{"as_of":"2026-08-15T00:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d2392518efcd709f135cec8530868efa8d38b99c5d82dde8332034821a859e28","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T04:37:02.231133Z","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":"2026-08-06T19:58:21.615308Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2001.06781","last_updated":"2020-01-19T06:07:20Z","snapshot_observed_at":"2026-08-12T08:18:30.586561Z","submitted_at":"2020-01-19T06:07:20Z","title":"FRESH: Interactive Reward Shaping in High-Dimensional State Spaces using Human Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.06781","snapshot_observed_at":"2026-08-10T04:37:02.231133Z","title":"Fresh: Interactive reward shaping in high-dimensional state spaces using human feedback","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2501.17842","last_updated":"2025-01-29T18:46:35Z","snapshot_observed_at":"2026-08-14T14:34:41.863531Z","submitted_at":"2025-01-29T18:46:35Z","title":"From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learning","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-10T04:37:02.231133Z"},"links":{"cited_paper":"/paper/2001.06781","citing_paper":"/paper/2501.17842"},"observation_digest":"sha256:142082b317cb6e43a2324440281e1d2d6972d3d55e1ee065778a0b6e0842f4d5","observation_id":"156d6535-e62d-4ad4-b6ed-8181b30129fc","resolution":{"observed_at":"2026-08-10T04:37:02.231133Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.06781","last_updated":"2020-01-19T06:07:20Z","snapshot_observed_at":"2026-08-12T08:18:30.586561Z","submitted_at":"2020-01-19T06:07:20Z","title":"FRESH: Interactive Reward Shaping in High-Dimensional State Spaces using Human Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.06781","snapshot_observed_at":"2026-08-07T23:51:35.773348Z","title":"Fresh: Interactive reward shaping in high-dimensional state spaces using human feedback","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2502.08759","last_updated":"2025-02-12T20:03:56Z","snapshot_observed_at":"2026-08-14T13:20:09.129807Z","submitted_at":"2025-02-12T20:03:56Z","title":"Contextual bandits with entropy-based human feedback","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T23:51:35.773348Z"},"links":{"cited_paper":"/paper/2001.06781","citing_paper":"/paper/2502.08759"},"observation_digest":"sha256:86606d7093ab502300c1a44bad76c4266d0c75931df8078410c1708e4a914fa7","observation_id":"3eb569e2-74e1-4e2e-b5be-a6537b2ea515","resolution":{"observed_at":"2026-08-07T23:51:35.773348Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.06781","last_updated":"2020-01-19T06:07:20Z","snapshot_observed_at":"2026-08-12T08:18:30.586561Z","submitted_at":"2020-01-19T06:07:20Z","title":"FRESH: Interactive Reward Shaping in High-Dimensional State Spaces using Human Feedback","version":1},"cited_work":{"arxiv_id":"2001.06781","doi":null,"metadata_source":"pith","pith_arxiv_id":"2001.06781","snapshot_observed_at":"2026-08-06T19:58:21.615308Z","title":"FRESH: Interactive Reward Shaping in High-Dimensional State Spaces using Human Feedback","venue":"cs.AI","work_id":"2658affb-192d-48a3-85c6-4ab98ea42f48","year":2020},"citing_paper":{"arxiv_id":"2507.04187","last_updated":"2025-07-05T23:40:55Z","snapshot_observed_at":"2026-08-12T08:18:10.369354Z","submitted_at":"2025-07-05T23:40:55Z","title":"Where to Intervene: Action Selection in Deep Reinforcement Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T19:58:20.970823Z"},"links":{"cited_paper":"/paper/2001.06781","citing_paper":"/paper/2507.04187"},"observation_digest":"sha256:f75a247f123089b5e8ecd0365a41422fd78d807175bc8a8541edeebb303f5e1b","observation_id":"71d44aa7-5877-4d8c-92cb-277a1e0e7ac9","resolution":{"observed_at":"2026-08-06T19:58:21.676126Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2001.06781/citation-record","integrity":"/paper/2001.06781/integrity","json":"/paper/2001.06781/citation-record.json","paper":"/paper/2001.06781"},"outbound":[],"paper":{"arxiv_id":"2001.06781","last_updated":"2020-01-19T06:07:20Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-12T08:18:30.586561Z","submitted_at":"2020-01-19T06:07:20Z","title":"FRESH: Interactive Reward Shaping in High-Dimensional State Spaces using Human Feedback"},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2001.06781."}