{"as_of":"2026-08-14T01:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3dec6d33f30db5e3df71e3bbbc03860cc759a55f30d173e1370966ba0cf77f97","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":13,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":13,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":13,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":13,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T15:26:44.971047Z","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":"2026-07-04T03:39:30.783853Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.16218","last_updated":"2024-11-01T00:01:01Z","snapshot_observed_at":"2026-08-12T23:36:35.761559Z","submitted_at":"2024-06-23T21:05:31Z","title":"Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.16218","snapshot_observed_at":"2026-08-12T15:26:44.971047Z","title":"Cheng, A","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.14251","last_updated":"2025-05-28T00:04:45Z","snapshot_observed_at":"2026-08-12T15:20:36.226251Z","submitted_at":"2024-11-21T15:57:02Z","title":"Natural Language Reinforcement Learning","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T15:26:44.971047Z"},"links":{"cited_paper":"/paper/2406.16218","citing_paper":"/paper/2411.14251"},"observation_digest":"sha256:5904e47f0d5a6d3f54cf885ab35ccf1e38e0e4799a0caf41ff6bd08ebb40c6b9","observation_id":"215f34e5-cb78-4abd-bae6-8d664bfbc452","resolution":{"observed_at":"2026-08-12T15:26:44.971047Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16218","last_updated":"2024-11-01T00:01:01Z","snapshot_observed_at":"2026-08-12T23:36:35.761559Z","submitted_at":"2024-06-23T21:05:31Z","title":"Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.16218","snapshot_observed_at":"2026-08-12T05:26:14.104184Z","title":"Cheng , author A","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00431","last_updated":"2024-12-03T15:33:42Z","snapshot_observed_at":"2026-08-13T16:22:16.663890Z","submitted_at":"2024-11-30T10:58:56Z","title":"Multi-Agent System for Cosmological Parameter Analysis","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-12T05:26:14.104184Z"},"links":{"cited_paper":"/paper/2406.16218","citing_paper":"/paper/2412.00431"},"observation_digest":"sha256:6d6db267605ef7c9a44d0e246d938a20d7a2c6ebf3c8dc574af52775ccfae6c3","observation_id":"951835f2-a5bc-4ac0-befd-85cb9051d30a","resolution":{"observed_at":"2026-08-12T05:26:14.104184Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16218","last_updated":"2024-11-01T00:01:01Z","snapshot_observed_at":"2026-08-12T23:36:35.761559Z","submitted_at":"2024-06-23T21:05:31Z","title":"Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.16218","snapshot_observed_at":"2026-08-10T23:07:33.523504Z","title":"Trace is the New AutoDiff–unlocking efficient optimization of computational workflows","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.21154","last_updated":"2024-12-30T18:33:28Z","snapshot_observed_at":"2026-08-11T00:56:48.615443Z","submitted_at":"2024-12-30T18:33:28Z","title":"Aviary: training language agents on challenging scientific tasks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T23:07:33.523504Z"},"links":{"cited_paper":"/paper/2406.16218","citing_paper":"/paper/2412.21154"},"observation_digest":"sha256:6ea054adcff751a64625d6a4e8f88eb1802afdf22b6a8edc25d3b7aa62789e68","observation_id":"bdb87e88-420e-4934-ac49-0bbb4b3d1c09","resolution":{"observed_at":"2026-08-10T23:07:33.523504Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16218","last_updated":"2024-11-01T00:01:01Z","snapshot_observed_at":"2026-08-12T23:36:35.761559Z","submitted_at":"2024-06-23T21:05:31Z","title":"Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs","version":2},"cited_work":{"arxiv_id":"2406.16218","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.16218","snapshot_observed_at":"2026-07-04T03:39:30.783853Z","title":"Trace