{"as_of":"2026-08-16T11:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2e79e6e8c99581a056cf41313077f14a05167bd5e5be4b08b200178e86ed2d0b","coverage":[{"denominator":115,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T14:42:15.218877Z","state":"measured"},{"denominator":101,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":101,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T14:42:14.814682Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-14T14:42:15.484287Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"cited_work":{"arxiv_id":"1908.02894","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.02894","snapshot_observed_at":"2026-08-14T14:42:15.484287Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","venue":"cs.LG","work_id":"6f4602c7-521c-4a2d-b79c-faff18d9a156","year":2019},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.814682Z"},"links":{"cited_paper":"/paper/1908.02894","citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:eefe25dd13b3451df2933e6931a4ff2dbd02e7af43ad3e2204fb359bf1dc7c46","observation_id":"1a6e8f33-6c9f-4e7e-9120-f6bd9621daa0","resolution":{"observed_at":"2026-08-14T14:42:15.489711Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1908.02894/citation-record","integrity":"/paper/1908.02894/integrity","json":"/paper/1908.02894/citation-record.json","paper":"/paper/1908.02894"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:14.740592Z","title":"SCIP: solving constraint integer programs","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.740592Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:3ca751c7f42c18ad0c239ae0ce26b3b6a876867607f263c556d21aa810874707","observation_id":"454decad-89c1-450f-a189-2b169eb02c4d","resolution":{"observed_at":"2026-08-14T14:42:14.740592Z","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":"2026-08-14T14:42:14.746486Z","title":"Learning to prune: Speeding up repeated computations","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.746486Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:259e287552f9b7612540489c45c0c3bd304ef924dfab65cc55c2a4ed8db3d597","observation_id":"d35835b4-5324-4f65-a911-bafaefdcd269","resolution":{"observed_at":"2026-08-14T14:42:14.746486Z","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":"2026-08-14T14:42:14.751725Z","title":"Densit´ e et dimension","venue":null,"work_id":null,"year":1983},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.751725Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:e2f79805b3c4e4bd4a6757e185cabe0fd21188756633afb3a9eff932e9200f56","observation_id":"dbaccf17-dfbe-47b5-9b0b-f19eee1e3eb8","resolution":{"observed_at":"2026-08-14T14:42:14.751725Z","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":"2026-08-14T14:42:14.756680Z","title":"Data-driven algorithm design","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.756680Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:f94ce7b6acdd0e347cad8c9661f14bdb27a9fac2896966de23f6e36c73b8eb44","observation_id":"d20690da-b5dd-4fd3-ad6c-488509297f02","resolution":{"observed_at":"2026-08-14T14:42:14.756680Z","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":"2026-08-14T14:42:14.761337Z","title":"Mechanism design via machine learning","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.761337Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:50cc4b40d31232de08b4794a52ed7277343b0b2554d5ee41882425093caf6227","observation_id":"65114c32-a9d7-41b0-a56e-d380f96c9a58","resolution":{"observed_at":"2026-08-14T14:42:14.761337Z","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":"2026-08-14T14:42:14.766287Z","title":"Sample complexity of auto- mated mechanism design","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.766287Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:bf3e85eb03ea62d7a7b9128f64d14efb3ecd38eb241b3b8b3eb9bbfec39f1587","observation_id":"d7c4a696-51d1-40b6-9d86-92d16cf57568","resolution":{"observed_at":"2026-08-14T14:42:14.766287Z","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":"2026-08-14T14:42:14.771549Z","title":"Learning- theoretic foundations of algorithm configuration for combinatorial partitioning problems","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.771549Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:a14ec69a3117ce8a7f0d7b86a346a0761995fab016a20fc8ef092881575dde96","observation_id":"5178db69-f679-45c0-b80e-82cfe3d6e26f","resolution":{"observed_at":"2026-08-14T14:42:14.771549Z","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":"2026-08-14T14:42:14.776083Z","title":"Learning to