{"as_of":"2026-08-08T18:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:957c5c2967ee56d0780b17b4c667ca8884214f612b994ab6daa1cd69394138ab","coverage":[{"denominator":38,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":38,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T01:25:24.770921Z","state":"measured"},{"denominator":38,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":38,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.25831/citation-record","integrity":"/paper/2607.25831/integrity","json":"/paper/2607.25831/citation-record.json","paper":"/paper/2607.25831"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.471114Z","title":"A survey on compiler autotuning using machine learning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.471114Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:99d76282e19477f391410969b0d90a518d3f89b6fbfd9bb50898a31f18024041","observation_id":"13290bde-2605-4ca8-8c9a-63403f1490ad","resolution":{"observed_at":"2026-08-01T01:25:24.471114Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.517252Z","title":"Using machine learning to focus iterative optimization,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.517252Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:620911ab382adfdf76e3a97dc2c594d863dfd3f569ee27ac32d2a3e6e14fe12b","observation_id":"d8460c8f-888f-4761-862e-13766da10c3a","resolution":{"observed_at":"2026-08-01T01:25:24.517252Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.569524Z","title":"Finding effective compilation sequences,","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.569524Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:7a17b6e782d770c901a84302a30da6b069623d6927cdfcb9b1d181c630b8d30b","observation_id":"37e143e3-571a-4ecc-9f93-ec1e5221f2de","resolution":{"observed_at":"2026-08-01T01:25:24.569524Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.590558Z","title":"Efficient compiler autotuning via bayesian optimization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.590558Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:223b18c31bab0d6c5f11611ec7a78e002723264e2c6ce9d48f621e493ed7aa6c","observation_id":"cb3d614c-777c-40d8-bb50-e03ea0f56913","resolution":{"observed_at":"2026-08-01T01:25:24.590558Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.623868Z","title":"Evolutionary optimization of com- piler flag selection by learning and exploiting flags interactions,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.623868Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:21e1be09d2fe3c2dbb3249598e75b87894854b85767a9c00ede97c84568c323a","observation_id":"0dc1e2b8-589f-454e-bbcd-9badb2d4cace","resolution":{"observed_at":"2026-08-01T01:25:24.623868Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.661868Z","title":"Kisuki, P","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.661868Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:ece65c5d0b44075452b2f67e320e8d228133f9eba98bbdfe100be55f47562448","observation_id":"126e67d2-3e90-44d0-bc1c-4d1e8f6985c6","resolution":{"observed_at":"2026-08-01T01:25:24.661868Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.689040Z","title":"Feature mining for machine learning based compilation optimization,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.689040Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:4aba4e5b5f883cf490955b2ec55b6c8bcd43c1493aaad00b96f43fccc01cad5c","observation_id":"b6a3a0a6-67a7-4a58-9f19-6bc4a24403e5","resolution":{"observed_at":"2026-08-01T01:25:24.689040Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.692095Z","title":"Compiler auto-tuning via critical flag selection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.692095Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:5bf01e39651d42cbfa820889f627cbe1239ea606588f205e235f6788fe422a8a","observation_id":"aadd62f3-d96d-41c1-8843-24be523fd5a1","resolution":{"observed_at":"2026-08-01T01:25:24.692095Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.694830Z","title":"Compiler autotuning through multiple- phase learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.694830Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:0febf6f1cd12a21ea54ce9d89c18821b7a81ce31c3ba2b44e3349269cd8ec34b","observation_id":"248b9b0e-4522-4c14-91d4-39830c21a1ca","resolution":{"observed_at":"2026-08-01T01:25:24.694830Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.697383Z","title":"COLE: Compiler optimization level ex- ploration,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.697383Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:5ca0913c621711cf1ae26f9904ff0736d1be18030a0e3e35f89e3049435a81a9","observation_id":"33eadc28-961d-4163-9e16-d9984bf7b2ce","resolution":{"observed_at":"2026-08-01T01:25:24.697383Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.699941Z","title":"Automatic