{"as_of":"2026-08-20T12:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6865e751af5d7c8395e8ed3a8f618f2a60cb6a82c444c15c7862fdd24db3fffa","coverage":[{"denominator":7,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":7,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-30T11:28:29.391851Z","state":"measured"},{"denominator":8,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":8,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T04:37:21.478819Z","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":"2026-08-14T04:37:21.891300Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2605.26343","last_updated":"2026-06-28T17:43:23Z","snapshot_observed_at":"2026-08-20T09:32:42.505041Z","submitted_at":"2026-05-25T21:32:57Z","title":"MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability","version":2},"cited_work":{"arxiv_id":"2605.26343","doi":null,"metadata_source":"pith","pith_arxiv_id":"2605.26343","snapshot_observed_at":"2026-08-14T04:37:21.891300Z","title":"MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability","venue":"cs.LG","work_id":"e307ca26-0126-4d70-b496-9551047c797a","year":2026},"citing_paper":{"arxiv_id":"2608.08536","last_updated":"2026-08-09T07:14:13Z","snapshot_observed_at":"2026-08-19T18:44:33.828775Z","submitted_at":"2026-08-09T07:14:13Z","title":"Can Graph Learning Learn Circuits?","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-14T04:37:21.478819Z"},"links":{"cited_paper":"/paper/2605.26343","citing_paper":"/paper/2608.08536"},"observation_digest":"sha256:bdf201e4743bb06a796585bfe2e9ec0df0c180bdd6851026382b03603b875436","observation_id":"aedab491-bb82-450f-9745-760b271543e4","resolution":{"observed_at":"2026-08-14T04:37:21.896236Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2605.26343/citation-record","integrity":"/paper/2605.26343/integrity","json":"/paper/2605.26343/citation-record.json","paper":"/paper/2605.26343"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T10:06:10.241841Z","title":"Towards automated circuit discovery for mechanistic interpretability","venue":null,"work_id":"46a77475-775e-4a47-9a38-6fea9f763087","year":2023},"citing_paper":{"arxiv_id":"2605.26343","last_updated":"2026-06-28T17:43:23Z","snapshot_observed_at":"2026-08-20T09:32:42.505041Z","submitted_at":"2026-05-25T21:32:57Z","title":"MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-06-30T11:28:29.391851Z"},"links":{"citing_paper":"/paper/2605.26343"},"observation_digest":"sha256:ba4f2b2e6f9615590b725eb02b460dbb8966a9ed6307aa79da8dc9e68c2ea03a","observation_id":"a81839fe-1001-439f-81fe-7b50e35ca24c","resolution":{"observed_at":"2026-07-09T10:06:10.243217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T10:06:10.231319Z","title":"A mathematical framework for transformer circuits","venue":null,"work_id":"a2753dcc-62bb-4e80-ab63-767470a04209","year":2021},"citing_paper":{"arxiv_id":"2605.26343","last_updated":"2026-06-28T17:43:23Z","snapshot_observed_at":"2026-08-20T09:32:42.505041Z","submitted_at":"2026-05-25T21:32:57Z","title":"MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-06-30T11:28:29.391851Z"},"links":{"citing_paper":"/paper/2605.26343"},"observation_digest":"sha256:4fe0c24fe71f18085be98a6f001216080cc73d2d92c8fc496ac42586b96c5e56","observation_id":"eb619642-b9fe-4722-b99e-16b8fcfd1744","resolution":{"observed_at":"2026-07-09T10:06:10.232951Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T10:06:10.237860Z","title":"A circuit for Python docstrings in a 4-layer attention-only