is the next autodiff: Generative optimization with rich feedback, execution traces, and LLMs","venue":null,"work_id":"0f7b4f18-577b-4a27-9c24-0da50da73e4e","year":2024},"citing_paper":{"arxiv_id":"2605.10913","last_updated":"2026-06-24T17:55:07Z","snapshot_observed_at":"2026-08-13T15:51:48.523223Z","submitted_at":"2026-05-11T17:50:51Z","title":"Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-12T03:29:33.497561Z"},"links":{"cited_paper":"/paper/2406.16218","citing_paper":"/paper/2605.10913"},"observation_digest":"sha256:0236b13f18feaff9c1a7db1521af68256e855bd313ef1b9a1144ce1dc003f4b9","observation_id":"0f7a0bab-b325-4aed-bf10-a1e17af7dd32","resolution":{"observed_at":"2026-05-12T07:21:23.193228Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16218","last_updated":"2024-11-01T00:01:01Z","snapshot_observed_at":"2026-08-12T23:36:35.761559Z","submitted_at":"2024-06-23T21:05:31Z","title":"Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs","version":2},"cited_work":{"arxiv_id":"2406.16218","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.16218","snapshot_observed_at":"2026-07-04T03:39:30.783853Z","title":"Trace is the next autodiff: Generative optimization with rich feedback, execution traces, and LLMs","venue":null,"work_id":"0f7b4f18-577b-4a27-9c24-0da50da73e4e","year":2024},"citing_paper":{"arxiv_id":"2605.10913","last_updated":"2026-06-24T17:55:07Z","snapshot_observed_at":"2026-08-13T15:51:48.523223Z","submitted_at":"2026-05-11T17:50:51Z","title":"Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-30T22:24:26.528532Z"},"links":{"cited_paper":"/paper/2406.16218","citing_paper":"/paper/2605.10913"},"observation_digest":"sha256:acb5b030d49bf8a5af9f312d72ccf0e8e97b89be1ff86052da9d7dd3020747dd","observation_id":"ba241145-2577-46f8-aa81-c3e50cd1029c","resolution":{"observed_at":"2026-06-30T22:25:06.774418Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16218","last_updated":"2024-11-01T00:01:01Z","snapshot_observed_at":"2026-08-12T23:36:35.761559Z","submitted_at":"2024-06-23T21:05:31Z","title":"Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs","version":2},"cited_work":{"arxiv_id":"2406.16218","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.16218","snapshot_observed_at":"2026-07-04T03:39:30.783853Z","title":"Trace is the next autodiff: Generative optimization with rich feedback, execution traces, and LLMs","venue":null,"work_id":"0f7b4f18-577b-4a27-9c24-0da50da73e4e","year":2024},"citing_paper":{"arxiv_id":"2605.12484","last_updated":"2026-05-14T17:49:32Z","snapshot_observed_at":"2026-08-12T18:28:37.189735Z","submitted_at":"2026-05-12T17:58:20Z","title":"Learning, Fast and Slow: Towards LLMs That Adapt Continually","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-13T05:00:31.452781Z"},"links":{"cited_paper":"/paper/2406.16218","citing_paper":"/paper/2605.12484"},"observation_digest":"sha256:a6a3a5b3bb20068dba1f1d9b126ac93bee379fb1487ee8de5d87869ba1963c38","observation_id":"9bb546e7-1886-4910-b1df-ded240f37b84","resolution":{"observed_at":"2026-05-13T05:07:18.400455Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16218","last_updated":"2024-11-01T00:01:01Z","snapshot_observed_at":"2026-08-12T23:36:35.761559Z","submitted_at":"2024-06-23T21:05:31Z","title":"Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs","version":2},"cited_work":{"arxiv_id":"2406.16218","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.16218","snapshot_observed_at":"2026-07-04T03:39:30.783853Z","title":"Trace is the next autodiff: Generative optimization with rich feedback, execution traces, and LLMs","venue":null,"work_id":"0f7b4f18-577b-4a27-9c24-0da50da73e4e","year":2024},"citing_paper":{"arxiv_id":"2605.12484","last_updated":"2026-05-14T17:49:32Z","snapshot_observed_at":"2026-08-12T18:28:37.189735Z","submitted_at":"2026-05-12T17:58:20Z","title":"Learning, Fast