branch","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.776083Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:2caa157f206e6870f9f2be3b2cada5b3da5d95570b7d102d8bd93ad83194f9c6","observation_id":"debb3c38-e78a-455a-b5d6-aef7f1fb3abe","resolution":{"observed_at":"2026-08-14T14:42:14.776083Z","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":"2026-08-14T14:42:14.780817Z","title":"Dispersion for data-driven algorithm design, online learning, and private optimization","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.780817Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:8e7c7a9d777ef6450e9b2b9b8c7c987b17b34830a17501c5c2be3ed26fa9a37d","observation_id":"2d97e5b6-a77e-4271-a6c1-a662fe49987b","resolution":{"observed_at":"2026-08-14T14:42:14.780817Z","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":"2026-08-14T14:42:14.785545Z","title":"A general theory of sample complexity for multi-item profit maximization","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.785545Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:b79a41bbe6d006e22ebeab8acb788ca07a062c3b1116a4e7eda8d5a4b14343ee","observation_id":"44adc20f-5c0c-4979-a7d2-00adab54b9a5","resolution":{"observed_at":"2026-08-14T14:42:14.785545Z","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":"2026-08-14T14:42:14.790463Z","title":"Learning to link","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.790463Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:1b0a6587a9bc17cb233b76819bafc913fb13b1b01f334ea0c7fd05a315298115","observation_id":"9c8f5301-1353-46d1-b903-cb5ae10919fe","resolution":{"observed_at":"2026-08-14T14:42:14.790463Z","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":"2026-08-14T14:42:14.795089Z","title":"Semi-bandit optimization in the dispersed setting","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.795089Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:713a94ff8b58d1f28baa390042b92ceeb04ff3b8c09c8baf7e628b8242784af3","observation_id":"07ab0632-8227-4069-926b-80d78365ecb1","resolution":{"observed_at":"2026-08-14T14:42:14.795089Z","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":"2026-08-14T14:42:14.799812Z","title":"Learning to optimize com- putational resources: Frugal training with generalization guarantees","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.799812Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:b321d02fe7e9f7c6afb40b89b7b6c6dea394135d369ae6dc8d1e3cd2eb20fc7a","observation_id":"5b6dfa07-fe18-49a1-9750-9e02e21be51a","resolution":{"observed_at":"2026-08-14T14:42:14.799812Z","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":"2026-08-14T14:42:14.804860Z","title":"Generalization in portfolio- based algorithm selection","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.804860Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:279f3e6c1838148e33896249f3d77d957a74b682e448b2cbb5d41882cfbb12dd","observation_id":"cfe63534-e285-4614-bb4b-9f77e3ab32ca","resolution":{"observed_at":"2026-08-14T14:42:14.804860Z","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":"2026-08-14T14:42:14.809599Z","title":"Some unexpected expected behavior results for bin packing","venue":null,"work_id":null,"year":1984},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.809599Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:01ab1b35e7fcf6637e2b9116fd0b60fda2c6d1f0ab1188ee36af10e7e742e657","observation_id":"229a31be-983a-4cdf-9a93-6db264295ce1","resolution":{"observed_at":"2026-08-14T14:42:14.809599Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"cited_work":{"arxiv_id":"1908.02894","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.02894","snapshot_observed_at":"2026-08-14T14:42:15.484287Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","venue":"cs.LG","work_id":"6f4602c7-521c-4a2d-b79c-faff18d9a156","year":2019},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.814682Z"},"links":{"cited_paper":"/paper/1908.02894","citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:eefe25dd13b3451df2933e6931a4ff2dbd02e7af43ad3e2204fb359bf1dc7c46","observation_id":"1a6e8f33-6c9f-4e7e-9120-f6bd9621daa0","resolution":{"observed_at":"2026-08-14T14:42:15.489711Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:42:14.819810Z","title":"Learning complexity of simulated annealing","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.819810Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:62e9a1d06869eb3061335b9fd726440e2d8687f5172e9eeb110d9b299b3c3a53","observation_id":"ecf74e06-2b9a-4b7b-a7d6-4dd419f18139","resolution":{"observed_at":"2026-08-14T14:42:14.819810Z","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":"2026-08-14T14:42:14.824735Z","title":"Partition