{"as_of":"2026-08-16T17:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dce8da93fcde3a057e6a73e95235d6cf90905e66779a359985b03e28d27239cc","coverage":[{"denominator":28,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":28,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T15:01:13.326513Z","state":"measured"},{"denominator":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"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/1908.02037/citation-record","integrity":"/paper/1908.02037/integrity","json":"/paper/1908.02037/citation-record.json","paper":"/paper/1908.02037"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T15:01:13.646189Z","title":"Analysis of engagement and user experience with a laughter responsive social robot,","venue":null,"work_id":"34ba145b-784a-4b29-b122-1f89daf49772","year":2017},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.231854Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:baf724744ad16ba8686b20629049136f17a594bdc31c4283eb51a30ef8406f08","observation_id":"629403b6-76df-4f7d-82a7-cf4897cc09e6","resolution":{"observed_at":"2026-08-14T15:01:13.649775Z","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":"2026-08-14T15:01:13.635857Z","title":"Timing and entrainment of multimodal backchanneling behavior for an embodied conversational agent,","venue":null,"work_id":"92f8274e-3b4d-4fbf-af68-906b50bf0f6d","year":2013},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.235911Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:f49c6ccaf7f3967d675306d290036d7f92a930c7c145a3e50fb72e3dd271ee72","observation_id":"3ce93b11-335d-4c5c-9b07-1d903bbf9ab9","resolution":{"observed_at":"2026-08-14T15:01:13.639467Z","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":"2026-08-14T15:01:13.624750Z","title":"Definitions of engagement in human-agent interaction,","venue":null,"work_id":"02d9c21e-efdc-42a8-a006-32bc27389f9c","year":2015},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.239317Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:2d9a85efb590971507a7be52fde7b639208e511118077a2332301d1934b4f567","observation_id":"80c1b059-43fe-4ee6-bf3b-6ab3b41d0e0b","resolution":{"observed_at":"2026-08-14T15:01:13.628728Z","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":"2026-08-14T15:01:13.613296Z","title":"Poggi, Mind, hands, face and body: a goal and belief view of multimodal communication","venue":null,"work_id":"953470c9-b7d9-4f7f-b080-4dcedf9b8ce1","year":2007},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.243464Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:bff888e5a92dbd8137c7cb32b1d50ca28c32b72d3b99f4e63306bd242dea2d6e","observation_id":"07f7e90a-c53e-42e2-b6c8-ee3c09890f3b","resolution":{"observed_at":"2026-08-14T15:01:13.617460Z","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":"1507.06527","last_updated":"2017-01-11T20:25:54Z","snapshot_observed_at":"2026-08-14T22:39:17.382664Z","submitted_at":"2015-07-23T15:16:46Z","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1507.06527","snapshot_observed_at":"2026-08-14T15:01:13.247809Z","title":"Deep recurrent q-learning for partially observable mdps,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.247809Z"},"links":{"cited_paper":"/paper/1507.06527","citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:ac49a43873b0e084b49ca7245e0d96eeb2564d5f7ef239e5518fcd72b509cdd2","observation_id":"d3a8c68c-8d5f-455a-8354-b2e4cff02d2c","resolution":{"observed_at":"2026-08-14T15:01:13.247809Z","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":"2026-08-14T15:01:13.252437Z","title":"Q-learning,","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.252437Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:2a9f2c0e32f4558a6f5ed6b9ecb9461d43b3f4c7d6bf922b99d4fbebc29e3f03","observation_id":"5993df38-fdf6-44cc-a986-c3924466429d","resolution":{"observed_at":"2026-08-14T15:01:13.252437Z","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":"2026-08-14T15:01:13.594130Z","title":null,"venue":null,"work_id":"f2eed6c1-aa18-4e8c-bc76-29b63bba9cbc","year":1998},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.256371Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:8c34927a1b5631f64680f1290b3e757fbdc2a10c1cf86e9798cddad5a38156f1","observation_id":"0c31758a-b30b-478f-a5d6-567ced8cbe49","resolution":{"observed_at":"2026-08-14T15:01:13.597908Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-14T15:01:13.581968Z","title":"Batch