitted_at":"2025-05-23T13:58:29Z","title":"KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches"},"reference_resolution":{"displayed":33,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":0,"verified_fuzzy":22},"total_outbound_references":33},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2505.17919."}