{"as_of":"2026-08-22T12:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f763d94784d16fff7bc7d52313a06185d823c47c4c59ac614b3bb25fac9380bc","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T12:16:31.933188Z","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":"2026-08-06T16:34:25.466718Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.10093","last_updated":"2024-10-14T02:21:29Z","snapshot_observed_at":"2026-08-16T13:09:47.815647Z","submitted_at":"2024-10-14T02:21:29Z","title":"How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.10093","snapshot_observed_at":"2026-08-11T12:16:31.933188Z","title":"How to leverage demonstration data in alignment for large language model? a self-imitation learning perspective","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.14516","last_updated":"2024-12-19T04:31:56Z","snapshot_observed_at":"2026-08-15T23:47:47.627897Z","submitted_at":"2024-12-19T04:31:56Z","title":"Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T12:16:31.933188Z"},"links":{"cited_paper":"/paper/2410.10093","citing_paper":"/paper/2412.14516"},"observation_digest":"sha256:f7b1a402c34f3cbc2537b3f7ff0e908921e407557aeba5f65aebac8e00379762","observation_id":"a4256de8-453d-45da-95c8-e554d4f05985","resolution":{"observed_at":"2026-08-11T12:16:31.933188Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10093","last_updated":"2024-10-14T02:21:29Z","snapshot_observed_at":"2026-08-16T13:09:47.815647Z","submitted_at":"2024-10-14T02:21:29Z","title":"How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective","version":1},"cited_work":{"arxiv_id":"2410.10093","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.10093","snapshot_observed_at":"2026-08-06T16:34:25.466718Z","title":"How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective","venue":"cs.CL","work_id":"2c2381d3-00ff-4ebf-91c3-7fedb298aabe","year":2024},"citing_paper":{"arxiv_id":"2507.13158","last_updated":"2025-07-17T14:22:24Z","snapshot_observed_at":"2026-08-15T15:23:09.345799Z","submitted_at":"2025-07-17T14:22:24Z","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-06T16:34:25.246579Z"},"links":{"cited_paper":"/paper/2410.10093","citing_paper":"/paper/2507.13158"},"observation_digest":"sha256:61b9f07ac6f6e23d95fc0785db756ec324f59ffb1f79d9a878a23c1e73d7fc90","observation_id":"b81d8143-0d29-4284-9d02-6ba928991711","resolution":{"observed_at":"2026-08-06T16:34:25.472318Z","resolver_source":"local_arxiv","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"}}],"links":{"evidence":"/evidence","html":"/paper/2410.10093/citation-record","integrity":"/paper/2410.10093/integrity","json":"/paper/2410.10093/citation-record.json","paper":"/paper/2410.10093"},"outbound":[],"paper":{"arxiv_id":"2410.10093","last_updated":"2024-10-14T02:21:29Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T13:09:47.815647Z","submitted_at":"2024-10-14T02:21:29Z","title":"How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective"},"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 2 inbound Pith citation observations for arXiv:2410.10093."}