{"as_of":"2026-08-16T10:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:23158d8664c1ad3d952c9e639b545aec1f78af20497f1c494fbbdf67a6bf2ff7","coverage":[{"denominator":25,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":25,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T13:48:19.295633Z","state":"measured"},{"denominator":25,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":25,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/1908.04332/citation-record","integrity":"/paper/1908.04332/integrity","json":"/paper/1908.04332/citation-record.json","paper":"/paper/1908.04332"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T13:48:20.207537Z","title":"Learning long -term dependencies with gradient descent is difficult,","venue":null,"work_id":"82b7cf79-2fdc-41fd-b9c0-d5fefa046cff","year":1994},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.030815Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:be95abaf5316f262f142e572b0292a0102ce118926c30254edc42c5e012a5085","observation_id":"1e7686bc-a929-4613-ade6-9af23e742389","resolution":{"observed_at":"2026-08-14T13:48:20.223172Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1406.1078","last_updated":"2014-09-03T00:25:02Z","snapshot_observed_at":"2026-08-15T13:36:27.756066Z","submitted_at":"2014-06-03T17:47:08Z","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1406.1078","snapshot_observed_at":"2026-08-14T13:48:19.039916Z","title":"Learning phrase representations using RNN encoder -decoder for statistical machine translation,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.039916Z"},"links":{"cited_paper":"/paper/1406.1078","citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:c2e62a8e5e497d82849340372167132892b3f0a043802e052568fd5f20eca837","observation_id":"bbf85a8e-cb85-45a0-8e3a-243b9c4489d1","resolution":{"observed_at":"2026-08-14T13:48:19.039916Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1506.00019","last_updated":"2015-10-17T05:06:11Z","snapshot_observed_at":"2026-08-14T22:46:30.846767Z","submitted_at":"2015-05-29T20:16:51Z","title":"A Critical Review of Recurrent Neural Networks for Sequence Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.00019","snapshot_observed_at":"2026-08-14T13:48:19.050598Z","title":"A Critical Review of Recurrent Neural Networks,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.050598Z"},"links":{"cited_paper":"/paper/1506.00019","citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:a80f4a44a6eca4cede0d2468d4c7ef412cbfef0d6fefe6e58392b6d0c0c578ba","observation_id":"ac14eb06-a345-4fe6-abc4-e40006a37870","resolution":{"observed_at":"2026-08-14T13:48:19.050598Z","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":"2026-08-14T13:48:20.181599Z","title":"Got.pkl,","venue":null,"work_id":"c8718712-f882-4a3d-96ba-f2cecb5c878b","year":2019},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.057718Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:5fe53457bf75bf65140180e2a40dbcd12be01da7c766a36c58440d248cd19673","observation_id":"9758cb2b-f12a-4381-8e1a-c50808c7898d","resolution":{"observed_at":"2026-08-14T13:48:20.190479Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.01541","last_updated":"2016-09-29T15:02:32Z","snapshot_observed_at":"2026-08-14T21:54:08.133617Z","submitted_at":"2016-06-05T17:59:23Z","title":"Deep Reinforcement Learning for Dialogue Generation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.01541","snapshot_observed_at":"2026-08-14T13:48:19.070282Z","title":"Deep reinforcement learning for dialogue generation,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.070282Z"},"links":{"cited_paper":"/paper/1606.01541","citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:7ca970f0e098182197effd7b0ed93880ca0bf709ff8ae38806310042b617385f","observation_id":"bd271f7e-13ab-4eae-975f-c22c1734b738","resolution":{"observed_at":"2026-08-14T13:48:19.070282Z","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":"2026-08-14T13:48:20.147707Z","title":"Data -driven response generation in social media,","venue":null,"work_id":"de90f96e-7867-41be-a530-02f1133cdbff","year":2011},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.081252Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:c597cbccda577beeae0ff6dfe4bad5c1c1c1f57c9428058fd8c6c2238fa140e9","observation_id":"f8e83151-26d5-4634-a4d0-188be89f2943","resolution":{"observed_at":"2026-08-14T13:48:20.157614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1506.05869","last_updated":"2015-07-22T03:29:47Z","snapshot_observed_at":"2026-08-14T22:43:48.519467Z","submitted_at":"2015-06-19T02:52:23Z","title":"A Neural Conversational Model","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.05869","snapshot_observed_at":"2026-08-14T13:48:19.090328Z","title":"A neural conversational