{"as_of":"2026-08-09T13:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:23a24f26f81fcb4334d97249a3d3009b01d54d0903bde12c9300782308a05bfc","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":"2026-08-09T06:31:02.800959+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":"2026-08-01T22:03:47.847142Z","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":"2026-07-03T00:07:28.650206Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.13710","last_updated":"2024-11-17T22:32:53Z","snapshot_observed_at":"2026-07-06T19:18:53.582890Z","submitted_at":"2024-09-06T16:17:06Z","title":"You can remove GPT2's LayerNorm by fine-tuning","version":2},"cited_work":{"arxiv_id":"2409.13710","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2409.13710","snapshot_observed_at":"2026-07-03T00:07:28.650206Z","title":"You can remove gpt2’s layernorm by fine-tuning.arXiv preprint arXiv:2409.13710","venue":null,"work_id":"2fadd615-c21c-4033-8955-0356491391a7","year":2024},"citing_paper":{"arxiv_id":"2510.23912","last_updated":"2026-04-23T06:11:56Z","snapshot_observed_at":"2026-08-04T11:05:56.199122Z","submitted_at":"2025-10-27T22:39:34Z","title":"Key and Value Weights Are Probably All You Need: On the Necessity of the Query, Key, Value weight Triplet in Self-Attention Transformers","version":7},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-18T03:38:36.932424Z"},"links":{"cited_paper":"/paper/2409.13710","citing_paper":"/paper/2510.23912"},"observation_digest":"sha256:7d910cecc9c5822cb5087450e6c556f93d4934902fbc5f8e5c7ff99f94c9184e","observation_id":"696aec1f-3d23-47dd-893c-e4920248d475","resolution":{"observed_at":"2026-05-18T03:40:50.489589Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.13710","last_updated":"2024-11-17T22:32:53Z","snapshot_observed_at":"2026-07-06T19:18:53.582890Z","submitted_at":"2024-09-06T16:17:06Z","title":"You can remove GPT2's LayerNorm by fine-tuning","version":2},"cited_work":{"arxiv_id":"2409.13710","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2409.13710","snapshot_observed_at":"2026-07-03T00:07:28.650206Z","title":"You can remove gpt2’s layernorm by fine-tuning.arXiv preprint arXiv:2409.13710","venue":null,"work_id":"2fadd615-c21c-4033-8955-0356491391a7","year":2024},"citing_paper":{"arxiv_id":"2606.09940","last_updated":"2026-06-08T00:15:44Z","snapshot_observed_at":"2026-07-06T23:49:12.754871Z","submitted_at":"2026-06-08T00:15:44Z","title":"Interactions Between Crosscoder Features: A Compact Proofs Perspective","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-06-27T17:25:55.152823Z"},"links":{"cited_paper":"/paper/2409.13710","citing_paper":"/paper/2606.09940"},"observation_digest":"sha256:764cbda6fd8366f4f743ebee7905b23e19eab2ff361b5089cb18002bbd5d0227","observation_id":"97e7c7a8-9661-4146-b28e-1310bdd64260","resolution":{"observed_at":"2026-07-03T00:07:28.651968Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.13710","last_updated":"2024-11-17T22:32:53Z","snapshot_observed_at":"2026-07-06T19:18:53.582890Z","submitted_at":"2024-09-06T16:17:06Z","title":"You can remove GPT2's LayerNorm by fine-tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.13710","snapshot_observed_at":"2026-08-01T22:03:47.847142Z","title":"arXiv preprint arXiv:2409.13710 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.15893","last_updated":"2026-07-20T09:15:04Z","snapshot_observed_at":"2026-08-06T03:20:22.645111Z","submitted_at":"2026-07-17T12:07:59Z","title":"Induction in Both Directions: A Mechanistic Analysis of In-Context Learning in Masked Diffusion Language Models","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-01T22:03:47.847142Z"},"links":{"cited_paper":"/paper/2409.13710","citing_paper":"/paper/2607.15893"},"observation_digest":"sha256:3632de4b18293ac7ea1192c21efbeb46b0d38a884d9b7c1a99b8aa3ec7bcc120","observation_id":"dbfe7642-9732-4edd-9462-061916c160c1","resolution":{"observed_at":"2026-08-01T22:03:47.847142Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2409.13710/citation-record","integrity":"/paper/2409.13710/integrity","json":"/paper/2409.13710/citation-record.json","paper":"/paper/2409.13710"},"outbound":[],"paper":{"arxiv_id":"2409.13710","last_updated":"2024-11-17T22:32:53Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T19:18:53.582890Z","submitted_at":"2024-09-06T16:17:06Z","title":"You can remove GPT2's LayerNorm by fine-tuning"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2409.13710."}