{"as_of":"2026-08-23T19:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9cdef2d005056f7519107d7dad70fbf6f79eceb9666d994ac6212623b66f90ba","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":"2026-08-23T06:30:58.430688+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":"2026-08-07T12:59:39.709667Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-11T09:16:03.069064Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1807.01672","last_updated":"2018-12-06T23:32:05Z","snapshot_observed_at":"2026-08-20T20:01:56.685524Z","submitted_at":"2018-07-04T16:40:53Z","title":"Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.01672","snapshot_observed_at":"2026-08-07T12:59:39.709667Z","title":"Ranked reward: Enabling self-play reinforcement learning for combinatorial optimization.arXiv preprint arXiv:1807.01672, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.23131","last_updated":"2026-06-04T20:53:20Z","snapshot_observed_at":"2026-08-14T22:00:11.264091Z","submitted_at":"2025-05-29T06:04:32Z","title":"DOPPLER: Dual-Policy Learning for Device Assignment in Asynchronous Dataflow Graphs","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T12:59:39.709667Z"},"links":{"cited_paper":"/paper/1807.01672","citing_paper":"/paper/2505.23131"},"observation_digest":"sha256:f71e2497392e79200f316ef14702406191ab817b9c128441360d10caca9ee387","observation_id":"decacaa9-f0b3-40ee-a723-1fcf6afa5fd7","resolution":{"observed_at":"2026-08-07T12:59:39.709667Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.01672","last_updated":"2018-12-06T23:32:05Z","snapshot_observed_at":"2026-08-20T20:01:56.685524Z","submitted_at":"2018-07-04T16:40:53Z","title":"Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.01672","snapshot_observed_at":"2026-08-04T10:26:08.510755Z","title":"K.; Cohen, A.-S.; Kas, D.; Hajjar, K.; Dahl, T","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2510.10057","last_updated":"2026-07-22T06:28:33Z","snapshot_observed_at":"2026-08-16T19:21:47.607439Z","submitted_at":"2025-10-11T06:47:49Z","title":"One4Many-StablePacker: An Efficient Deep Reinforcement Learning Framework for the 3D Bin Packing Problem","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-04T10:26:08.510755Z"},"links":{"cited_paper":"/paper/1807.01672","citing_paper":"/paper/2510.10057"},"observation_digest":"sha256:ca2293aeab65d92f32be4bcb6d1c8aa2a492bbbc07fac99cf8f2625cc884e6f0","observation_id":"2442e345-8c24-4d80-b58d-6f7c2b6438d1","resolution":{"observed_at":"2026-08-04T10:26:08.510755Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.01672","last_updated":"2018-12-06T23:32:05Z","snapshot_observed_at":"2026-08-20T20:01:56.685524Z","submitted_at":"2018-07-04T16:40:53Z","title":"Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization","version":3},"cited_work":{"arxiv_id":"1807.01672","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1807.01672","snapshot_observed_at":"2026-07-04T23:15:04.178370Z","title":"Ranked reward: Enabling self -play reinforcement learning for combinatorial optimization","venue":null,"work_id":"3fe8f3a2-1d13-4cd4-a034-50261f93b251","year":2018},"citing_paper":{"arxiv_id":"2604.10953","last_updated":"2026-04-13T03:50:12Z","snapshot_observed_at":"2026-08-15T10:54:43.691553Z","submitted_at":"2026-04-13T03:50:12Z","title":"Diffusion Reinforcement Learning Based Online 3D Bin Packing Spatial Strategy Optimization","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-10T16:08:12.531857Z"},"links":{"cited_paper":"/paper/1807.01672","citing_paper":"/paper/2604.10953"},"observation_digest":"sha256:5ee184405f0591ef243c7dc2db09adf727e67dde8dc1a221c56c8e3151deac2c","observation_id":"e991ce27-a8d3-44e6-a902-8bdf1d231828","resolution":{"observed_at":"2026-07-04T23:15:04.178370Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1807.01672/citation-record","integrity":"/paper/1807.01672/integrity","json":"/paper/1807.01672/citation-record.json","paper":"/paper/1807.01672"},"outbound":[],"paper":{"arxiv_id":"1807.01672","last_updated":"2018-12-06T23:32:05Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-20T20:01:56.685524Z","submitted_at":"2018-07-04T16:40:53Z","title":"Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization"},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:1807.01672."}