{"as_of":"2026-08-08T04:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d9099f40dd6ec5b0a694a0743ac78599eca0e47bfef2f75484c05d0e6c145607","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":9,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":9,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":9,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":9,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T00:38:39.775330Z","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":"2026-05-22T06:24:40.500232Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.09970","last_updated":"2025-05-19T03:17:21Z","snapshot_observed_at":"2026-08-07T15:45:13.424803Z","submitted_at":"2025-05-15T05:17:47Z","title":"Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents","version":2},"cited_work":{"arxiv_id":"2505.09970","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.09970","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pre-Act: Multi-step planning and reasoning improves acting in LLM agents","venue":null,"work_id":"db137848-b22e-4f62-bcfb-2762dd0e04c9","year":2025},"citing_paper":{"arxiv_id":"2511.20857","last_updated":"2026-05-18T16:18:02Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-11-25T21:08:07Z","title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","version":1},"reference_index":230,"source":"arxiv_source","source_observed_at":"2026-05-14T23:13:15.016486Z"},"links":{"cited_paper":"/paper/2505.09970","citing_paper":"/paper/2511.20857"},"observation_digest":"sha256:3e7731d8095bb1e471dd4f81cd51c62ddcbc0e6b0287d09d035de06532d7ae44","observation_id":"eb5d2e69-9e66-4020-a399-b7b8d8abb2f1","resolution":{"observed_at":"2026-05-14T23:13:15.648858Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09970","last_updated":"2025-05-19T03:17:21Z","snapshot_observed_at":"2026-08-07T15:45:13.424803Z","submitted_at":"2025-05-15T05:17:47Z","title":"Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents","version":2},"cited_work":{"arxiv_id":"2505.09970","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.09970","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pre-Act: Multi-step planning and reasoning improves acting in LLM agents","venue":null,"work_id":"db137848-b22e-4f62-bcfb-2762dd0e04c9","year":2025},"citing_paper":{"arxiv_id":"2601.12538","last_updated":"2026-01-18T18:58:23Z","snapshot_observed_at":"2026-08-04T22:42:23.171653Z","submitted_at":"2026-01-18T18:58:23Z","title":"Agentic Reasoning for Large Language Models","version":1},"reference_index":102,"source":"pdf_text","source_observed_at":"2026-05-17T15:14:25.558878Z"},"links":{"cited_paper":"/paper/2505.09970","citing_paper":"/paper/2601.12538"},"observation_digest":"sha256:a939441d40e5102f79a9a322f2e81cf31e92df19cdeaa11458e39cb67f7b47f5","observation_id":"f1d23a85-752e-44a1-a505-0654b106accb","resolution":{"observed_at":"2026-05-17T15:14:25.983640Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09970","last_updated":"2025-05-19T03:17:21Z","snapshot_observed_at":"2026-08-07T15:45:13.424803Z","submitted_at":"2025-05-15T05:17:47Z","title":"Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents","version":2},"cited_work":{"arxiv_id":"2505.09970","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.09970","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pre-Act: Multi-step planning and reasoning improves acting in LLM agents","venue":null,"work_id":"db137848-b22e-4f62-bcfb-2762dd0e04c9","year":2025},"citing_paper":{"arxiv_id":"2605.06534","last_updated":"2026-05-20T11:37:51Z","snapshot_observed_at":"2026-08-03T06:43:16.351179Z","submitted_at":"2026-05-07T16:33:40Z","title":"ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-08T05:14:14.168753Z"},"links":{"cited_paper":"/paper/2505.09970","citing_paper":"/paper/2605.06534"},"observation_digest":"sha256:af41c166bd49346e2cd8bb51eda942ace4951fe1956fd350296c43c97c20a819","observation_id":"2a95c44f-249b-4b7a-8e1f-e53a8240e461","resolution":{"observed_at":"2026-05-11T21:31:16.016521Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09970","last_updated":"2025-05-19T03:17:21Z","snapshot_observed_at":"2026-08-07T15:45:13.424803Z","submitted_at":"2025-05-15T05:17:47Z","title":"Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents","version":2},"cited_work":{"arxiv_id":"2505.09970","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.09970","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pre-Act: Multi-step planning and reasoning improves acting in LLM agents","venue":null,"work_id":"db137848-b22e-4f62-bcfb-2762dd0e04c9","year":2025},"citing_paper":{"arxiv_id":"2605.06534","last_updated":"2026-05-20T11:37:51Z","snapshot_observed_at":"2026-08-03T06:43:16.351179Z","submitted_at":"2026-05-07T16:33:40Z","title":"ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-21T08:39:31.911497Z"},"links":{"cited_paper":"/paper/2505.09970","citing_paper":"/paper/2605.06534"},"observation_digest":"sha256:3c58cbe1b9cd2a01b1274cb07bc5323a89a79d5f58d294f9cc214cb00977d8ac","observation_id":"5412bea4-b3ca-4ee3-980e-7c41b3819e9b","resolution":{"observed_at":"2026-05-21T08:39:53.221001Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09970","last_updated":"2025-05-19T03:17:21Z","snapshot_observed_at":"2026-08-07T15:45:13.424803Z","submitted_at":"2025-05-15T05:17:47Z","title":"Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents","version":2},"cited_work":{"arxiv_id":"2505.09970","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.09970","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pre-Act: Multi-step planning and reasoning improves acting in LLM agents","venue":null,"work_id":"db137848-b22e-4f62-bcfb-2762dd0e04c9","year":2025},"citing_paper":{"arxiv_id":"2605.14465","last_updated":"2026-05-14T07:00:26Z","snapshot_observed_at":"2026-08-03T18:28:07.146194Z","submitted_at":"2026-05-14T07:00:26Z","title":"From Table to Cell: Attention for Better Reasoning with TABALIGN","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-15T01:31:03.738527Z"},"links":{"cited_paper":"/paper/2505.09970","citing_paper":"/paper/2605.14465"},"observation_digest":"sha256:a0faacc9ceacde0d1500fe5f349276e3a1f3f3006d9800246557a2797ccabe86","observation_id":"c3e685fb-94eb-412e-b203-f22b735dc32a","resolution":{"observed_at":"2026-05-15T01:33:27.258645Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09970","last_updated":"2025-05-19T03:17:21Z","snapshot_observed_at":"2026-08-07T15:45:13.424803Z","submitted_at":"2025-05-15T05:17:47Z","title":"Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents","version":2},"cited_work":{"arxiv_id":"2505.09970","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.09970","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pre-Act: Multi-step planning and reasoning improves acting in LLM agents","venue":null,"work_id":"db137848-b22e-4f62-bcfb-2762dd0e04c9","year":2025},"citing_paper":{"arxiv_id":"2605.22154","last_updated":"2026-05-21T08:25:17Z","snapshot_observed_at":"2026-07-30T19:02:11.122375Z","submitted_at":"2026-05-21T08:25:17Z","title":"IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-22T06:21:56.971204Z"},"links":{"cited_paper":"/paper/2505.09970","citing_paper":"/paper/2605.22154"},"observation_digest":"sha256:aa1afa0de1786102c68711da64c73cc2df119b3696392c82c5c46a36da569fcd","observation_id":"ecb73ab9-6c69-4cd5-9d70-10c52deae6a9","resolution":{"observed_at":"2026-05-22T06:24:40.502910Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09970","last_updated":"2025-05-19T03:17:21Z","snapshot_observed_at":"2026-08-07T15:45:13.424803Z","submitted_at":"2025-05-15T05:17:47Z","title":"Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09970","snapshot_observed_at":"2026-08-03T16:54:57.580777Z","title":"arXiv preprint arXiv:2505.09970 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28942","last_updated":"2026-08-03T20:04:55Z","snapshot_observed_at":"2026-08-08T01:22:52.744777Z","submitted_at":"2026-07-31T01:53:41Z","title":"NeSyFS: A Neuro-symbolic Fast-Slow Thinking Framework for LLM Agent under Partial Observability","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-03T16:54:57.580777Z"},"links":{"cited_paper":"/paper/2505.09970","citing_paper":"/paper/2607.28942"},"observation_digest":"sha256:5d88cac716b84c04aeff38a2f097db852e990e6c230989fd314cc3f03d162a7b","observation_id":"00b896cc-a6a3-40b4-8918-f27d76cee025","resolution":{"observed_at":"2026-08-03T16:54:57.580777Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09970","last_updated":"2025-05-19T03:17:21Z","snapshot_observed_at":"2026-08-07T15:45:13.424803Z","submitted_at":"2025-05-15T05:17:47Z","title":"Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09970","snapshot_observed_at":"2026-08-05T04:24:56.445855Z","title":"arXiv preprint arXiv:2505.09970 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28942","last_updated":"2026-08-03T20:04:55Z","snapshot_observed_at":"2026-08-08T01:22:52.744777Z","submitted_at":"2026-07-31T01:53:41Z","title":"NeSyFS: A Neuro-symbolic Fast-Slow Thinking Framework for LLM Agent under Partial Observability","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-05T04:24:56.445855Z"},"links":{"cited_paper":"/paper/2505.09970","citing_paper":"/paper/2607.28942"},"observation_digest":"sha256:d004ecadca7c1a34d5deedbe39fc6046b506cd39ed1b2794a433ba552de6ca55","observation_id":"03686e7a-0366-405a-bcc1-af840b9802ed","resolution":{"observed_at":"2026-08-05T04:24:56.445855Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09970","last_updated":"2025-05-19T03:17:21Z","snapshot_observed_at":"2026-08-07T15:45:13.424803Z","submitted_at":"2025-05-15T05:17:47Z","title":"Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09970","snapshot_observed_at":"2026-08-06T00:38:39.775330Z","title":"Pre-act: Multi-step planning and reasoning improves acting in llm agents.arXiv preprint arXiv:2505.09970, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.00967","last_updated":"2026-08-02T03:36:03Z","snapshot_observed_at":"2026-08-08T01:52:29.536096Z","submitted_at":"2026-08-02T03:36:03Z","title":"TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T00:38:39.775330Z"},"links":{"cited_paper":"/paper/2505.09970","citing_paper":"/paper/2608.00967"},"observation_digest":"sha256:f99cdb36e0d5038ffb83663459c1e40649fedddfe346bdab3ed2ef8dd321313f","observation_id":"352d16cb-a162-4458-b858-2ae9db23668d","resolution":{"observed_at":"2026-08-06T00:38:39.775330Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2505.09970/citation-record","integrity":"/paper/2505.09970/integrity","json":"/paper/2505.09970/citation-record.json","paper":"/paper/2505.09970"},"outbound":[],"paper":{"arxiv_id":"2505.09970","last_updated":"2025-05-19T03:17:21Z","latest_version":2,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-07T15:45:13.424803Z","submitted_at":"2025-05-15T05:17:47Z","title":"Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents"},"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 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 9 inbound Pith citation observations for arXiv:2505.09970."}