of space","venue":null,"work_id":null,"year":1943},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.824735Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:e791ee762b0081ce2034f2845b7d647c721833dc0a668a92efb853c3477da50c","observation_id":"08bd1349-2f2f-468d-8210-9ccd741b92f6","resolution":{"observed_at":"2026-08-14T14:42:14.824735Z","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":"2026-08-14T14:42:14.829763Z","title":"Learning multi-item auctions with (or without) samples","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.829763Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:aa88d78db61294bec121b63ad90b17e3f81aebc2f23816efc4c6e7b267bfa0e3","observation_id":"a13013e6-4c44-4f63-b3ef-169ca8b1e8e8","resolution":{"observed_at":"2026-08-14T14:42:14.829763Z","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":"2026-08-14T14:42:14.834520Z","title":"Pandora’s box with correlations: Learning and approximation","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.834520Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:d13214b573c2021a0429c9d439d939a8ed0b5b5f3ce8d9e3d680d975428cc8aa","observation_id":"2476362f-5abd-430f-88b4-c214b959e515","resolution":{"observed_at":"2026-08-14T14:42:14.834520Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10294","last_updated":"2021-03-18T14:49:52Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T14:49:52Z","title":"Learning to Schedule Heuristics in Branch-and-Bound","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10294","snapshot_observed_at":"2026-08-14T14:42:14.839085Z","title":"Learning to schedule heuristics in branch-and-bound","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.839085Z"},"links":{"cited_paper":"/paper/2103.10294","citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:30a805f9b28fb0b60e4973811dd53ef3251d43f44b3b64e97cc4fbdaced10c23","observation_id":"4573a097-64cb-4f0d-8b39-44c33b0ad6d4","resolution":{"observed_at":"2026-08-14T14:42:14.839085Z","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":"2026-08-14T14:42:14.844142Z","title":null,"venue":null,"work_id":null,"year":1971},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.844142Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:2c2bae9045794f9f0266c517bb9b0cabcc85608b3a12c3c21a4878e28a300ecc","observation_id":"356529ea-04d1-4cf2-a5fb-b2505578376d","resolution":{"observed_at":"2026-08-14T14:42:14.844142Z","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":"2026-08-14T14:42:14.848793Z","title":"The sample complexity of revenue maximization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.848793Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:a146d6efa4b36beda863f724187e95f0c7c06e6143e829c95ecc4945cc87d509","observation_id":"c3444239-2ab6-4a56-b6d8-1e8297c6c09c","resolution":{"observed_at":"2026-08-14T14:42:14.848793Z","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":"2026-08-14T14:42:14.853453Z","title":"Parameter Advising for Multiple Sequence Alignment","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.853453Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:69bb19ff3bb490aabc7c42403ed01e214e2b4de78e1e2adf898244a64239ebc7","observation_id":"41089d4d-ee39-446d-ac10-fde2eed7a01a","resolution":{"observed_at":"2026-08-14T14:42:14.853453Z","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":"2026-08-14T14:42:14.858069Z","title":"The sample complexity of auctions with side information","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.858069Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:291ef32454e2a1912634951f1041906ffe86422372607c62ae26b3528a41b2d4","observation_id":"0cedc2a2-a8cc-4c92-8092-ffcc78db0124","resolution":{"observed_at":"2026-08-14T14:42:14.858069Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.06726","last_updated":"2020-11-13T02:24:02Z","snapshot_observed_at":"2026-07-06T10:14:13.767423Z","submitted_at":"2020-11-13T02:24:02Z","title":"Secretaries with Advice","version":1},"cited_work":{"arxiv_id":"2011.06726","doi":null,"metadata_source":"pith","pith_arxiv_id":"2011.06726","snapshot_observed_at":"2026-08-14T14:42:15.446007Z","title":"Secretaries with Advice","venue":"cs.DS","work_id":"5d755662-daf9-49c4-8ac0-1a0c4e544775","year":2020},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.862893Z"},"links":{"cited_paper":"/paper/2011.06726","citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:6e7fa9675a2da9cd4d28603468e8da63226ecae472c28fe592d512eb70f17dd9","observation_id":"6200f28d-4938-4c4e-83b1-d974d4ac9df6","resolution":{"observed_at":"2026-08-14T14:42:15.451105Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:42:14.868138Z","title":"Learning-based