{"as_of":"2026-08-12T18:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7b68e3e102470b87458ba98176e0b06b3f674768a79ce071a22df4ed3bd40656","coverage":[{"denominator":6,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":6,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T04:54:49.092280Z","state":"measured"},{"denominator":6,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":6,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+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/2412.00944/citation-record","integrity":"/paper/2412.00944/integrity","json":"/paper/2412.00944/citation-record.json","paper":"/paper/2412.00944"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1912.01588","last_updated":"2020-07-26T18:39:26Z","snapshot_observed_at":"2026-08-06T18:05:01.923590Z","submitted_at":"2019-12-03T18:34:03Z","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.01588","snapshot_observed_at":"2026-08-12T04:54:49.062845Z","title":"Leveraging procedural generation to benchmark reinforcement learning, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.00944","last_updated":"2024-12-01T19:32:04Z","snapshot_observed_at":"2026-08-12T04:48:25.357284Z","submitted_at":"2024-12-01T19:32:04Z","title":"Bilinear Convolution Decomposition for Causal RL Interpretability","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-12T04:54:49.062845Z"},"links":{"cited_paper":"/paper/1912.01588","citing_paper":"/paper/2412.00944"},"observation_digest":"sha256:43dd14b8ac5b22aed1fb54cc5cabf8c265083055eeb274d370aa1f7d32753520","observation_id":"7cd0f961-0f24-48d1-acc7-6ebb1642d356","resolution":{"observed_at":"2026-08-12T04:54:49.062845Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.01561","last_updated":"2018-06-28T06:54:39Z","snapshot_observed_at":"2026-07-06T06:21:49.379500Z","submitted_at":"2018-02-05T18:47:30Z","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.01561","snapshot_observed_at":"2026-08-12T04:54:49.069229Z","title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.00944","last_updated":"2024-12-01T19:32:04Z","snapshot_observed_at":"2026-08-12T04:48:25.357284Z","submitted_at":"2024-12-01T19:32:04Z","title":"Bilinear Convolution Decomposition for Causal RL Interpretability","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-12T04:54:49.069229Z"},"links":{"cited_paper":"/paper/1802.01561","citing_paper":"/paper/2412.00944"},"observation_digest":"sha256:5861c28f1f3ade0969a0624fdad64cb49f65f2def81527e679dc656ee8dcc474","observation_id":"30932dcd-0afc-4cf7-b23d-1156aedd7cc6","resolution":{"observed_at":"2026-08-12T04:54:49.069229Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.08417","last_updated":"2025-06-25T10:36:59Z","snapshot_observed_at":"2026-08-10T15:04:26.349085Z","submitted_at":"2024-10-10T23:22:11Z","title":"Bilinear MLPs enable weight-based mechanistic interpretability","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.08417","snapshot_observed_at":"2026-08-12T04:54:49.074872Z","title":"T., Dooms, T., Rigg, A., Oramas, J","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00944","last_updated":"2024-12-01T19:32:04Z","snapshot_observed_at":"2026-08-12T04:48:25.357284Z","submitted_at":"2024-12-01T19:32:04Z","title":"Bilinear Convolution Decomposition for Causal RL Interpretability","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-12T04:54:49.074872Z"},"links":{"cited_paper":"/paper/2410.08417","citing_paper":"/paper/2412.00944"},"observation_digest":"sha256:3fa2a0b9583a4e9049d86356c533b5108e2d4c3cea75c96a418ed3c93af3cadc","observation_id":"8fe9ce05-d47c-4d6e-a664-2267b6887697","resolution":{"observed_at":"2026-08-12T04:54:49.074872Z","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":"2026-08-12T04:54:49.205008Z","title":"A technical note on bilinear layers for interpretability, 2023","venue":null,"work_id":"d39160b6-ee21-43a9-8006-704b8afb2603","year":2023},"citing_paper":{"arxiv_id":"2412.00944","last_updated":"2024-12-01T19:32:04Z","snapshot_observed_at":"2026-08-12T04:48:25.357284Z","submitted_at":"2024-12-01T19:32:04Z","title":"Bilinear Convolution Decomposition for Causal RL Interpretability","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-12T04:54:49.081150Z"},"links":{"citing_paper":"/paper/2412.00944"},"observation_digest":"sha256:c626ccd32dc4c1a78ad2890fb3630c9efd30da3601a9661d4b070208f801a144","observation_id":"544d5190-7ce7-4041-ad36-a735a2cfff4c","resolution":{"observed_at":"2026-08-12T04:54:49.212069Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.05202","last_updated":"2020-02-12T19:57:13Z","snapshot_observed_at":"2026-08-11T06:21:56.129166Z","submitted_at":"2020-02-12T19:57:13Z","title":"GLU Variants Improve Transformer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.05202","snapshot_observed_at":"2026-08-12T04:54:49.086784Z","title":"Glu variants improve transformer, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.00944","last_updated":"2024-12-01T19:32:04Z","snapshot_observed_at":"2026-08-12T04:48:25.357284Z","submitted_at":"2024-12-01T19:32:04Z","title":"Bilinear Convolution Decomposition for Causal RL Interpretability","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-12T04:54:49.086784Z"},"links":{"cited_paper":"/paper/2002.05202","citing_paper":"/paper/2412.00944"},"observation_digest":"sha256:9a029c5f7cb561b5824029c8cca75554852c046f56470378e785335851084d20","observation_id":"f4f0eb27-49c5-44d0-a139-0b644c63119b","resolution":{"observed_at":"2026-08-12T04:54:49.086784Z","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":"2026-08-12T04:54:49.092280Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.00944","last_updated":"2024-12-01T19:32:04Z","snapshot_observed_at":"2026-08-12T04:48:25.357284Z","submitted_at":"2024-12-01T19:32:04Z","title":"Bilinear Convolution Decomposition for Causal RL Interpretability","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-12T04:54:49.092280Z"},"links":{"citing_paper":"/paper/2412.00944"},"observation_digest":"sha256:b1d30bba6a0748a9ed223651451712501eb2b109fb377915cde8aef1e3ffc337","observation_id":"cdeb06cd-fabd-4717-8684-477985ae0c78","resolution":{"observed_at":"2026-08-12T04:54:49.092280Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.00944","last_updated":"2024-12-01T19:32:04Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T04:48:25.357284Z","submitted_at":"2024-12-01T19:32:04Z","title":"Bilinear Convolution Decomposition for Causal RL Interpretability"},"reference_resolution":{"displayed":6,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":5,"verified_exact":0,"verified_fuzzy":1},"total_outbound_references":6},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 6 of 6 outbound references and 0 inbound Pith citation observations for arXiv:2412.00944."}