and Slow: Towards LLMs That Adapt Continually","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-15T05:19:05.368681Z"},"links":{"cited_paper":"/paper/2406.16218","citing_paper":"/paper/2605.12484"},"observation_digest":"sha256:4adb5a89d5c831bf0d59acad116d4a59b52e513859fba791819481803c0d470c","observation_id":"f74077c8-4448-4435-ad85-d5964237d666","resolution":{"observed_at":"2026-05-15T05:19:45.511166Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16218","last_updated":"2024-11-01T00:01:01Z","snapshot_observed_at":"2026-08-12T23:36:35.761559Z","submitted_at":"2024-06-23T21:05:31Z","title":"Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs","version":2},"cited_work":{"arxiv_id":"2406.16218","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.16218","snapshot_observed_at":"2026-07-04T03:39:30.783853Z","title":"Trace is the next autodiff: Generative optimization with rich feedback, execution traces, and LLMs","venue":null,"work_id":"0f7b4f18-577b-4a27-9c24-0da50da73e4e","year":2024},"citing_paper":{"arxiv_id":"2605.19330","last_updated":"2026-05-19T04:07:41Z","snapshot_observed_at":"2026-07-06T23:30:06.876413Z","submitted_at":"2026-05-19T04:07:41Z","title":"MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-20T06:09:56.684622Z"},"links":{"cited_paper":"/paper/2406.16218","citing_paper":"/paper/2605.19330"},"observation_digest":"sha256:b6b4bf9c9538b5940e97ede2fdbc5786c57adf0b207d871d3c2d3c1e9c006992","observation_id":"75ccd0cc-4644-4ef2-bcd3-8055773098ea","resolution":{"observed_at":"2026-05-20T06:13:05.293872Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16218","last_updated":"2024-11-01T00:01:01Z","snapshot_observed_at":"2026-08-12T23:36:35.761559Z","submitted_at":"2024-06-23T21:05:31Z","title":"Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs","version":2},"cited_work":{"arxiv_id":"2406.16218","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.16218","snapshot_observed_at":"2026-07-04T03:39:30.783853Z","title":"Trace is the next autodiff: Generative optimization with rich feedback, execution traces, and LLMs","venue":null,"work_id":"0f7b4f18-577b-4a27-9c24-0da50da73e4e","year":2024},"citing_paper":{"arxiv_id":"2605.21958","last_updated":"2026-05-21T03:44:47Z","snapshot_observed_at":"2026-07-06T23:32:20.708664Z","submitted_at":"2026-05-21T03:44:47Z","title":"Diagnosis Is Not Prescription: Linguistic Co-Adaptation Explains Patching Hazards in LLM Pipelines","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-05-22T06:54:34.531580Z"},"links":{"cited_paper":"/paper/2406.16218","citing_paper":"/paper/2605.21958"},"observation_digest":"sha256:246bfacaa95fd6bf4560a342e99cc42e4b5fe7788487cd1f6b95a9528425af19","observation_id":"b55b14e5-aa67-4d81-8a0a-210bc2c47031","resolution":{"observed_at":"2026-05-22T06:54:42.008874Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16218","last_updated":"2024-11-01T00:01:01Z","snapshot_observed_at":"2026-08-12T23:36:35.761559Z","submitted_at":"2024-06-23T21:05:31Z","title":"Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs","version":2},"cited_work":{"arxiv_id":"2406.16218","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.16218","snapshot_observed_at":"2026-07-04T03:39:30.783853Z","title":"Trace is the next autodiff: Generative optimization with rich feedback, execution traces, and LLMs","venue":null,"work_id":"0f7b4f18-577b-4a27-9c24-0da50da73e4e","year":2024},"citing_paper":{"arxiv_id":"2605.26275","last_updated":"2026-08-04T02:46:14Z","snapshot_observed_at":"2026-08-08T18:03:00.968158Z","submitted_at":"2026-05-25T19:01:10Z","title":"SPEAR: Code-Augmented Agentic Prompt