{"as_of":"2026-08-08T22:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:26990885bb224cb5d10172915ee49023db0df6c0f9f6b728cbf26111ad9e54f9","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":6,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":6,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":6,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":6,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:00:26.767130Z","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":"2026-06-28T18:42:29.146302Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.14662","last_updated":"2025-05-29T23:51:24Z","snapshot_observed_at":"2026-08-07T18:01:38.197354Z","submitted_at":"2025-02-20T15:58:25Z","title":"iAgent: LLM Agent as a Shield between User and Recommender Systems","version":4},"cited_work":{"arxiv_id":"2502.14662","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.14662","snapshot_observed_at":"2026-06-28T18:42:29.146302Z","title":"Instructagent: Building user controllable recommender via llm agent","venue":null,"work_id":"d888c49f-751b-4cbf-9959-c04a4d3cd3f0","year":2025},"citing_paper":{"arxiv_id":"2410.02644","last_updated":"2025-05-30T03:50:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-10-03T16:30:47Z","title":"Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents","version":4},"reference_index":151,"source":"arxiv_source","source_observed_at":"2026-05-12T13:36:57.011451Z"},"links":{"cited_paper":"/paper/2502.14662","citing_paper":"/paper/2410.02644"},"observation_digest":"sha256:ad9138fb7e554a00c3102cb3148e6f40022628a6102012e801df0c4e408bea91","observation_id":"9f98b56f-5568-4f7b-b4b4-5639a00bf0ea","resolution":{"observed_at":"2026-05-12T13:36:57.206184Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.14662","last_updated":"2025-05-29T23:51:24Z","snapshot_observed_at":"2026-08-07T18:01:38.197354Z","submitted_at":"2025-02-20T15:58:25Z","title":"iAgent: LLM Agent as a Shield between User and Recommender Systems","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.14662","snapshot_observed_at":"2026-08-07T13:00:26.767130Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.23053","last_updated":"2025-05-29T03:50:24Z","snapshot_observed_at":"2026-08-07T12:52:38.029265Z","submitted_at":"2025-05-29T03:50:24Z","title":"Augment or Not? A Comparative Study of Pure and Augmented Large Language Model Recommenders","version":1},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-07T13:00:26.767130Z"},"links":{"cited_paper":"/paper/2502.14662","citing_paper":"/paper/2505.23053"},"observation_digest":"sha256:42b4cd3bab52ae66d88b4f19466efdb164dc3df02d471b5723d54c87f52fd0ec","observation_id":"77779603-556f-496b-82ee-b15af2befd56","resolution":{"observed_at":"2026-08-07T13:00:26.767130Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.14662","last_updated":"2025-05-29T23:51:24Z","snapshot_observed_at":"2026-08-07T18:01:38.197354Z","submitted_at":"2025-02-20T15:58:25Z","title":"iAgent: LLM Agent as a Shield between User and Recommender Systems","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.14662","snapshot_observed_at":"2026-08-04T17:56:38.861709Z","title":"iagent: Llm agent as a shield between user and recommender systems, 2025 c","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-07T01:01:23.391389Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.861709Z"},"links":{"cited_paper":"/paper/2502.14662","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:019a4a13546e5545803be5f6c88abbaeb7abee4d99fe048603f6d36151a6a6ee","observation_id":"7f42eb2d-bdc9-4a29-84e0-33982710a516","resolution":{"observed_at":"2026-08-04T17:56:38.861709Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.14662","last_updated":"2025-05-29T23:51:24Z","snapshot_observed_at":"2026-08-07T18:01:38.197354Z","submitted_at":"2025-02-20T15:58:25Z","title":"iAgent: LLM Agent as a Shield between User and Recommender