{"as_of":"2026-08-22T02:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:071f039c1be5532c5dcbc305ce2a86fd642ec387485412f11bc90ad68f4f81c4","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":"2026-08-14T04:48:03.959164Z","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":"2026-08-21T06:32:19.484+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/1909.02702/citation-record","integrity":"/paper/1909.02702/integrity","json":"/paper/1909.02702/citation-record.json","paper":"/paper/1909.02702"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:48:03.815357Z","title":"Multilayer feedforward networks are universal approximators","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.815357Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:2d1152db9d00ace0b3abb15bbe1c5c905e6378c18643e47f7bbae5b84cd52895","observation_id":"e92c9926-05c2-4edd-885f-9aa2fc565a41","resolution":{"observed_at":"2026-08-14T04:48:03.815357Z","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":"2026-08-14T04:48:03.820017Z","title":"Learning internal representations by error propagation","venue":null,"work_id":null,"year":1985},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.820017Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:28c783184bea33de58ddd1e4c0ea02399e7d2eefe700b002d2c66536ff180abf","observation_id":"00da5a1a-c493-494a-9bf7-b21e62fa5714","resolution":{"observed_at":"2026-08-14T04:48:03.820017Z","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":"2026-08-14T04:48:03.824604Z","title":"Mask r-cnn","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.824604Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:b729e35c8d26c793846a34abe419d23b5586bf65dcf4a6a0a154497551a64127","observation_id":"323441c4-a283-45a3-89e9-13fa5c0c0c82","resolution":{"observed_at":"2026-08-14T04:48:03.824604Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.11096","last_updated":"2019-02-25T21:32:06Z","snapshot_observed_at":"2026-07-06T07:04:57.275371Z","submitted_at":"2018-09-28T15:38:49Z","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.11096","snapshot_observed_at":"2026-08-14T04:48:03.829332Z","title":"Large scale gan training for high fidelity natural image synthesis","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.829332Z"},"links":{"cited_paper":"/paper/1809.11096","citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:10e746a17919c978338e409f3437663ec5928d58d7772b1d6de5e42f5f6e09d0","observation_id":"1c0615ef-5c5c-4fad-8506-242d83db7619","resolution":{"observed_at":"2026-08-14T04:48:03.829332Z","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":"2026-08-14T04:48:03.834695Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.834695Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:8fb4e0c0094a5ee2c4ff58d1ae851071eaed52141606724fc6c83f06839c5d6b","observation_id":"bc47556c-55d5-4d05-9756-6c286692d844","resolution":{"observed_at":"2026-08-14T04:48:03.834695Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-08-14T18:16:28.847993Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-14T04:48:03.839761Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.839761Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:d1feeacdf811f5d46946074f540b175be44a7cbfde548df6e3eac407f0ee27c5","observation_id":"9c2c31fc-1064-4ce2-87de-a2b5a736da76","resolution":{"observed_at":"2026-08-14T04:48:03.839761Z","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":"2026-08-14T04:48:04.347945Z","title":"Kingma and Jimmy Ba","venue":null,"work_id":"76f86295-2641-425e-a1a4-548eb7031a01","year":2015},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.844254Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:b00e3c0b0342e265bed7db304365b9fcb8feddaa0671a5216b3e1ac9c9a91742","observation_id":"258976d9-9385-4555-8746-70c189faac06","resolution":{"observed_at":"2026-08-14T04:48:04.352139Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.333429Z","title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","venue":null,"work_id":"4079d8c9-69c2-4582-8536-c00a2ded7b6a","year":2012},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.848086Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:bc108911da75763f7b5b7b33841ccaba95ab15b928fc6525f7d3215b8d53ef4e","observation_id":"8c16ac56-f62e-463b-9d6e-7fccf74e2f35","resolution":{"observed_at":"2026-08-14T04:48:04.339000Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.03265","last_updated":"2021-10-26T02:48:30Z","snapshot_observed_at":"2026-08-19T14:20:48.530093Z","submitted_at":"2019-08-08T20:51:17Z","title":"On the Variance of the