Optimization","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-29T21:34:29.828536Z"},"links":{"cited_paper":"/paper/2406.16218","citing_paper":"/paper/2605.26275"},"observation_digest":"sha256:9ac39c5ff67ef5fac0859b7b53dc25882ac2ed24dea02fdba42421c382c73471","observation_id":"657eb882-d2a1-4de6-b922-b61e4475fab6","resolution":{"observed_at":"2026-06-29T21:43:59.769526Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16218","last_updated":"2024-11-01T00:01:01Z","snapshot_observed_at":"2026-08-12T23:36:35.761559Z","submitted_at":"2024-06-23T21:05:31Z","title":"Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs","version":2},"cited_work":{"arxiv_id":"2406.16218","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.16218","snapshot_observed_at":"2026-07-04T03:39:30.783853Z","title":"Trace is the next autodiff: Generative optimization with rich feedback, execution traces, and LLMs","venue":null,"work_id":"0f7b4f18-577b-4a27-9c24-0da50da73e4e","year":2024},"citing_paper":{"arxiv_id":"2606.20475","last_updated":"2026-06-18T16:54:25Z","snapshot_observed_at":"2026-07-06T23:55:38.979306Z","submitted_at":"2026-06-18T16:54:25Z","title":"Marginal Advantage Accumulation for Memory-Driven Agent Self-Evolution","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-06-26T17:45:49.272070Z"},"links":{"cited_paper":"/paper/2406.16218","citing_paper":"/paper/2606.20475"},"observation_digest":"sha256:f0dcf3ba08bf64e01a7c436cb7eee387bbd99fec4f021ada70b0dea7479b9041","observation_id":"711cd5cc-80fc-4640-938c-7b6c89530213","resolution":{"observed_at":"2026-07-04T03:39:30.785893Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16218","last_updated":"2024-11-01T00:01:01Z","snapshot_observed_at":"2026-08-12T23:36:35.761559Z","submitted_at":"2024-06-23T21:05:31Z","title":"Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.16218","snapshot_observed_at":"2026-08-07T06:02:25.649833Z","title":"Cheng, A","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.06301","last_updated":"2026-08-06T17:21:05Z","snapshot_observed_at":"2026-08-12T16:49:55.368455Z","submitted_at":"2026-08-06T17:21:05Z","title":"HarnessOpt-Bench: Evaluating LLMs at Harness Optimization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T06:02:25.649833Z"},"links":{"cited_paper":"/paper/2406.16218","citing_paper":"/paper/2608.06301"},"observation_digest":"sha256:a598c0b82b78095d33e943fe116d7e88935bd1cbef3e1f6737b5e9938a1f6f83","observation_id":"7e24c6bc-e978-4394-a654-b4a3c2cfc91a","resolution":{"observed_at":"2026-08-07T06:02:25.649833Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16218","last_updated":"2024-11-01T00:01:01Z","snapshot_observed_at":"2026-08-12T23:36:35.761559Z","submitted_at":"2024-06-23T21:05:31Z","title":"Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.16218","snapshot_observed_at":"2026-08-12T00:28:29.164750Z","title":"Cheng, A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.08156","last_updated":"2026-08-08T14:35:22Z","snapshot_observed_at":"2026-08-13T23:24:16.245648Z","submitted_at":"2026-08-08T14:35:22Z","title":"A Hybrid Nested Harness for Decoupling Structure and Parameters in LLM-Driven Optimization","version":1},"reference_index":2010,"source":"pdf_text","source_observed_at":"2026-08-12T00:28:29.164750Z"},"links":{"cited_paper":"/paper/2406.16218","citing_paper":"/paper/2608.08156"},"observation_digest":"sha256:7e9b990a0053596eb8d12bda57ad1b493fe3867a335f6ee82ae08ab0914abd3c","observation_id":"afa4c939-57e6-4c6b-a006-90c5380604c4","resolution":{"observed_at":"2026-08-12T00:28:29.164750Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2406.16218/citation-record","integrity":"/paper/2406.16218/integrity","json":"/paper/2406.16218/citation-record.json","paper":"/paper/2406.16218"},"outbound":[],"paper":{"arxiv_id":"2406.16218","last_updated":"2024-11-01T00:01:01Z","latest_version":2,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-12T23:36:35.761559Z","submitted_at":"2024-06-23T21:05:31Z","title":"Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 13 inbound Pith citation observations for arXiv:2406.16218."}