Systems","version":4},"cited_work":{"arxiv_id":"2502.14662","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.14662","snapshot_observed_at":"2026-06-28T18:42:29.146302Z","title":"Instructagent: Building user controllable recommender via llm agent","venue":null,"work_id":"d888c49f-751b-4cbf-9959-c04a4d3cd3f0","year":2025},"citing_paper":{"arxiv_id":"2604.20858","last_updated":"2026-03-01T23:20:48Z","snapshot_observed_at":"2026-07-31T06:29:20.014752Z","submitted_at":"2026-03-01T23:20:48Z","title":"Mixture of Sequence: Theme-Aware Mixture-of-Experts for Long-Sequence Recommendation","version":1},"reference_index":128,"source":"pdf_text","source_observed_at":"2026-05-15T17:30:44.919870Z"},"links":{"cited_paper":"/paper/2502.14662","citing_paper":"/paper/2604.20858"},"observation_digest":"sha256:81427184e2a625345805a26ccf5c12f6126c5373ec040bb1e98724cd33645185","observation_id":"c40b7d4d-2962-4dc1-9171-b82dab80ce17","resolution":{"observed_at":"2026-05-15T17:31:22.323119Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.14662","last_updated":"2025-05-29T23:51:24Z","snapshot_observed_at":"2026-08-07T18:01:38.197354Z","submitted_at":"2025-02-20T15:58:25Z","title":"iAgent: LLM Agent as a Shield between User and Recommender Systems","version":4},"cited_work":{"arxiv_id":"2502.14662","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.14662","snapshot_observed_at":"2026-06-28T18:42:29.146302Z","title":"Instructagent: Building user controllable recommender via llm agent","venue":null,"work_id":"d888c49f-751b-4cbf-9959-c04a4d3cd3f0","year":2025},"citing_paper":{"arxiv_id":"2605.11874","last_updated":"2026-05-12T09:52:21Z","snapshot_observed_at":"2026-07-06T23:23:39.723268Z","submitted_at":"2026-05-12T09:52:21Z","title":"RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender Systems","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-13T05:04:08.454422Z"},"links":{"cited_paper":"/paper/2502.14662","citing_paper":"/paper/2605.11874"},"observation_digest":"sha256:e0d3ca6837ba52c8558abce881faae2fd056671931c8352d7b77225535927e86","observation_id":"01a61dc4-8ca2-4a7a-96ff-687d9f07dd99","resolution":{"observed_at":"2026-05-13T05:07:17.491256Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.14662","last_updated":"2025-05-29T23:51:24Z","snapshot_observed_at":"2026-08-07T18:01:38.197354Z","submitted_at":"2025-02-20T15:58:25Z","title":"iAgent: LLM Agent as a Shield between User and Recommender Systems","version":4},"cited_work":{"arxiv_id":"2502.14662","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.14662","snapshot_observed_at":"2026-06-28T18:42:29.146302Z","title":"Instructagent: Building user controllable recommender via llm agent","venue":null,"work_id":"d888c49f-751b-4cbf-9959-c04a4d3cd3f0","year":2025},"citing_paper":{"arxiv_id":"2606.00540","last_updated":"2026-05-30T05:14:53Z","snapshot_observed_at":"2026-08-01T17:48:34.431096Z","submitted_at":"2026-05-30T05:14:53Z","title":"Trustworthy Recommendation in the Era of Large Language Models: Opportunities and Challenges","version":1},"reference_index":271,"source":"pdf_text","source_observed_at":"2026-06-28T18:41:06.636352Z"},"links":{"cited_paper":"/paper/2502.14662","citing_paper":"/paper/2606.00540"},"observation_digest":"sha256:c045c167d9eb2a15c0c518f7443456c7417660a6301901acba915858411bbe73","observation_id":"c48bad9e-8fab-4c32-801e-4d765168b2fd","resolution":{"observed_at":"2026-06-28T18:42:29.147943Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.14662/citation-record","integrity":"/paper/2502.14662/integrity","json":"/paper/2502.14662/citation-record.json","paper":"/paper/2502.14662"},"outbound":[],"paper":{"arxiv_id":"2502.14662","last_updated":"2025-05-29T23:51:24Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T18:01:38.197354Z","submitted_at":"2025-02-20T15:58:25Z","title":"iAgent: LLM Agent as a Shield between User and Recommender Systems"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 6 inbound Pith citation observations for arXiv:2502.14662."}