model,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.090328Z"},"links":{"cited_paper":"/paper/1506.05869","citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:6c463ef7649aed1de0f7decb6340ee397e3ee1e6f2eea0a75e18995eca7b9ffe","observation_id":"18f16db5-ec66-4ac8-9ab3-9792d194b86a","resolution":{"observed_at":"2026-08-14T13:48:19.090328Z","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":"2026-08-14T13:48:20.103857Z","title":"Learning from delayed rewards,","venue":null,"work_id":"7d3ea4c3-1563-4353-bd77-e708d2e47b02","year":1989},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.104848Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:d5dfa91c0ba05f14a75bed244c2484200e574959ce0e360ab5b4633eb7f5adc0","observation_id":"5dcd9622-c1ad-41f4-9947-f70e3bd12a2a","resolution":{"observed_at":"2026-08-14T13:48:20.120165Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T13:48:20.068707Z","title":"Sequence to sequence learning with neural networks,","venue":null,"work_id":"cb91aaef-8597-44b9-8239-58f0f26f8cd9","year":2014},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.120572Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:589299ea197fcdf0c5f616f6ce16b261206b7f7d8431935b02e2c0429bf862fe","observation_id":"c99872fb-8094-4a96-8bd2-789843be5644","resolution":{"observed_at":"2026-08-14T13:48:20.076251Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T13:48:20.040539Z","title":"Building end -to-end dialogue systems using generative hierarchical neural ne twork models,","venue":null,"work_id":"bea57e7e-9348-4df0-b6c2-3035344e9d23","year":2016},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.132353Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:eddf7d8b6d665f3a4b1e449a629ff270a8a7ac0a843b829c9ba9d41a13c5c7cb","observation_id":"473a0d30-95de-4390-842a-b469245be3f2","resolution":{"observed_at":"2026-08-14T13:48:20.047607Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T13:48:20.002477Z","title":"Using Markov decision process for learning dialogue strategies,","venue":null,"work_id":"0a5d1af8-325b-44ea-b27d-5d389b02e5fd","year":1998},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.143442Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:e90f3a592cb1e1d67dec10e4ac0b15600528eb302818bd21ec88048a5ad09ef4","observation_id":"440e6553-d8fe-4468-8fda-acb8342f0d42","resolution":{"observed_at":"2026-08-14T13:48:20.012376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T13:48:19.978796Z","title":"A Markovian decision process,","venue":null,"work_id":"89a4a1a2-33d7-4cd2-9c97-350dab342008","year":1957},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.154291Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:47c2919b80d4250cfac1287937fd8ee614729ad75f9617bb0356c9e1437c3630","observation_id":"cc1d1af5-e8ab-4ccb-968a-79bb6065b89e","resolution":{"observed_at":"2026-08-14T13:48:19.984437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T13:48:19.929457Z","title":"Training a Real -world POMDP-based Dialogue System,","venue":null,"work_id":"b5d0d61e-3be2-4fac-8943-c242353029d1","year":2007},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.168426Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:9edecbaccb39468070fd4a7c4a3dae58fe81377b2d591a6ed45a210acb83489d","observation_id":"fbd4b0b1-0d26-43a9-8c95-6c98a6f7fb77","resolution":{"observed_at":"2026-08-14T13:48:19.954246Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.02689","last_updated":"2016-06-08T19:03:06Z","snapshot_observed_at":"2026-08-14T21:53:36.333733Z","submitted_at":"2016-06-08T19:03:06Z","title":"Continuously Learning Neural Dialogue Management","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.02689","snapshot_observed_at":"2026-08-14T13:48:19.178115Z","title":"Continuously learning neural dialogue management,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.178115Z"},"links":{"cited_paper":"/paper/1606.02689","citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:6e4f007bb2b7533a8b7950ab4449466692ac4cb74583e81c3b78d3281b025261","observation_id":"6ece0da1-9f3a-4e9b-9017-97705b816e4b","resolution":{"observed_at":"2026-08-14T13:48:19.178115Z","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":"2026-08-14T13:48:19.891667Z","title":"Magenta,","venue":null,"work_id":"a222cc71-eed7-4119-a91e-40fb75b69fa0","year":2018},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.191005Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:3d281582cb33ec15b05721f70ec87940ff3ecffc40b7bd7fd724ebae543af3e8","observation_id":"c0c7fd20-5d0f-41dc-84a5-ffad35da3470","resolution":{"observed_at":"2026-08-14T13:48:19.900650Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T13:48:19.862340Z","title":"Word embedding by