transformer","venue":null,"work_id":"806a76fd-ba22-4334-8afa-80bbc28baaf9","year":2023},"citing_paper":{"arxiv_id":"2605.26343","last_updated":"2026-06-28T17:43:23Z","snapshot_observed_at":"2026-08-20T09:32:42.505041Z","submitted_at":"2026-05-25T21:32:57Z","title":"MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-06-30T11:28:29.391851Z"},"links":{"citing_paper":"/paper/2605.26343"},"observation_digest":"sha256:5b85b2b7c212f4e3a8ba9f26ae2d5766b3118e49d5105d39557a6d2e0c816ce0","observation_id":"e03b03cb-7cbe-443c-958e-725828609baa","resolution":{"observed_at":"2026-07-09T10:06:10.239188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T10:06:10.233811Z","title":"Attribution patching: Activation patching at industrial scale","venue":null,"work_id":"a09754de-4071-48c3-8d2d-783c8a6ec442","year":2023},"citing_paper":{"arxiv_id":"2605.26343","last_updated":"2026-06-28T17:43:23Z","snapshot_observed_at":"2026-08-20T09:32:42.505041Z","submitted_at":"2026-05-25T21:32:57Z","title":"MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-06-30T11:28:29.391851Z"},"links":{"citing_paper":"/paper/2605.26343"},"observation_digest":"sha256:517456faf3f0145ba656458ae78efac807bc484d7eb78f8cb99726ba6dee113c","observation_id":"8aa17024-6a27-440c-911b-797ca109fe40","resolution":{"observed_at":"2026-07-09T10:06:10.235220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T10:06:10.243790Z","title":"In-context learning and induction heads","venue":null,"work_id":"b9fd09cb-1a68-48d2-bf7f-c673ddda7b1c","year":2022},"citing_paper":{"arxiv_id":"2605.26343","last_updated":"2026-06-28T17:43:23Z","snapshot_observed_at":"2026-08-20T09:32:42.505041Z","submitted_at":"2026-05-25T21:32:57Z","title":"MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-06-30T11:28:29.391851Z"},"links":{"citing_paper":"/paper/2605.26343"},"observation_digest":"sha256:74fd70261bfc267407e2f9443fdc8af838624600d29dcfec55a90981046e0ae1","observation_id":"901c0840-bf4e-4c0e-8c81-bcbaee0f659c","resolution":{"observed_at":"2026-07-09T10:06:10.245140Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T10:06:10.239871Z","title":"Proximal policy optimization algorithms","venue":null,"work_id":"3fd006b3-ce9f-4777-887c-2e1b5edfdf04","year":2017},"citing_paper":{"arxiv_id":"2605.26343","last_updated":"2026-06-28T17:43:23Z","snapshot_observed_at":"2026-08-20T09:32:42.505041Z","submitted_at":"2026-05-25T21:32:57Z","title":"MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-06-30T11:28:29.391851Z"},"links":{"citing_paper":"/paper/2605.26343"},"observation_digest":"sha256:c695cdcafc1febbda7111066a5eaba67f79ea3244dce8ec513fd2ed573b5ec1e","observation_id":"3d52c52b-48e9-4083-9b3b-5a14e9587b85","resolution":{"observed_at":"2026-07-09T10:06:10.241270Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T10:06:10.235788Z","title":"Interpretability in the wild: A circuit for indirect object identification in GPT -2 small","venue":null,"work_id":"8c501056-4c94-47a5-becb-3afcd7ba004c","year":2023},"citing_paper":{"arxiv_id":"2605.26343","last_updated":"2026-06-28T17:43:23Z","snapshot_observed_at":"2026-08-20T09:32:42.505041Z","submitted_at":"2026-05-25T21:32:57Z","title":"MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-06-30T11:28:29.391851Z"},"links":{"citing_paper":"/paper/2605.26343"},"observation_digest":"sha256:d18599ce6dc3c7d4bd0ea94a953d13c78f769e24a1df1bdca49f6fbba0f8844b","observation_id":"526dfb5d-95a5-43cc-8518-096149de8dbc","resolution":{"observed_at":"2026-07-09T10:06:10.237327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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"}}],"paper":{"arxiv_id":"2605.26343","last_updated":"2026-06-28T17:43:23Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-20T09:32:42.505041Z","submitted_at":"2026-05-25T21:32:57Z","title":"MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability"},"reference_resolution":{"displayed":7,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":7},"total_outbound_references":7},"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 7 of 7 outbound references and 1 inbound Pith citation observation for arXiv:2605.26343."}