Adaptive Learning Rate and Beyond","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.03265","snapshot_observed_at":"2026-08-14T04:48:03.852071Z","title":"On the variance of the adaptive learning rate and beyond","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.852071Z"},"links":{"cited_paper":"/paper/1908.03265","citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:bc4865cf5e40ecb4d0d558c3906f25fa038dd17502578fca32e4a9df05cafdcc","observation_id":"43ec225f-5dfe-4f7b-9cc2-091a0ccb5c79","resolution":{"observed_at":"2026-08-14T04:48:03.852071Z","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":"2026-08-14T04:48:04.320038Z","title":"Visualizing the loss landscape of neural nets","venue":null,"work_id":"ce31f64e-336d-42cb-bf3d-fa95bfaa12e4","year":2018},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.856231Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:38a313183063cca8c472c96b935616cf53aaeda41b804ea04ce320ab6133f982","observation_id":"5fb6579b-646e-4348-a907-eb8caf305569","resolution":{"observed_at":"2026-08-14T04:48:04.324940Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.306324Z","title":"Training a 3-node neural network is np-complete","venue":null,"work_id":"53e18536-8ab7-424e-bf3c-07de318aa832","year":1989},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.860391Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:aed0d9ae8ab8e774910c9a84ee6eaac772959f4257dc405222c5377b5a2b3fae","observation_id":"e3654960-4386-4a19-b728-5c0d441cad8f","resolution":{"observed_at":"2026-08-14T04:48:04.310303Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.294039Z","title":"Port-controlled hamiltonian systems: modelling origins and systemtheoretic properties","venue":null,"work_id":"2a6b09a7-4693-43ae-9193-5a5da7786e63","year":1992},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.864834Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:1b21ddcf646fa608b322427d48287651bdfd7aac4da0f6191caf3d9f85fe891f","observation_id":"2f8efb5a-405e-4166-87dd-65c287a15deb","resolution":{"observed_at":"2026-08-14T04:48:04.298324Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.281743Z","title":"Modeling and control of complex physical systems: the port-Hamiltonian approach","venue":null,"work_id":"81def398-e4c0-47fc-9b2d-033414bcc48f","year":2009},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.869349Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:c80079c30ccfca3b6bf6b46094ed336fc0a19cc766cd5cec38d39209b1ce55e4","observation_id":"ab5e4a70-d318-45e4-87e4-f688abb190f8","resolution":{"observed_at":"2026-08-14T04:48:04.286537Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.269545Z","title":"Port-hamiltonian systems theory: An introductory overview","venue":null,"work_id":"aebc33c2-5865-4821-9798-00f8d78df8bf","year":2014},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.875088Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:eaf0dd0e9d80db45230878f99df62bc7056c100a18c0e11f40455abf6c27345e","observation_id":"15ecdc65-7668-4371-be66-4b3e06ed37c6","resolution":{"observed_at":"2026-08-14T04:48:04.273624Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.257576Z","title":"Putting energy back in control","venue":null,"work_id":"fdca3858-a0dc-4fec-aea8-7d9086ce4ff6","year":2001},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.880281Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:cc0e205c128c17acd05270dfe3e63617289b79e27b305c9249b211389c405af6","observation_id":"ebcadb9a-2259-46ef-af4d-a79e6544655a","resolution":{"observed_at":"2026-08-14T04:48:04.261628Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.244889Z","title":"Interconnection and damping assignment passivity- based control of port-controlled hamiltonian systems","venue":null,"work_id":"80369512-50ee-41f3-b006-8ff4de86e82e","year":2002},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.885457Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:e33c7b9e9a8beaef42dcb5c86bf4e8834dcd2075569b1fcea7632f7f0cb6a469","observation_id":"9c7c2596-f8ba-4175-8f16-7e0590a8bcb2","resolution":{"observed_at":"2026-08-14T04:48:04.249307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.231458Z","title":"Control by interconnection and standard passivity- based control of port-hamiltonian systems","venue":null,"work_id":"5968fdb4-9f51-495a-97ac-75571abc1201","year":2008},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.891523Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:a6a82ccc774448029345d0edfac98d16ee63ee5bfdb68de791fe2d35f22e7dd4","observation_id":"787c8971-7375-4939-b708-50bcd6093e74","resolution":{"observed_at":"2026-08-14T04:48:04.235737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.219013Z","title":"Neural