selection of GCC optimization options using a gene weighted genetic algorithm,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.699941Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:f14475efd8e089896c050a2feba0ba62faad4a6e67eabd11bd4fb8de02bcc99f","observation_id":"39013c42-c1ad-4c40-ae89-18a1cf40817b","resolution":{"observed_at":"2026-08-01T01:25:24.699941Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.702527Z","title":"Deconstructing iterative optimization,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.702527Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:d09c4ab100167bf7e5db3d029fcf664ff0879fb42360a13aa5846fba5e44cff1","observation_id":"679852c2-ef4d-4588-8ca9-c4e9c072d051","resolution":{"observed_at":"2026-08-01T01:25:24.702527Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.705186Z","title":"Automatic configuration of GCC using irace,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.705186Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:54d7bbea04f0062b55cfda1f59599e302e1e979ab9002e4f3db00d1888423a7a","observation_id":"0b156147-e3f2-4007-9a43-8b9fa34654f6","resolution":{"observed_at":"2026-08-01T01:25:24.705186Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.707829Z","title":"OpenTuner: An extensible frame- work for program autotuning,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.707829Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:d23954e5c1fb4055cd30e90e71dcfff4d80e469ccf6329be542aa6ef9668db99","observation_id":"dacd3f35-e34d-4512-9998-c280a73e0767","resolution":{"observed_at":"2026-08-01T01:25:24.707829Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.710387Z","title":"COBAYN: Compiler autotuning framework using bayesian networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.710387Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:7f1a8f4555af87adfab7f9a0c9ca8bf488736e877dbadb91046d70aae83a5b4c","observation_id":"27502cab-d631-48a5-a457-6d16396f7a39","resolution":{"observed_at":"2026-08-01T01:25:24.710387Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.712958Z","title":"PDCAT: Preference-driven compiler auto- tuning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.712958Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:52482968b2e101d0435a1b27915f3188394145403c5808fdf442a575ed1c6244","observation_id":"b349bc3e-7f0a-453f-bec3-ddee5dfd57ff","resolution":{"observed_at":"2026-08-01T01:25:24.712958Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.715606Z","title":"SRTuner: Effective compiler optimization customization by exposing synergistic relations,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.715606Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:9e12fa872d646c19ef81ff25f69965e241cef13668ebc2c4a5796f5dd7f1d7af","observation_id":"150bf39f-efda-459f-8466-05da577c6b31","resolution":{"observed_at":"2026-08-01T01:25:24.715606Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.718004Z","title":"GroupTuner: Efficient group-aware compiler auto-tuning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.718004Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:f1fb5e93aaa4e54c2b160682294a00a49743490262a4c2274ce04a702fa813ef","observation_id":"04762404-a27b-485b-9829-f5912de4c612","resolution":{"observed_at":"2026-08-01T01:25:24.718004Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03300","last_updated":"2024-04-27T15:25:53Z","snapshot_observed_at":"2026-08-06T14:58:42.911363Z","submitted_at":"2024-02-05T18:55:32Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03300","snapshot_observed_at":"2026-08-01T01:25:24.720550Z","title":"DeepSeekMath: Pushing the limits of mathematical reasoning in open language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.720550Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:131af8912de9cfd3716178ad5cb4bed47e9d823be9cfeecac85b1bd5d2af745e","observation_id":"4d02a116-9287-4b91-98fc-2131b866be9b","resolution":{"observed_at":"2026-08-01T01:25:24.720550Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.723576Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.723576Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:f5dbdc76f9b2dd549419a7a2b8d0ce9e93310cf44a6d16bc1b02f25d37d22ca0","observation_id":"72c6ebe3-762c-4212-bedb-79f2ef6b2acd","resolution":{"observed_at":"2026-08-01T01:25:24.723576Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.726199Z","title":"PolyBench,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.726199Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:4ca76f88726c102f3b9c2263a95192103ce9b1830dd2dadba6680665d7935974","observation_id":"ebdb4b30-f020-4327-9fdc-ab60632713f2","resolution":{"observed_at":"2026-08-01T01:25:24.726199Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.5281/zenodo.21091417","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:54.799944Z","title":"Artifact