support estimation in sublinear time","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.868138Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:4773d8561ca7f5f1ae3820e2d64f4231deff07a4027a0ad94f1327ac91b6ed0e","observation_id":"04f22d81-b976-4357-8ebd-e0923d5b008b","resolution":{"observed_at":"2026-08-14T14:42:14.868138Z","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":"2026-08-14T14:42:14.872722Z","title":"Quality measures for protein alignment benchmarks","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.872722Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:93e69d045361c82701bcb4c18c9f718145ecf3733a7a78e773bcb651a07e616b","observation_id":"a827b1d8-be7e-4fb3-bb70-cb6490084acb","resolution":{"observed_at":"2026-08-14T14:42:14.872722Z","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":"2026-08-14T14:42:14.877712Z","title":"Designing and learning optimal finite support auctions","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.877712Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:83fada9b3727b9c0f34f37d5a172d9c5a16a7a8d071cde86901c7e2c25b373ba","observation_id":"0efbc738-0689-4117-a336-3bd7f04c8104","resolution":{"observed_at":"2026-08-14T14:42:14.877712Z","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":"2026-08-14T14:42:14.882385Z","title":"Rein- forcement learning for variable selection in a branch and bound algorithm","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.882385Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:2d53485473dc436cd342e5cd7f9aec1a28bae055687e05cb4e47daea634e50bf","observation_id":"4d020909-dbb2-4f1d-b0db-bf5d5926b581","resolution":{"observed_at":"2026-08-14T14:42:14.882385Z","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":"2026-08-14T14:42:14.887193Z","title":"Learning augmented energy minimization via speed scaling","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.887193Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:d63921d755c4b311ab1c57ae7c9b9e3f8def6836736fd9db785d97297a311c86","observation_id":"96737da3-f516-4f1b-be12-26a3408d7b53","resolution":{"observed_at":"2026-08-14T14:42:14.887193Z","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":"2026-08-14T14:42:14.891817Z","title":"The primal-dual method for learn- ing augmented algorithms","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.891817Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:a2ddbf06548611c7afeba01ef07314d73b18c992985f6ca90b7f3273561c0fd5","observation_id":"2155ea39-19ee-4a5d-b679-d03cd11011b5","resolution":{"observed_at":"2026-08-14T14:42:14.891817Z","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":"2026-08-14T14:42:14.896386Z","title":"The RPR 2 rounding technique for semidefinite programs","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.896386Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:b0ed4cb3a7c7d8fc21f7914e01bf55435108bddd146934b2f3a94d4b7e9ac44d","observation_id":"6795d287-e423-4c46-ba3d-0515bcf59937","resolution":{"observed_at":"2026-08-14T14:42:14.896386Z","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":"2026-08-14T14:42:14.900953Z","title":"Progressive sequence alignment as a prerequisite to correct phylogenetic trees","venue":null,"work_id":null,"year":1987},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.900953Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:5399e65380d4aa1488a0820abeddd3b1954f9f71ec74f0c6fe5a933a099b4800","observation_id":"91b9aab0-a474-4b66-93de-a48b95f92c93","resolution":{"observed_at":"2026-08-14T14:42:14.900953Z","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":"2026-08-14T14:42:14.905959Z","title":"MIPaaL: Mixed integer program as a layer","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.905959Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:1645f84bde7bad21f11d29eb56328b7caae8224032bfea60422b192b5c8f328f","observation_id":"e4568c05-23e3-4b37-8866-0485d2b11f58","resolution":{"observed_at":"2026-08-14T14:42:14.905959Z","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":"2026-08-14T14:42:14.910412Z","title":"Parametric multiple sequence alignment and phylogeny construction","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.910412Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:41e033545e51373f5ab17a3b3726ec94b5baf75d151c4f2ccbafa96b2473f71f","observation_id":"3e838d11-13f7-43e8-bee7-a57ac0424681","resolution":{"observed_at":"2026-08-14T14:42:14.910412Z","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":"2026-08-14T14:42:14.914797Z","title":"Identification