{"as_of":"2026-08-16T11:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6f8da24d768c455431262af7149494c41cbfe3898e42ac960dc14222d331a58e","coverage":[{"denominator":20,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T13:25:16.301672Z","state":"measured"},{"denominator":20,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":20,"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/1908.05117/citation-record","integrity":"/paper/1908.05117/integrity","json":"/paper/1908.05117/citation-record.json","paper":"/paper/1908.05117"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T13:25:16.203369Z","title":"URL: \" 'urlintro :=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.203369Z"},"links":{"citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:1359159058998bbd4b7e0cd43493e58d3915b58265812a39140392d8727ef473","observation_id":"3ae6cdec-0115-4631-9524-1c74d1202b48","resolution":{"observed_at":"2026-08-14T13:25:16.203369Z","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":"2026-08-14T13:25:16.208932Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.208932Z"},"links":{"citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:1e37f07b0c098587286c134471f45225576097ce6473a9eb70be9a8465da9ec4","observation_id":"3be1b737-b0e3-4be6-9e88-11b9d98bff02","resolution":{"observed_at":"2026-08-14T13:25:16.208932Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1607.06450","last_updated":"2016-07-21T19:57:52Z","snapshot_observed_at":"2026-08-15T04:53:45.483331Z","submitted_at":"2016-07-21T19:57:52Z","title":"Layer Normalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1607.06450","snapshot_observed_at":"2026-08-14T13:25:16.213863Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.213863Z"},"links":{"cited_paper":"/paper/1607.06450","citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:6182f8ee35277981e49ac26497fa2c6a96483c5c570fe98efb52cf11e21870a5","observation_id":"19b1b8e4-c29f-4419-9b61-56f059133761","resolution":{"observed_at":"2026-08-14T13:25:16.213863Z","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":"2026-08-14T13:25:16.612672Z","title":null,"venue":null,"work_id":"b0077c2a-b4aa-4e84-8724-f50de9b6fde2","year":2018},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.219439Z"},"links":{"citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:b27b3bb33a8bbba39d426fad080f54ee842c0d4c77785c7e17f106c0e6cbfb85","observation_id":"98093aa8-307c-4ec3-9333-077e1634b5e9","resolution":{"observed_at":"2026-08-14T13:25:16.617327Z","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":{"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":"2026-08-14T13:25:16.224082Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.224082Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:0e40efc6c41bbfdb6715a3741adbbc1bb8221abd2ca0e3fe1ae531f2be96a71e","observation_id":"7971358c-2501-4f56-b72f-b1ff8cff15aa","resolution":{"observed_at":"2026-08-14T13:25:16.224082Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.04987","last_updated":"2018-05-28T19:35:39Z","snapshot_observed_at":"2026-08-14T20:13:58.001445Z","submitted_at":"2017-11-14T07:55:39Z","title":"Unified Pragmatic Models for Generating and Following Instructions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.04987","snapshot_observed_at":"2026-08-14T13:25:16.228977Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.228977Z"},"links":{"cited_paper":"/paper/1711.04987","citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:804008e99c036f7194cb5acf11a786fba285061f7bd6197e552ba1e6cd24d08d","observation_id":"2cd8737d-3468-4725-aaac-375f9e6e1e35","resolution":{"observed_at":"2026-08-14T13:25:16.228977Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1704.07926","last_updated":"2017-04-25T22:51:12Z","snapshot_observed_at":"2026-08-14T21:04:43.945304Z","submitted_at":"2017-04-25T22:51:12Z","title":"From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.07926","snapshot_observed_at":"2026-08-14T13:25:16.234829Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.234829Z"},"links":{"cited_paper":"/paper/1704.07926","citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:ba895a290a53c9b0b7732d83f3c52fd07a664d0abbd3190d8f24f517501f5586","observation_id":"7730a968-a6ef-4adb-894f-6e084ccd0011","resolution":{"observed_at":"2026-08-14T13:25:16.234829Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.06683","last_updated":"2019-04-16T03:17:47Z","snapshot_observed_at":"2026-08-14T18:18:32.009111Z","submitted_at":"2018-10-06T20:46:49Z","title":"FlowQA: Grasping Flow in History for