Package for An Offline-to-Online Reinforcement Learning Framework for Compiler Autotuning,","venue":null,"work_id":"accc57dd-3d7c-4998-8e37-b401eef22686","year":2026},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.728783Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:b1a9dabdddfa4c4c3a163ed3c52c201002bfef2d297d4dad36ddfe0aef3a261f","observation_id":"8f5bbd0c-ebf8-4f08-8c91-977d1b1affde","resolution":{"observed_at":"2026-08-01T01:25:54.919787Z","resolver_source":"doi","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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.731415Z","title":"CodeBERT: A pre-trained model for programming and natural languages,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.731415Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:92d51ded4014052831cadef516080ffe620378f6906ea6595b6946c16cacfa50","observation_id":"f9cfcdbe-2411-40dd-9814-f59a7cf9f045","resolution":{"observed_at":"2026-08-01T01:25:24.731415Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06347","last_updated":"2017-08-28T09:20:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-07-20T02:32:33Z","title":"Proximal Policy Optimization Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.06347","snapshot_observed_at":"2026-08-01T01:25:24.733838Z","title":"Prox- imal policy optimization algorithms,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.733838Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:fc1a7e1984c6f01d9e012b637aa187d4c85a034f398438f656c1113223493aea","observation_id":"ddf9c64d-02e8-4816-bf74-256a4afe1c44","resolution":{"observed_at":"2026-08-01T01:25:24.733838Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.736673Z","title":"PyTorch: An imperative style, high-performance deep learning library,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.736673Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:6dfa8685a5f20bfcd0570b6d5a7121e4d1546a1f87055f94337d59837a70833c","observation_id":"fd258e68-dd57-4b2e-bc8b-9b29ede81901","resolution":{"observed_at":"2026-08-01T01:25:24.736673Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.739157Z","title":"Transformers: State- of-the-art natural language processing,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.739157Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:5056a90e541f1325694649647e5be0b53b07d050405f7aad539558cf07031419","observation_id":"74021650-c907-4182-afbe-22198a1704f7","resolution":{"observed_at":"2026-08-01T01:25:24.739157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.741878Z","title":"Available: https://gcc.gnu.org/onlinedocs/gcc- 15.2.0/gcc/Optimize-Options.html","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.741878Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:29f3dce8d653c07cebb0e38119177d0ae7a5e94937ced984009a1829f139cdcb","observation_id":"22fb54ac-810e-4233-8ce1-a3253f46f680","resolution":{"observed_at":"2026-08-01T01:25:24.741878Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.744459Z","title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning,","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.744459Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:a6ddd6e90c1008e8b4611957f506f02cdf5a2af34076e590d5370b4f701e5535","observation_id":"6feb5105-0aac-4094-bb30-1160518014cd","resolution":{"observed_at":"2026-08-01T01:25:24.744459Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.747298Z","title":"Micomp: Mitigating the compiler phase-ordering problem using optimization sub-sequences and machine learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.747298Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:0636bdbfeda2857a1b517dc179d16c1d8b6e2c544261445bd6adbf20c6f01814","observation_id":"c555b728-b683-49e1-87ff-ece954c9d4a2","resolution":{"observed_at":"2026-08-01T01:25:24.747298Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.749781Z","title":"AutoPhase: Compiler phase-ordering for HLS with deep reinforcement learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.749781Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:22cd801295237e253d612a94611c2daa606835617cfd6520f82f25d3e4b95326","observation_id":"24fb0366-27c5-447a-99de-844de819fce1","resolution":{"observed_at":"2026-08-01T01:25:24.749781Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.752298Z","title":"Mitigating the compiler optimization phase-ordering problem using