of alternative topological domains in chromatin","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.914797Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:a1a7e8966f12ca10fef1134b52228ef3dd27c77ab057c17ff4412a96f67180d2","observation_id":"ff65d59d-5024-42c8-bcdb-a7780c30b3f8","resolution":{"observed_at":"2026-08-14T14:42:14.914797Z","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":"2026-08-14T14:42:14.919464Z","title":"A machine learning- based branch and price algorithm for a sampled vehicle routing problem","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.919464Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:3886a629136331e80f60b478ec91b36adfb7e3c0f906094565fa9c187c51999e","observation_id":"64034912-6efb-4837-baf8-a6578880bb27","resolution":{"observed_at":"2026-08-14T14:42:14.919464Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.601195Z","title":"Supervising unsupervised learning","venue":null,"work_id":"ae0ca8ec-0d6d-4679-89fa-e31795fe5474","year":2018},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.924737Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:fa4dcce2aad1e12156e9aee3a023055336644995c84121c0200993c30df17d3d","observation_id":"4882ec53-7830-4f04-abd5-ed4c5c7516c3","resolution":{"observed_at":"2026-08-14T14:42:16.606100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.585351Z","title":"Information-theoretic approaches to branching in search","venue":null,"work_id":"bb4fa6c9-c8cc-491f-90a4-7c07e53b7755","year":2011},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.929644Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:7c8012ca9728509ff0a43585f4575b9da843ec37c668b744178858f8d400a205","observation_id":"6034d43a-013f-4ff8-907c-8e8933d1bfd6","resolution":{"observed_at":"2026-08-14T14:42:16.590913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.569560Z","title":"Improved approximation algorithms for max- imum cut and satisfiability problems using semidefinite programming","venue":null,"work_id":"3805a56f-264b-4564-a85a-bc9f8aca5d42","year":1995},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.934524Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:7b0d72f389f19ca51d43868a76ee227679053ee969f812caea5980d10f628b21","observation_id":"e532deda-429f-4409-b8dd-e19280225001","resolution":{"observed_at":"2026-08-14T14:42:16.574970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.553725Z","title":"Eigentaste: A constant time collaborative filtering algorithm","venue":null,"work_id":"9f0cbc57-01ed-4ae7-b691-93f399ef5c0b","year":2001},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.939205Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:f02292ec9762da49a8331330e08862f64d7cbb3a980cccc975833c0ca83fba65","observation_id":"fb21592d-0453-4782-8f99-6ef0100495ea","resolution":{"observed_at":"2026-08-14T14:42:16.558757Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.537868Z","title":"Efficient empirical revenue maximization in single- parameter auction environments","venue":null,"work_id":"b9d4a691-59c0-4894-a5c5-5e9c62c9bd99","year":2017},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.944491Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:d513eadc1bf0b4c9c91f6f7fefd8612a4b5f62f8fac071df276552fbb13f0e89","observation_id":"d6a71b2d-cb5e-467f-928b-392ccd0d7985","resolution":{"observed_at":"2026-08-14T14:42:16.543061Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.521905Z","title":"The sample complexity of up-to- ε multi- dimensional revenue maximization","venue":null,"work_id":"14b71cb6-ef18-40b6-9067-ef2f181d6dbd","year":2021},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.949106Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:5710a808751f1654004f2b6c4ef38863d83b1e6ed14ce8dd337a061914b11bc2","observation_id":"f564e2bb-8f80-4164-a0ab-60dc6b56860c","resolution":{"observed_at":"2026-08-14T14:42:16.526686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.505442Z","title":"An improved algorithm for matching biological sequences","venue":null,"work_id":"2adabec6-1c69-485d-be5e-825997140638","year":1982},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.953827Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:46a7d56d7748b6a312b55ae4d873b5daf3c2ed556397fdbc16bed7100a4dcf16","observation_id":"3e3a77f2-7e73-42f6-91ad-ee394b15d70e","resolution":{"observed_at":"2026-08-14T14:42:16.511249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.488324Z","title":"Incentives in