ordinary differential equations","venue":null,"work_id":"092a6d07-af6e-44fa-9300-a9d69d669040","year":2018},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.895143Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:64f8c0063f17515e5224cbafbd75fbd541828527112d19842ac7c6a40f993ebc","observation_id":"f6bf3f5b-57a0-4dc6-b577-24a6c2d9d04c","resolution":{"observed_at":"2026-08-14T04:48:04.223326Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.04272","last_updated":"2018-12-10T21:51:10Z","snapshot_observed_at":"2026-08-14T19:26:49.931748Z","submitted_at":"2018-04-12T01:40:55Z","title":"Deep Neural Networks Motivated by Partial Differential Equations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.04272","snapshot_observed_at":"2026-08-14T04:48:03.899404Z","title":"Deep neural networks motivated by partial differential equations","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.899404Z"},"links":{"cited_paper":"/paper/1804.04272","citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:aca3a34071e15e49dd53c96a32a0d77315124e3d46af4ff19140a76348745698","observation_id":"2467a84b-c1f8-4f25-b21f-9be690e58a0a","resolution":{"observed_at":"2026-08-14T04:48:03.899404Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.01563","last_updated":"2019-09-05T04:20:28Z","snapshot_observed_at":"2026-08-14T16:21:01.276672Z","submitted_at":"2019-06-04T16:27:55Z","title":"Hamiltonian Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.01563","snapshot_observed_at":"2026-08-14T04:48:03.903836Z","title":"Hamiltonian neural networks","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.903836Z"},"links":{"cited_paper":"/paper/1906.01563","citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:7b0fd86a874a26fde2288337bbfe6f676b93298a977f5b4a0d08442a9c3a500d","observation_id":"e6b11d80-b7f9-40f0-afec-a4a94a9046a6","resolution":{"observed_at":"2026-08-14T04:48:03.903836Z","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":"2026-08-14T04:48:04.206506Z","title":"Deep relaxation: partial differential equations for optimizing deep neural networks","venue":null,"work_id":"e1b77a6d-5425-4860-aad4-f431360593f4","year":2018},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.908287Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:23c4f99a8ca84bedd4cb819bf1b3a477e45ffee94461775ad000ae1757b584e4","observation_id":"14152578-394b-4324-a83f-833d1fdd1f40","resolution":{"observed_at":"2026-08-14T04:48:04.210647Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.194516Z","title":"Gradient and hamiltonian dynamics applied to learning in neural networks","venue":null,"work_id":"eb9f1c8c-e6d4-4d05-b273-cf4bb9073a19","year":1996},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.912283Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:43e9fd21e962f5433f85348cc0a60c7e7d6f92eb310d9f87bf1a4254e26f4bdf","observation_id":"775e2a6b-1aa7-4ffb-9b75-0f6c40c98348","resolution":{"observed_at":"2026-08-14T04:48:04.199117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.182403Z","title":"Learning and system modeling via hamiltonian neural networks","venue":null,"work_id":"b84982b3-7b1b-402a-97cc-fea8e3b1ad7e","year":null},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.917245Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:7754d1674b0571bcf640670aa1a3ad854eb627cc9b3a04a3261080a820099c43","observation_id":"0b0683a3-179f-4d37-85b5-55748199f7b9","resolution":{"observed_at":"2026-08-14T04:48:04.186974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.170760Z","title":"A learning algorithm for boltzmann machines","venue":null,"work_id":"2a8634d3-4377-4ce3-b8fd-5e003176d407","year":1985},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.921534Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:38b2f2f26eae7dea8d2b974a51283de9546981e15e6cafb5b14b3a16e0d87824","observation_id":"01cd9a6c-19bc-4e3a-8979-5647be4da458","resolution":{"observed_at":"2026-08-14T04:48:04.174730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.157036Z","title":"Neural networks and physical systems with emer- gent collective computational abilities","venue":null,"work_id":"3b2eeb94-80f3-4ef3-ada3-47152e1ff0c5","year":1982},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.925494Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:de5dbe047267aeeca9b7c12e42617976d2d5ea6733579f29adb8068fa9fb201d","observation_id":"99c6b27d-30b8-4880-a471-a806b0ea382d","resolution":{"observed_at":"2026-08-14T04:48:04.162241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.144340Z","title":"Theory