Conversational Machine Comprehension","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.06683","snapshot_observed_at":"2026-08-14T13:25:16.239631Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.239631Z"},"links":{"cited_paper":"/paper/1810.06683","citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:3877decbb30c608c2278e64060897f81dfaf1f39598e3c19482610f27bacddaa","observation_id":"f76ae298-ce02-46d4-b93f-96522897bee2","resolution":{"observed_at":"2026-08-14T13:25:16.239631Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.07341","last_updated":"2018-02-04T04:56:45Z","snapshot_observed_at":"2026-08-14T20:13:09.200503Z","submitted_at":"2017-11-16T03:52:41Z","title":"FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.07341","snapshot_observed_at":"2026-08-14T13:25:16.245221Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.245221Z"},"links":{"cited_paper":"/paper/1711.07341","citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:bb7f718ce8a518cdcfe074265a38a7443b0a1bd741f46157b1211bc48f85e1a5","observation_id":"ea233c72-cfd6-40b6-8ccf-1a2a54d7c7cf","resolution":{"observed_at":"2026-08-14T13:25:16.245221Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.05378","last_updated":"2016-06-16T21:57:11Z","snapshot_observed_at":"2026-08-14T21:52:22.020718Z","submitted_at":"2016-06-16T21:57:11Z","title":"Simpler Context-Dependent Logical Forms via Model Projections","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.05378","snapshot_observed_at":"2026-08-14T13:25:16.250110Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.250110Z"},"links":{"cited_paper":"/paper/1606.05378","citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:2372a57664a86b000394b3e54591968f5dc1616675184125648c7c8a5062fa83","observation_id":"dfb391e7-c4e4-4a67-a933-ace132cb744e","resolution":{"observed_at":"2026-08-14T13:25:16.250110Z","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":"2026-08-14T13:25:16.598114Z","title":null,"venue":null,"work_id":"2c0c20d4-532a-4f6e-8bbf-7de17ffd146a","year":2019},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.255753Z"},"links":{"citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:d4193a74fb51e6842f9a57dd5d8a0c6567459f1a41fbbbc2c79072ebe7344445","observation_id":"6755337d-35f7-4080-bfbb-6ed228225577","resolution":{"observed_at":"2026-08-14T13:25:16.602737Z","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":{"arxiv_id":"1806.03822","last_updated":"2018-06-11T06:10:11Z","snapshot_observed_at":"2026-08-14T19:05:25.482398Z","submitted_at":"2018-06-11T06:10:11Z","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.03822","snapshot_observed_at":"2026-08-14T13:25:16.260737Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.260737Z"},"links":{"cited_paper":"/paper/1806.03822","citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:6faff9e4fd180185da4e7c3dd765ac611f484d758a50cac663ef67c6ecbb5d53","observation_id":"e0add528-a5f2-4997-a6b4-566a41e18e5f","resolution":{"observed_at":"2026-08-14T13:25:16.260737Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.05250","last_updated":"2016-10-11T02:42:36Z","snapshot_observed_at":"2026-08-15T14:23:50.348670Z","submitted_at":"2016-06-16T16:36:00Z","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.05250","snapshot_observed_at":"2026-08-14T13:25:16.265736Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.265736Z"},"links":{"cited_paper":"/paper/1606.05250","citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:6134bf4593c31654438f217271d4ebc0d24c894284c02d5ffca7ac6eacd675db","observation_id":"4a2f28ef-a597-40e6-9b1b-b3044b071388","resolution":{"observed_at":"2026-08-14T13:25:16.265736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1808.07042","last_updated":"2019-03-29T20:50:21Z","snapshot_observed_at":"2026-08-14T18:38:43.776838Z","submitted_at":"2018-08-21T17:52:02Z","title":"CoQA: A Conversational Question Answering