{"as_of":"2026-08-10T18:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9c55f4b96adf078cb51a76f3c799a9308373ddf2f90aa2b1226b835b0260da67","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":"2026-08-10T06:31:04.303077+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":"2026-08-09T13:46:43.599362Z","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":"2026-05-11T23:26:12.787211Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.05409","last_updated":"2025-01-13T11:35:37Z","snapshot_observed_at":"2026-08-10T17:45:11.579801Z","submitted_at":"2024-05-08T20:23:24Z","title":"Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.05409","snapshot_observed_at":"2026-08-09T13:46:43.599362Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.02007","last_updated":"2025-02-20T03:38:38Z","snapshot_observed_at":"2026-08-10T07:06:07.756557Z","submitted_at":"2025-02-04T04:46:41Z","title":"Reasoning Bias of Next Token Prediction Training","version":2},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-09T13:46:43.599362Z"},"links":{"cited_paper":"/paper/2405.05409","citing_paper":"/paper/2502.02007"},"observation_digest":"sha256:58db14a8a235118374aef56825a02efb78881df6b40d2dede87028eae64dc74c","observation_id":"98a53005-a589-4721-9d72-b65c5d036bc9","resolution":{"observed_at":"2026-08-09T13:46:43.599362Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.05409","last_updated":"2025-01-13T11:35:37Z","snapshot_observed_at":"2026-08-10T17:45:11.579801Z","submitted_at":"2024-05-08T20:23:24Z","title":"Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing","version":5},"cited_work":{"arxiv_id":"2405.05409","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.05409","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Initialization is critical to whether transformers fit composite functions by inference or memorizing.arXiv preprint arXiv:2405.05409","venue":null,"work_id":"6e8c48ef-d60a-4ee0-9a78-f1866376fb28","year":null},"citing_paper":{"arxiv_id":"2605.03667","last_updated":"2026-05-05T12:04:51Z","snapshot_observed_at":"2026-08-07T08:19:40.429347Z","submitted_at":"2026-05-05T12:04:51Z","title":"ELAS: Efficient Pre-Training of Low-Rank Large Language Models via 2:4 Activation Sparsity","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-07T17:07:18.278784Z"},"links":{"cited_paper":"/paper/2405.05409","citing_paper":"/paper/2605.03667"},"observation_digest":"sha256:07091fd244e0a4050f63ebde3cb77012d7eee042fd32d4ab87e3e5586a9de203","observation_id":"13604e9b-b46d-403b-b4c8-146ca1bdf252","resolution":{"observed_at":"2026-05-11T23:26:12.790391Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.05409","last_updated":"2025-01-13T11:35:37Z","snapshot_observed_at":"2026-08-10T17:45:11.579801Z","submitted_at":"2024-05-08T20:23:24Z","title":"Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.05409","snapshot_observed_at":"2026-08-01T17:31:50.701835Z","title":"Initial- ization is critical to whether transformer fits composite function by inference or memorizing","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17624","last_updated":"2026-07-20T07:26:17Z","snapshot_observed_at":"2026-08-07T13:43:21.717264Z","submitted_at":"2026-07-20T07:26:17Z","title":"Can Transformers Really Do It All? On the Compatibility of Inductive Biases Across Tasks","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-01T17:31:50.701835Z"},"links":{"cited_paper":"/paper/2405.05409","citing_paper":"/paper/2607.17624"},"observation_digest":"sha256:a32b22b5b1e87c207d51b3c1cbaca68bceaad49f6a308a70312d333c3987f0de","observation_id":"4efd00a0-ec58-49a5-8b3d-9ef47b08e1f4","resolution":{"observed_at":"2026-08-01T17:31:50.701835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2405.05409/citation-record","integrity":"/paper/2405.05409/integrity","json":"/paper/2405.05409/citation-record.json","paper":"/paper/2405.05409"},"outbound":[],"paper":{"arxiv_id":"2405.05409","last_updated":"2025-01-13T11:35:37Z","latest_version":5,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T17:45:11.579801Z","submitted_at":"2024-05-08T20:23:24Z","title":"Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2405.05409."}