machine learning,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.752298Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:184cd81a3f26a69617dec33de62377c94bb07ff40296f394118353877ab98a52","observation_id":"78a3a339-43be-4663-baf4-4da8b1894aa6","resolution":{"observed_at":"2026-08-01T01:25:24.752298Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.754914Z","title":"MILEPOST GCC: Machine learning enabled self-tuning compiler,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.754914Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:12808687ceb322b8e35031d469dc2603bbf9d5ce0cdc38ce4f09f838bc6382a5","observation_id":"6a5fd666-6fa0-4767-b591-7b538dcf620c","resolution":{"observed_at":"2026-08-01T01:25:24.754914Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.757419Z","title":"CompilerGym: Robust, performant compiler optimization environments for AI research,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.757419Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:f6cd2c3716aed11f7eb7afa55f1a6002b38822c0c25946719d58b208740c779d","observation_id":"d342bd6c-4eba-41f9-b225-b4ee35f3c9e7","resolution":{"observed_at":"2026-08-01T01:25:24.757419Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.04808","last_updated":"2021-01-13T00:02:49Z","snapshot_observed_at":"2026-07-06T10:32:03.160764Z","submitted_at":"2021-01-13T00:02:49Z","title":"MLGO: a Machine Learning Guided Compiler Optimizations Framework","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.04808","snapshot_observed_at":"2026-08-01T01:25:24.759911Z","title":"MLGO: A machine learning guided compiler optimizations frame- work,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.759911Z"},"links":{"cited_paper":"/paper/2101.04808","citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:f34ec1c064fd1ce48233cac824f7b750c5dc0549eae5456593bc5bb9ff150cf5","observation_id":"4922a27f-7128-47c7-9b30-66c38b8b3737","resolution":{"observed_at":"2026-08-01T01:25:24.759911Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.07062","last_updated":"2023-09-11T22:11:46Z","snapshot_observed_at":"2026-08-04T14:17:17.034755Z","submitted_at":"2023-09-11T22:11:46Z","title":"Large Language Models for Compiler Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.07062","snapshot_observed_at":"2026-08-01T01:25:24.762536Z","title":"Large language models for compiler optimization,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.762536Z"},"links":{"cited_paper":"/paper/2309.07062","citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:b31e392f1ce886eb4cbfdacdabf3b95c6933f4daf8d1b757e7321039fb751b8b","observation_id":"d3fc32e6-a3e7-4d34-9241-865746fd723e","resolution":{"observed_at":"2026-08-01T01:25:24.762536Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.765308Z","title":"LLM Compiler: Foundation language models for compiler optimization,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.765308Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:075fd12ef310b1edfce279db76eb759da96b5219570d9a5406bf3b4023261b1f","observation_id":"cd99df44-8468-4dca-9420-2ee98572baba","resolution":{"observed_at":"2026-08-01T01:25:24.765308Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.767994Z","title":"DeCOS: Data-efficient reinforcement learning for compiler optimization selection ignited by LLM,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.767994Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:d454b476fcc3d59684b526e6bcc0178b2448d00da108bab08e139d303089dc46","observation_id":"d9a95719-4200-4fbc-89f8-29c0de1e7111","resolution":{"observed_at":"2026-08-01T01:25:24.767994Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:25:24.770921Z","title":"LLM- VeriOpt: Verification-guided reinforcement learning for LLM-based compiler optimization,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-01T01:25:24.770921Z"},"links":{"citing_paper":"/paper/2607.25831"},"observation_digest":"sha256:104f257afe14e2ea4c137ede7dff852e40a18ee76a210ee096701ff0bca00792","observation_id":"99d2d371-e326-4782-b068-07d803124255","resolution":{"observed_at":"2026-08-01T01:25:24.770921Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.25831","last_updated":"2026-07-28T15:11:02Z","latest_version":1,"primary_category":"cs.SE","snapshot_observed_at":"2026-08-05T08:10:32.297594Z","submitted_at":"2026-07-28T15:11:02Z","title":"WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning"},"reference_resolution":{"displayed":38,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":37,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":38},"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 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2607.25831."}