Keras,","venue":null,"work_id":"028b05a3-bac4-47f3-8fa9-2728ae18f14b","year":2019},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.200241Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:a02f1270eda5e9eaf9fe9cae6483c2503e3d4316fdb200c6a77b2f907e8e32a6","observation_id":"f4f80257-c564-448f-84dd-a9566647bf9f","resolution":{"observed_at":"2026-08-14T13:48:19.870194Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T13:48:19.832760Z","title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting,","venue":null,"work_id":"65be4bb2-11f4-4351-87a2-1012cf575607","year":1929},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.215590Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:b6def10cdb8383fa2cff250b85f11a01baa70eee93e4fa49bbed5e5bf37ac6cf","observation_id":"80371947-d542-42e9-b8f3-1ae9c91ea6ac","resolution":{"observed_at":"2026-08-14T13:48:19.840188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T13:48:19.791293Z","title":"Densely connected convolutional networks.,","venue":null,"work_id":"b90b0e69-a37e-49ac-890f-e7e044ceb9a4","year":2017},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.225034Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:a81b68329c91229057e845f78d39e6c1848e2d8fc94c7cd28ee6904627511f66","observation_id":"7045cb26-3d82-44d4-98ba-057c96156d94","resolution":{"observed_at":"2026-08-14T13:48:19.809145Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T13:48:19.762760Z","title":"Rnndrop: A novel dropout for rnns in asr,","venue":null,"work_id":"ad0b7170-bfb5-4054-836a-d47a0492b8eb","year":2015},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.234022Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:162741b28940ff73a6f93cb354099f5a1a0f10049b3ecf0654f4f26c6d21395f","observation_id":"9723c10d-fd00-4c35-8c44-afe69fadef7f","resolution":{"observed_at":"2026-08-14T13:48:19.770167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T13:48:19.738953Z","title":"Lecture 6.5 -rmsprop: Divide the gradient by a running average of its recent magnitude,","venue":null,"work_id":"946abb18-5f59-478d-b354-566b64b1e32d","year":2012},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.244715Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:2a20cd1aa4c9f38dbd540cd6f50f64447585cc71d08f5f55addee4746b7a2d9d","observation_id":"efd9cd18-cc17-47c7-9392-2dcfa2a97d67","resolution":{"observed_at":"2026-08-14T13:48:19.748707Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T13:48:19.700702Z","title":"pickle — Python object serialization,","venue":null,"work_id":"886822b8-9be3-4a81-bbd0-021e8061a2c1","year":2019},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.252100Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:9d8626f9ee86102b06679a8ade753dd6ac1e8f230e548110ca0d7117a25e05be","observation_id":"e3b14efe-1080-4908-aed1-a2705cdfa138","resolution":{"observed_at":"2026-08-14T13:48:19.708337Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T13:48:19.670977Z","title":"Learning representations by back-propagating errors,","venue":null,"work_id":"3b2158f6-06cb-405f-9272-d95292f8c618","year":1988},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.261125Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:f315418cc18a257b783fc89b96546360e8262b9d167139742e4657a3b72485b7","observation_id":"3211f80e-6455-47c2-b3e6-2878e0a13e03","resolution":{"observed_at":"2026-08-14T13:48:19.682824Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T13:48:19.626443Z","title":"gru_lstm_tv_script,","venue":null,"work_id":"83945bee-41a8-4e29-9634-9b064035de52","year":2019},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.272283Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:58d06a3a4004cfbff0687daa088bb27715aaa2ef7512cd11d58a0f42e8317d20","observation_id":"3affbb6d-6390-4920-8896-85885cdb4507","resolution":{"observed_at":"2026-08-14T13:48:19.637857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T13:48:19.587217Z","title":"Game of Thrones Data,","venue":null,"work_id":"626b9f59-ff6a-468d-af73-061c0f67fdc7","year":2019},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.286509Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:e5b65c862aae195993b95a779b196d7969499e358c8277f41a437fb7bca495ca","observation_id":"0a1e9284-ecc6-4ae5-aa9d-9924b65ecdb1","resolution":{"observed_at":"2026-08-14T13:48:19.597798Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T13:48:19.547977Z","title":"generated_text,","venue":null,"work_id":"4bf4d3a1-5f1e-42ee-b3cf-b2ebf62f68f8","year":2019},"citing_paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T13:48:19.295633Z"},"links":{"citing_paper":"/paper/1908.04332"},"observation_digest":"sha256:a249a8dc93b192f3674429ca4607bee86f4d28d623a35200a7205a2c270c308b","observation_id":"09df59c5-91bd-414a-a71d-4062b8c70fe4","resolution":{"observed_at":"2026-08-14T13:48:19.558470Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1908.04332","last_updated":"2019-08-12T18:39:10Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T04:40:06.749813Z","submitted_at":"2019-08-12T18:39:10Z","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation"},"reference_resolution":{"displayed":25,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":5,"verified_exact":0,"verified_fuzzy":20},"total_outbound_references":25},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 0 inbound Pith citation observations for arXiv:1908.04332."}