of holors: A generalization of tensors","venue":null,"work_id":"160d75d1-7812-4043-a80c-48124b7f7260","year":2005},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.929502Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:397cdb6b64c15110f836934696c9265b585d4438f885e4af1aa54b4f7b4a50f4","observation_id":"9b9c3ca7-b2de-438f-b043-d4b47ea6d06b","resolution":{"observed_at":"2026-08-14T04:48:04.148940Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.131217Z","title":"Tikhonov regularization and total least squares","venue":null,"work_id":"15855d4c-7311-447b-b7e9-005d01d2cc66","year":1999},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.933761Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:012dee4979ff9b6d76c20f2e728f876a8aaeb9a755f78de24e67c2581cb11546","observation_id":"f9cb90e4-941a-4a82-9fb3-e69121dc929b","resolution":{"observed_at":"2026-08-14T04:48:04.135366Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.118138Z","title":"A simple weight decay can improve generalization","venue":null,"work_id":"755007ef-b735-495c-92da-267b154069af","year":1992},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.937675Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:6d76f30e8de13bbba9a8ca9df5ad2d3322df16b80de6d4232469d5234b9e8026","observation_id":"1eef4c8e-b3d2-43b1-93a0-c220f864ac69","resolution":{"observed_at":"2026-08-14T04:48:04.122499Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.103802Z","title":"Multistable energy shaping of linear time–invariant systems with hybrid mode selector","venue":null,"work_id":"c031fbaa-0a6d-4b6f-b6db-68e326234fd8","year":2019},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.942604Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:a773330083d94943cbd35c046961fefe0c687d2ef7cbacdeca12744e5946f9f7","observation_id":"54e9d7f6-7434-4035-95f7-63f558d20923","resolution":{"observed_at":"2026-08-14T04:48:04.108436Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.091541Z","title":"An introduction to hybrid dynamical systems , volume 251","venue":null,"work_id":"04c4d84d-93e3-49e0-b4a2-90e2b869d4c9","year":2000},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.946445Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:0f5490958dabc77618df5d6c25c1f1df193573a1514be6616261d6e4968219c3","observation_id":"3919703a-21f0-4559-8ca6-b6a84fee7186","resolution":{"observed_at":"2026-08-14T04:48:04.095676Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.078753Z","title":"The Duffing equation: nonlin- ear oscillators and their behaviour","venue":null,"work_id":"8096ed03-fe55-4b9b-b72c-3e054627ef11","year":2011},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.950470Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:5ec66217f93526e894d6c5ebc8c06f9534ef19d2f920d64e805b15870466ff75","observation_id":"9db573b3-1673-46bc-9734-3e6e96130a66","resolution":{"observed_at":"2026-08-14T04:48:04.082874Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.066250Z","title":"The expressive power of neural networks: A view from the width","venue":null,"work_id":"4b457bfe-b0b2-49e4-bd0e-228e75c20791","year":2017},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.955063Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:9a4466c24ac2d3923a15f246ae4aa57c3dd732f8255c8e9f1361721f0d8986df","observation_id":"6245840b-6ea3-4752-8c17-27f019cf5236","resolution":{"observed_at":"2026-08-14T04:48:04.070442Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T04:48:04.051098Z","title":"The power of depth for feedforward neural networks","venue":null,"work_id":"e0864d68-dcf5-4bef-8d30-5f39629419fa","year":2016},"citing_paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T04:48:03.959164Z"},"links":{"citing_paper":"/paper/1909.02702"},"observation_digest":"sha256:8ba4605d554e1ded14f4f11f49e6ac6078decc45a1ae887bd2812fc69bd27bc0","observation_id":"c3c13ff3-6d64-49c6-8a50-1b9d01c654ed","resolution":{"observed_at":"2026-08-14T04:48:04.057574Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1909.02702","last_updated":"2019-09-06T03:31:40Z","latest_version":1,"primary_category":"cs.NE","snapshot_observed_at":"2026-08-19T14:22:06.711400Z","submitted_at":"2019-09-06T03:31:40Z","title":"Port-Hamiltonian Approach to Neural Network Training"},"reference_resolution":{"displayed":33,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":0,"verified_fuzzy":24},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:1909.02702."}