Challenge","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1808.07042","snapshot_observed_at":"2026-08-14T13:25:16.270801Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.270801Z"},"links":{"cited_paper":"/paper/1808.07042","citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:fd1101e1974f71fff37bc0409da5fa6e24e5c421647cc5bf5fa44ffa2ad10498","observation_id":"9cafd0d6-ea0d-4110-950d-5a316ebf3ae3","resolution":{"observed_at":"2026-08-14T13:25:16.270801Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.02671","last_updated":"2019-05-15T11:13:54Z","snapshot_observed_at":"2026-08-14T17:19:41.320386Z","submitted_at":"2019-02-07T15:05:46Z","title":"BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.02671","snapshot_observed_at":"2026-08-14T13:25:16.275618Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.275618Z"},"links":{"cited_paper":"/paper/1902.02671","citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:b9fa08ad20ea77c016c7c7390d1a534788d7a788aea7a74f8da74a0beba252e9","observation_id":"d93a1405-b8c4-433f-b4ba-3d511147d8ec","resolution":{"observed_at":"2026-08-14T13:25:16.275618Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.10209","last_updated":"2018-06-08T21:29:05Z","snapshot_observed_at":"2026-08-14T19:11:05.099503Z","submitted_at":"2018-05-25T15:47:38Z","title":"Situated Mapping of Sequential Instructions to Actions with Single-step Reward Observation","version":2},"cited_work":{"arxiv_id":"1805.10209","doi":null,"metadata_source":"pith","pith_arxiv_id":"1805.10209","snapshot_observed_at":"2026-08-14T13:25:16.393029Z","title":"Situated Mapping of Sequential Instructions to Actions with Single-step Reward Observation","venue":"cs.CL","work_id":"468d8d3f-132e-4268-9759-cf360a9d6057","year":2018},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.280455Z"},"links":{"cited_paper":"/paper/1805.10209","citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:d61a844c58b4c4313a350beec3acdfa7b1be2d170ff5127f7e8f4e3db6018eeb","observation_id":"0a1d3873-a497-4ded-820e-251f612411ad","resolution":{"observed_at":"2026-08-14T13:25:16.400185Z","resolver_source":"local_arxiv","status":"verified_exact"},"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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T13:25:16.285730Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.285730Z"},"links":{"citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:842afd95bcd3f556e2e280bfcf35d8947efbdadeae88d2b7ae215d52df1e4b64","observation_id":"27401151-1ed5-474a-82f7-f418fe377cb4","resolution":{"observed_at":"2026-08-14T13:25:16.285730Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.10735","last_updated":"2019-07-02T00:34:44Z","snapshot_observed_at":"2026-08-14T18:22:31.126207Z","submitted_at":"2018-09-27T19:33:03Z","title":"A Qualitative Comparison of CoQA, SQuAD 2.0 and QuAC","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.10735","snapshot_observed_at":"2026-08-14T13:25:16.290332Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.290332Z"},"links":{"cited_paper":"/paper/1809.10735","citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:3a8b422a9ddc02722fc2868d7c2bda602bc80a1ad885d0434a140b14e97680b0","observation_id":"21d4febd-58cc-4a24-a903-cf8e7129112a","resolution":{"observed_at":"2026-08-14T13:25:16.290332Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1804.09541","last_updated":"2018-04-23T11:33:43Z","snapshot_observed_at":"2026-08-14T19:23:07.768012Z","submitted_at":"2018-04-23T11:33:43Z","title":"QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.09541","snapshot_observed_at":"2026-08-14T13:25:16.295210Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.295210Z"},"links":{"cited_paper":"/paper/1804.09541","citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:3f98af71d4a833c4de4ff91fe6472a7612372ce7f44c0ddec96d6db8bf657dec","observation_id":"f614e82b-149b-4b64-acce-91d137c794c2","resolution":{"observed_at":"2026-08-14T13:25:16.295210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.03593","last_updated":"2019-01-02T23:24:54Z","snapshot_observed_at":"2026-08-16T00:54:39.535281Z","submitted_at":"2018-12-10T01:43:14Z","title":"SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.03593","snapshot_observed_at":"2026-08-14T13:25:16.301672Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension","version":3},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-14T13:25:16.301672Z"},"links":{"cited_paper":"/paper/1812.03593","citing_paper":"/paper/1908.05117"},"observation_digest":"sha256:d6853aa0460d6f872cc812bfcd1e29a9f70f5ccbce90c5815e5b91098a68806e","observation_id":"96349b1b-e962-4ec2-accf-bdde8722f1b1","resolution":{"observed_at":"2026-08-14T13:25:16.301672Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"1908.05117","last_updated":"2020-01-17T08:47:23Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T10:45:13.562475Z","submitted_at":"2019-08-14T13:34:40Z","title":"FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension"},"reference_resolution":{"displayed":20,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":20},"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 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:1908.05117."}