{"as_of":"2026-08-22T12:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a930a16d6c33794cc6fdac6fa63b982d4a1d55777f78367093eaafdd3ef44206","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":5,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":5,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+00:00","state":"measured"},{"denominator":5,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":5,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T04:17:09.279667Z","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":"2026-05-19T08:22:11.201213Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.01432","last_updated":"2024-12-02T10:48:36Z","snapshot_observed_at":"2026-08-16T14:13:23.227671Z","submitted_at":"2024-03-03T08:07:55Z","title":"Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.01432","snapshot_observed_at":"2026-08-07T14:17:58.286417Z","title":"Fine tuning vs","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.19433","last_updated":"2025-06-01T13:59:15Z","snapshot_observed_at":"2026-08-16T17:51:48.234243Z","submitted_at":"2025-05-26T02:49:07Z","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T14:17:58.286417Z"},"links":{"cited_paper":"/paper/2403.01432","citing_paper":"/paper/2505.19433"},"observation_digest":"sha256:669ae7463ba104bc093b10a459b839a15c748e6cf04c5cd2228bb9511f29c377","observation_id":"bfee7631-30d6-44bd-af46-accee6c6df5a","resolution":{"observed_at":"2026-08-07T14:17:58.286417Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.01432","last_updated":"2024-12-02T10:48:36Z","snapshot_observed_at":"2026-08-16T14:13:23.227671Z","submitted_at":"2024-03-03T08:07:55Z","title":"Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge","version":5},"cited_work":{"arxiv_id":"2403.01432","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.01432","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fine tuning vs","venue":null,"work_id":"31d549dd-ab1d-4656-a728-4a2485c5eca9","year":2024},"citing_paper":{"arxiv_id":"2506.18027","last_updated":"2026-04-07T08:01:49Z","snapshot_observed_at":"2026-08-15T02:42:42.443330Z","submitted_at":"2025-06-22T13:14:19Z","title":"PDF Retrieval Augmented Question Answering","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-19T08:17:19.048914Z"},"links":{"cited_paper":"/paper/2403.01432","citing_paper":"/paper/2506.18027"},"observation_digest":"sha256:09d951cd463cf8aabf7eeee40921bf465cb36f5a27ebc9c80fdff71405ae0d5e","observation_id":"234e9fd1-c2c6-4ea6-b3ec-b6d445c6e9b5","resolution":{"observed_at":"2026-05-19T08:22:11.205057Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.01432","last_updated":"2024-12-02T10:48:36Z","snapshot_observed_at":"2026-08-16T14:13:23.227671Z","submitted_at":"2024-03-03T08:07:55Z","title":"Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge","version":5},"cited_work":{"arxiv_id":"2403.01432","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.01432","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fine tuning vs","venue":null,"work_id":"31d549dd-ab1d-4656-a728-4a2485c5eca9","year":2024},"citing_paper":{"arxiv_id":"2604.27415","last_updated":"2026-04-30T04:35:43Z","snapshot_observed_at":"2026-08-08T21:42:05.972268Z","submitted_at":"2026-04-30T04:35:43Z","title":"ChipLingo: A Systematic Training Framework for Large Language Models in EDA","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-07T09:40:25.666277Z"},"links":{"cited_paper":"/paper/2403.01432","citing_paper":"/paper/2604.27415"},"observation_digest":"sha256:02a126e00d9ed032b70a1c97af6f8fef393960b1f08f53370714fba6a2035a98","observation_id":"1d5eed76-425d-4215-8288-a6bccf5134f9","resolution":{"observed_at":"2026-05-12T09:41:27.241837Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.01432","last_updated":"2024-12-02T10:48:36Z","snapshot_observed_at":"2026-08-16T14:13:23.227671Z","submitted_at":"2024-03-03T08:07:55Z","title":"Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge","version":5},"cited_work":{"arxiv_id":"2403.01432","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.01432","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fine tuning vs","venue":null,"work_id":"31d549dd-ab1d-4656-a728-4a2485c5eca9","year":2024},"citing_paper":{"arxiv_id":"2605.09533","last_updated":"2026-05-10T13:35:16Z","snapshot_observed_at":"2026-08-15T18:45:24.449223Z","submitted_at":"2026-05-10T13:35:16Z","title":"Assessment of RAG and Fine-Tuning for Industrial Question-Answering-Applications","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-05-12T05:06:43.040359Z"},"links":{"cited_paper":"/paper/2403.01432","citing_paper":"/paper/2605.09533"},"observation_digest":"sha256:634df8a7af01f4e4cbf3663ba2c1d67d789e270dc2bdaa0df80393b8997904f9","observation_id":"de363068-f9b4-44c4-b543-e4e9f3151940","resolution":{"observed_at":"2026-05-12T05:41:23.702421Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.01432","last_updated":"2024-12-02T10:48:36Z","snapshot_observed_at":"2026-08-16T14:13:23.227671Z","submitted_at":"2024-03-03T08:07:55Z","title":"Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.01432","snapshot_observed_at":"2026-08-14T04:17:09.279667Z","title":"re- trieval augmented generation for less popular knowl- edge.arXiv:2403.01432","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10224","last_updated":"2026-08-10T20:51:18Z","snapshot_observed_at":"2026-08-16T10:12:16.702104Z","submitted_at":"2026-08-10T20:51:18Z","title":"Self-evolving Agentic Customer Support System at LinkedIn","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T04:17:09.279667Z"},"links":{"cited_paper":"/paper/2403.01432","citing_paper":"/paper/2608.10224"},"observation_digest":"sha256:e123b80482584e7828a8544584e3bd313ad26cd19ac3bda12fec11ae28c2ba71","observation_id":"c9b0400b-9c9a-4b1f-b0d4-dbcc120f0f28","resolution":{"observed_at":"2026-08-14T04:17:09.279667Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2403.01432/citation-record","integrity":"/paper/2403.01432/integrity","json":"/paper/2403.01432/citation-record.json","paper":"/paper/2403.01432"},"outbound":[],"paper":{"arxiv_id":"2403.01432","last_updated":"2024-12-02T10:48:36Z","latest_version":5,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T14:13:23.227671Z","submitted_at":"2024-03-03T08:07:55Z","title":"Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge"},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 5 inbound Pith citation observations for arXiv:2403.01432."}