{"as_of":"2026-08-20T10:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0c115b0f37ac0b7041b3592a918bd2aae6b6c141d8b902bba1f1faf9906ebfef","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T22:52:23.819700Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T21:17:43.402574Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2005.02575","last_updated":"2020-06-03T23:08:00Z","snapshot_observed_at":"2026-08-18T08:56:21.104037Z","submitted_at":"2020-05-06T03:29:27Z","title":"Active Preference-Based Gaussian Process Regression for Reward Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.02575","snapshot_observed_at":"2026-08-10T20:55:50.075137Z","title":"Active preference-based gaussian process regression for reward learning,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2501.06946","last_updated":"2025-01-12T21:46:57Z","snapshot_observed_at":"2026-08-20T07:06:21.622141Z","submitted_at":"2025-01-12T21:46:57Z","title":"Learning Implicit Social Navigation Behavior using Deep Inverse Reinforcement Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T20:55:50.075137Z"},"links":{"cited_paper":"/paper/2005.02575","citing_paper":"/paper/2501.06946"},"observation_digest":"sha256:e999cdd4c00afd606521fbb10feda9015677540cfdd33a3672d35d5e105604b3","observation_id":"7986c8ac-db51-4892-bf14-1509a6a4b928","resolution":{"observed_at":"2026-08-10T20:55:50.075137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.02575","last_updated":"2020-06-03T23:08:00Z","snapshot_observed_at":"2026-08-18T08:56:21.104037Z","submitted_at":"2020-05-06T03:29:27Z","title":"Active Preference-Based Gaussian Process Regression for Reward Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.02575","snapshot_observed_at":"2026-08-15T22:52:23.819700Z","title":"Ac- tive preference-based gaussian process regression for reward learning,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2505.06079","last_updated":"2025-05-09T14:22:43Z","snapshot_observed_at":"2026-08-19T23:04:35.722733Z","submitted_at":"2025-05-09T14:22:43Z","title":"TREND: Tri-teaching for Robust Preference-based Reinforcement Learning with Demonstrations","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T22:52:23.819700Z"},"links":{"cited_paper":"/paper/2005.02575","citing_paper":"/paper/2505.06079"},"observation_digest":"sha256:51ce3724e09d99a22a0f209bff30990d2f8cc0d3f67615a0941baff6e7bf0afa","observation_id":"3369010c-f1da-4ca0-a102-b717adf3fbd0","resolution":{"observed_at":"2026-08-15T22:52:23.819700Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.02575","last_updated":"2020-06-03T23:08:00Z","snapshot_observed_at":"2026-08-18T08:56:21.104037Z","submitted_at":"2020-05-06T03:29:27Z","title":"Active Preference-Based Gaussian Process Regression for Reward Learning","version":2},"cited_work":{"arxiv_id":"2005.02575","doi":null,"metadata_source":"pith","pith_arxiv_id":"2005.02575","snapshot_observed_at":"2026-08-06T21:17:43.402574Z","title":"Active Preference-Based Gaussian Process Regression for Reward Learning","venue":"cs.RO","work_id":"a07f36b2-45f2-4383-aa35-0c7f3c5a6b56","year":2020},"citing_paper":{"arxiv_id":"2507.00611","last_updated":"2025-07-01T09:43:57Z","snapshot_observed_at":"2026-08-16T08:07:01.402551Z","submitted_at":"2025-07-01T09:43:57Z","title":"Residual Reward Models for Preference-based Reinforcement Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T21:17:39.634424Z"},"links":{"cited_paper":"/paper/2005.02575","citing_paper":"/paper/2507.00611"},"observation_digest":"sha256:b8dccf7253a7ed3a2471d896929c6f02bb8933dcb8a1c8f9cb24d0a9549e18f1","observation_id":"34b88cb9-7994-4e46-8ce1-dfc1bd02b6fb","resolution":{"observed_at":"2026-08-06T21:17:43.559189Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.02575","last_updated":"2020-06-03T23:08:00Z","snapshot_observed_at":"2026-08-18T08:56:21.104037Z","submitted_at":"2020-05-06T03:29:27Z","title":"Active Preference-Based Gaussian Process Regression for Reward Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.02575","snapshot_observed_at":"2026-07-14T05:38:58.035337Z","title":"Active preference-based gaussian process regression for reward learning.arXiv preprint arXiv:2005.02575,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.11432","last_updated":"2026-07-13T11:37:27Z","snapshot_observed_at":"2026-08-18T08:56:30.755902Z","submitted_at":"2026-07-13T11:37:27Z","title":"Generalizing Preference-based Reinforcement Learning: a Rationality Model for Incomparability","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-14T05:38:58.035337Z"},"links":{"cited_paper":"/paper/2005.02575","citing_paper":"/paper/2607.11432"},"observation_digest":"sha256:b811d7394ed7b9f131cfed6d3abe0c72ac80d1894a8ca0c0b92adf597df3cf88","observation_id":"f0f231be-1acc-4612-8e83-f3a3a9ba6fef","resolution":{"observed_at":"2026-07-14T05:38:58.035337Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2005.02575/citation-record","integrity":"/paper/2005.02575/integrity","json":"/paper/2005.02575/citation-record.json","paper":"/paper/2005.02575"},"outbound":[],"paper":{"arxiv_id":"2005.02575","last_updated":"2020-06-03T23:08:00Z","latest_version":2,"primary_category":"cs.RO","snapshot_observed_at":"2026-08-18T08:56:21.104037Z","submitted_at":"2020-05-06T03:29:27Z","title":"Active Preference-Based Gaussian Process Regression for Reward Learning"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2005.02575."}