{"as_of":"2026-08-07T15:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1703f2b6491d45329e773b1850674f884a5901a7115f113829e26d2e8ba2326c","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:08:28.338360Z","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":"2026-05-15T03:08:59.547623Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.14146","last_updated":"2024-10-29T11:13:14Z","snapshot_observed_at":"2026-08-07T04:01:11.825619Z","submitted_at":"2024-02-21T22:02:37Z","title":"Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.14146","snapshot_observed_at":"2026-08-07T12:08:28.338360Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00569","last_updated":"2025-05-31T13:57:10Z","snapshot_observed_at":"2026-08-07T12:00:12.795542Z","submitted_at":"2025-05-31T13:57:10Z","title":"AutoMixAlign: Adaptive Data Mixing for Multi-Task Preference Optimization in LLMs","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T12:08:28.338360Z"},"links":{"cited_paper":"/paper/2402.14146","citing_paper":"/paper/2506.00569"},"observation_digest":"sha256:1ac77dde854a63358dfb1e0c15f421a7cdddcb02a96cd80c06a99cfc97575944","observation_id":"5ca2c538-e768-432d-acc0-5f98cb4c4d11","resolution":{"observed_at":"2026-08-07T12:08:28.338360Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.14146","last_updated":"2024-10-29T11:13:14Z","snapshot_observed_at":"2026-08-07T04:01:11.825619Z","submitted_at":"2024-02-21T22:02:37Z","title":"Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.14146","snapshot_observed_at":"2026-08-07T11:04:06.866772Z","title":"Dynamic multi-reward weighting for multi-style controllable generation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03637","last_updated":"2025-07-07T09:53:22Z","snapshot_observed_at":"2026-08-07T12:09:45.031691Z","submitted_at":"2025-06-04T07:30:16Z","title":"RewardAnything: Generalizable Principle-Following Reward Models","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T11:04:06.866772Z"},"links":{"cited_paper":"/paper/2402.14146","citing_paper":"/paper/2506.03637"},"observation_digest":"sha256:1bb2ac4f58c7a23b775684b914525eda9c53b83665f7e8e3dcb02f819fbbfbf8","observation_id":"67a8321e-6415-4aa3-bdc3-7eefe6eaae70","resolution":{"observed_at":"2026-08-07T11:04:06.866772Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.14146","last_updated":"2024-10-29T11:13:14Z","snapshot_observed_at":"2026-08-07T04:01:11.825619Z","submitted_at":"2024-02-21T22:02:37Z","title":"Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.14146","snapshot_observed_at":"2026-08-06T17:13:46.539995Z","title":"Dynamic multi-reward weighting for multi-style controllable generation, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.11538","last_updated":"2025-07-15T17:59:42Z","snapshot_observed_at":"2026-08-06T17:04:02.815574Z","submitted_at":"2025-07-15T17:59:42Z","title":"How Many Instructions Can LLMs Follow at Once?","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-06T17:13:46.539995Z"},"links":{"cited_paper":"/paper/2402.14146","citing_paper":"/paper/2507.11538"},"observation_digest":"sha256:a470891a1d57e7da9c200df9fc14c42e72f866fd95e3cbdf23a298a54b1f1032","observation_id":"1fe5078d-15d3-4a82-88be-165b410fd056","resolution":{"observed_at":"2026-08-06T17:13:46.539995Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.14146","last_updated":"2024-10-29T11:13:14Z","snapshot_observed_at":"2026-08-07T04:01:11.825619Z","submitted_at":"2024-02-21T22:02:37Z","title":"Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation","version":3},"cited_work":{"arxiv_id":"2402.14146","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.14146","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2402.14146 , year=","venue":null,"work_id":"9808c09c-6c8e-4a3f-bf90-4cac03cc8e7e","year":null},"citing_paper":{"arxiv_id":"2605.14350","last_updated":"2026-05-14T04:22:24Z","snapshot_observed_at":"2026-07-06T23:25:49.545418Z","submitted_at":"2026-05-14T04:22:24Z","title":"Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling","version":1},"reference_index":270,"source":"arxiv_source","source_observed_at":"2026-05-15T03:05:36.871497Z"},"links":{"cited_paper":"/paper/2402.14146","citing_paper":"/paper/2605.14350"},"observation_digest":"sha256:41316f5ccc3659e24c40409630cd55c969c3b6e7e376f4770c2c1f930b4dad75","observation_id":"2bc30f1f-b59c-4990-af26-f6f209da8d5a","resolution":{"observed_at":"2026-05-15T03:08:59.549931Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.14146/citation-record","integrity":"/paper/2402.14146/integrity","json":"/paper/2402.14146/citation-record.json","paper":"/paper/2402.14146"},"outbound":[],"paper":{"arxiv_id":"2402.14146","last_updated":"2024-10-29T11:13:14Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T04:01:11.825619Z","submitted_at":"2024-02-21T22:02:37Z","title":"Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2402.14146."}