reinforcement learning,","venue":null,"work_id":"7931512f-9141-4dde-beb0-cc782e64436e","year":2012},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.259725Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:a70c0de07852afbba0c8d1dad8d80fa176ac2ddd2bef801a339aea20a3ee9bcf","observation_id":"bf384db1-edf5-4cbc-8c1e-ae98e33c4514","resolution":{"observed_at":"2026-08-14T15:01:13.585589Z","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":"2026-08-14T15:01:13.571514Z","title":"Human-level control through deep reinforcement learning,","venue":null,"work_id":"52515fd8-ee61-450b-82ae-c53c7c499568","year":2015},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.263120Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:999fa3b292d35883dbd34e71f0b9fd1c81177065cc591904256a3d43d43ebce7","observation_id":"f80e8beb-e119-4367-9055-f3fd8c91eb6c","resolution":{"observed_at":"2026-08-14T15:01:13.575254Z","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":"2026-08-14T15:01:13.562547Z","title":"Tree-based batch mode reinforcement learning,","venue":null,"work_id":"a1147e83-c8bf-41a0-b388-b084b5ffe462","year":2005},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.266415Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:8c6948ef904450bc41e3e800645f5b64ccb673903e6ee4b71889918fa96ee173","observation_id":"6f5097f4-c362-4048-a6a4-ad15478bffe2","resolution":{"observed_at":"2026-08-14T15:01:13.565622Z","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":"2026-08-14T15:01:13.552164Z","title":"Neural fitted q iteration–first experiences with a data efficient neural reinforcement learning method,","venue":null,"work_id":"5a85a6cc-6f2d-4202-9ec8-ccb74a77ea6a","year":2005},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.269440Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:d9ecca99fac3a28dc129a96764002c355d0e35b47cffa65fe6faae6c666a0ff6","observation_id":"9b8b33a3-1e81-4c45-a9e1-7196c4962d28","resolution":{"observed_at":"2026-08-14T15:01:13.556078Z","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":"2026-08-14T15:01:13.541789Z","title":"Robot gains social intelligence through multimodal deep reinforcement learning,","venue":null,"work_id":"08f2d1f0-0adb-4a4f-b6ea-981174aebec0","year":2016},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.272232Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:ef6c5ef854f1e2f274f758276112abbbefdede6e9f47e60adcdaab4c39ce9526","observation_id":"fa02c569-5869-4cea-8130-7d7f72236022","resolution":{"observed_at":"2026-08-14T15:01:13.545485Z","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":"2026-08-14T15:01:13.529611Z","title":"Show, attend and interact: Perceivable human-robot social interaction through neural attention q-network,","venue":null,"work_id":"f2d8d38c-300b-4784-9488-7dcac7e08acb","year":2017},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.275088Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:3c6b65c91d8173cd2038d4683e769cda6c664ae9a28675635970d4610ff71652","observation_id":"faec84c1-2a04-4d99-9c57-2fdd13786940","resolution":{"observed_at":"2026-08-14T15:01:13.534280Z","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":"2026-08-14T15:01:13.518391Z","title":"Robot behavior adaptation for human-robot interaction based on policy gradient reinforcement learning,","venue":null,"work_id":"1da05758-fbc3-40f5-a896-69d256e461cd","year":2006},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.278419Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:7c954316850881fba8ff94e863a06f336cfd554121c34a8e87c5db53221476fc","observation_id":"bc81b9ae-a074-4e07-bfda-05b06cec44c8","resolution":{"observed_at":"2026-08-14T15:01:13.522166Z","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":"2026-08-14T15:01:13.507878Z","title":"Neural network based reinforcement learning for audio–visual gaze control in human–robot interaction,","venue":null,"work_id":"495da18c-3fd6-4221-9ec8-d14e9c8d88da","year":2019},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.281467Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:3cdd4e654f8c9a4bd73c88bd0ce1d440d6e534411f65731fe4435ad746473bcf","observation_id":"88a6ad9a-7a26-474e-966e-7ec1485ad237","resolution":{"observed_at":"2026-08-14T15:01:13.511710Z","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":"2026-08-14T15:01:13.497529Z","title":"Fostering user engagement in face-to-face human-agent interactions: a survey,","venue":null,"work_id":"fcc99025-e27e-402d-90be-c39e7245cd56","year":2016},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.284635Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:9c50b0d6ce0a1ba5672a44dd7464ebabbc56b521b9b63ddcd23d2e31f02f73f0","observation_id":"5cbe9ba9-996a-4aa6-b412-70622d0f7f80","resolution":{"observed_at":"2026-08-14T15:01:13.500866Z","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":"2026-08-14T15:01:13.486449Z","title":"Generating robot/agent backchannels during a storytelling experiment,","venue":null,"work_id":"5e306ff9-4d5a-409d-bd87-55865d314b40","year":2009},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.287620Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:01720401c7eca2162b185948e13dee1f8ce0e135688beea72610e5c334cff803","observation_id":"3deb7a1a-5320-45fe-b89b-eab1eb94c3c5","resolution":{"observed_at":"2026-08-14T15:01:13.490371Z","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":"2026-08-14T15:01:13.474416Z","title":"Generation of nodding, head tilting and eye gazing for human-robot dialogue interaction,","venue":null,"work_id":"5cea5a18-49d5-4dd6-9670-5ffb2dbdb27a","year":2012},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.290685Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:fea2cb4cefc0187df3f90192719742bbcbcd3897516d5b5537ab275626c4f50d","observation_id":"dbafc922-4f9e-4eb4-a58b-b8f1ca36aad0","resolution":{"observed_at":"2026-08-14T15:01:13.479265Z","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":"2026-08-14T15:01:13.463819Z","title":"Data-driven model of nonverbal behavior for socially assistive human-robot interactions,","venue":null,"work_id":"7bb2e2bf-6a57-4f89-ac39-90c129a2d561","year":2014},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.294306Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:115c3ae7319607813d7d8671c7b254d72f2df3a6beae768085e39dd99c8a2a06","observation_id":"c668c4a4-8576-4ddd-90ed-65091435f368","resolution":{"observed_at":"2026-08-14T15:01:13.467865Z","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":"2026-08-14T15:01:13.453474Z","title":"Recognizing engagement in human-robot interaction,","venue":null,"work_id":"ff2ad052-73fb-41e8-84e3-2b12a08b402c","year":2010},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.297954Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:3a735be0a6c34cb10686e58a00f1a5f01fd684beacdaf7210523fd4424f95574","observation_id":"e61ccbdd-083a-45b5-89ae-bcaf0346f9e3","resolution":{"observed_at":"2026-08-14T15:01:13.457095Z","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":"2026-08-14T15:01:13.443026Z","title":"Iemocap: Interactive emotional dyadic motion capture database,","venue":null,"work_id":"eace4047-5219-4922-9c43-583a99a1501d","year":2008},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.301447Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:8bc7126b12a024507a8cb59821d97e78b906f1fbca8d1d02b524af3fbd5274c2","observation_id":"6f683ea6-d8fe-4ed3-b46a-63be7618cdf0","resolution":{"observed_at":"2026-08-14T15:01:13.446602Z","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":"2026-08-14T15:01:13.431517Z","title":"Multimodal analysis of speech and arm motion for prosody-driven synthesis of beat gestures,","venue":null,"work_id":"1600046a-0d69-4078-87ef-9e4cd56e5e98","year":2016},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.305221Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:e4f50b7fb6bb3e41b57cb0bb5e8b30af7dcc136233d68777a5df828722169703","observation_id":"ff52c2a4-0903-4b1f-a809-95c4989b5a73","resolution":{"observed_at":"2026-08-14T15:01:13.434958Z","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":"2026-08-14T15:01:13.420878Z","title":"Tracking continuous emotional trends of participants during affective dyadic interactions using body language and speech information,","venue":null,"work_id":"9a184649-5b9c-4318-b4d8-544a9e2fb2de","year":2013},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.309504Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:83fac2925a24df731584e8eb4494f3745d7f7740b61c4c38b95310ade7ef6fb5","observation_id":"093301d9-22ba-40de-8881-fc1d340d3470","resolution":{"observed_at":"2026-08-14T15:01:13.424280Z","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":"2026-08-14T15:01:13.410329Z","title":"Residual algorithms: Reinforcement learning with function approximation,","venue":null,"work_id":"c20fc2d2-a6e4-4990-b613-801174e5786a","year":1995},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.312977Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:30bfa2b90a63f23f9c630b1ceee45ecd4b0b2d895c96da0ec8a91a41e7115aa9","observation_id":"ca6eb764-29f4-4a1c-9ece-c258af004ac9","resolution":{"observed_at":"2026-08-14T15:01:13.413830Z","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":"2026-08-14T15:01:13.398912Z","title":"Data-efficient off-policy policy evaluation for reinforcement learning,","venue":null,"work_id":"0d66c8e7-8570-402b-a833-af75387423bc","year":2016},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.316576Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:9fe4bd64dd99dbaf00cee711f8b3b7c9d0f421c889a018206caa0892c104bdb6","observation_id":"339146ee-7a4a-4c47-a908-762ac2a4f991","resolution":{"observed_at":"2026-08-14T15:01:13.402603Z","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":"2026-08-14T15:01:13.387135Z","title":"Importance sampling for fair policy selection","venue":null,"work_id":"e3766fc5-2e6a-4469-8c52-7843917d89e6","year":2017},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.319712Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:48cda9d28d48edbdbcd5726bdd66cc9026cd5aa022bdca53cbb91be6563df208","observation_id":"dfcb2235-968e-4195-83c4-38bf8c414324","resolution":{"observed_at":"2026-08-14T15:01:13.390822Z","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":"1807.01066","last_updated":"2018-07-10T09:21:17Z","snapshot_observed_at":"2026-08-14T18:56:17.294751Z","submitted_at":"2018-07-03T10:20:22Z","title":"Behaviour Policy Estimation in Off-Policy Policy Evaluation: Calibration Matters","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.01066","snapshot_observed_at":"2026-08-14T15:01:13.322853Z","title":"Behaviour policy estimation in off-policy policy evaluation: Calibration matters,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.322853Z"},"links":{"cited_paper":"/paper/1807.01066","citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:2ca629dbfa6109fa235cf4f0018df56f1b54373e181692bbc2a115e1b9b82a5d","observation_id":"bf3e7dc8-4ff1-4e96-aabd-49d72844b742","resolution":{"observed_at":"2026-08-14T15:01:13.322853Z","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":"2026-08-14T15:01:13.373975Z","title":"Fast nearest neighbor search through sparse random projections and voting,","venue":null,"work_id":"b8e425aa-9ac7-477a-a9df-5b9b9c56b4b1","year":2016},"citing_paper":{"arxiv_id":"1908.02037","last_updated":"2019-08-06T09:25:51Z","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T15:01:13.326513Z"},"links":{"citing_paper":"/paper/1908.02037"},"observation_digest":"sha256:919989b0d2f79065e1790bfb6f8de2c5c76ab2710ffa57da875bb4ee28093703","observation_id":"bfc8ab65-334e-47f3-9582-2716b491553b","resolution":{"observed_at":"2026-08-14T15:01:13.380076Z","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":"1908.02037","last_updated":"2019-08-06T09:25:51Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-16T05:21:11.154649Z","submitted_at":"2019-08-06T09:25:51Z","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents"},"reference_resolution":{"displayed":28,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":0,"verified_fuzzy":24},"total_outbound_references":28},"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 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:1908.02037."}