teams","venue":null,"work_id":"e6b1b270-74fa-479b-b020-5d4f29ce6109","year":1973},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.958438Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:3da6f497e23fa7aaf7d259edba8ae108b5bb62297ea8961c5864ddb6c32595a1","observation_id":"198ab7ba-f19e-4f22-ae95-2d5e7c0d5d52","resolution":{"observed_at":"2026-08-14T14:42:16.493461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.465034Z","title":"Settling the sample complexity of single- parameter revenue maximization","venue":null,"work_id":"15f5cc9b-33d8-43b8-b5b5-6a52441f4e9c","year":2019},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.963023Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:48879be6b759dc18a9938beb5cce882a068e939ed6923b9ff75a7148f647b8e3","observation_id":"ba3f6d38-09de-40ff-9e69-1e5344203d4f","resolution":{"observed_at":"2026-08-14T14:42:16.470230Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.449400Z","title":"A PAC approach to application-specific algorithm se- lection","venue":null,"work_id":"9b6752f0-a790-4f48-ad50-80aac9facb54","year":2017},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.967508Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:2f574da91937f2dfcf30ca02efb9a38e32672a8510b9ee650a4614a7c1563618","observation_id":"c480324d-3a40-49f2-854a-54d8f06dcb33","resolution":{"observed_at":"2026-08-14T14:42:16.454453Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.433481Z","title":"Parametric and inverse-parametric sequence alignment with xparal","venue":null,"work_id":"ec330e70-dabf-4487-9c95-7511323ad9b5","year":1996},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.972332Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:373696ab5f6786b45cae84306a7666cd98ec8aaeddf3f48e6260a2b5f060c40b","observation_id":"345d6be6-2e32-4701-9e14-56cd569b6adb","resolution":{"observed_at":"2026-08-14T14:42:16.438997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.418219Z","title":"Parametric optimization of se- quence alignment","venue":null,"work_id":"62427cdd-f423-40b1-8eda-dad2b6c8c98d","year":1994},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.976969Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:20b9158b968ec4e256084462d90a0316de06c11577a05799e6144e8c57cbd9cd","observation_id":"27d97c0f-9982-449b-8c33-252a6ca269e5","resolution":{"observed_at":"2026-08-14T14:42:16.423189Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:42:14.981966Z","title":"Clustal: a package for performing multiple sequence alignment on a microcomputer","venue":null,"work_id":null,"year":1988},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.981966Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:97cbcfdcfa18755c927899afe7771bc06c5f5f99edf9b7c56076d305e3d00fa1","observation_id":"41705506-cdee-47e0-ad27-63c2d7eddf7e","resolution":{"observed_at":"2026-08-14T14:42:14.981966Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.392108Z","title":"Holley, Jean Apgar, George A","venue":null,"work_id":"083a6622-cc25-4275-aa1b-83eb7dce81e7","year":1965},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.986582Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:c1e015897d2a8cfbf1ea16e9f2929312eb64de55cff834e48560901605e2f6a3","observation_id":"bb46e198-a8e7-4dc6-afea-2811e6fdd1ac","resolution":{"observed_at":"2026-08-14T14:42:16.396879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.376291Z","title":"A Bayesian approach to tackling hard computational problems","venue":null,"work_id":"c1d445d3-bc49-4556-bff9-a0c52e8f104c","year":2001},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.991245Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:c941ce74cd607db744727d8de1d398c6aaca5e4a88118936b0f6d3ca8d1569dc","observation_id":"4daf9799-9037-46bf-9786-70060d793da6","resolution":{"observed_at":"2026-08-14T14:42:16.381322Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.359532Z","title":"Learning-based frequency estima- tion algorithms","venue":null,"work_id":"e2647da7-0f40-47da-837f-ff7b18ed6e67","year":2019},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:14.995818Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:ea3e271666582b1ad950cac89e2e90877606a173d52aecb18ff995429e295fd4","observation_id":"d1efd392-8c63-4793-ade2-949fa4aff68a","resolution":{"observed_at":"2026-08-14T14:42:16.364305Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.344482Z","title":"ParamILS: An auto- matic algorithm configuration framework","venue":null,"work_id":"7b8d3d4f-4c1f-4413-bc29-46ff935b7e84","year":2009},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.000565Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:db5b69cdf5e8eb2e928ab48238599a8a9c26f2c229480a8a2ecfb2ef8682213c","observation_id":"b099935c-6997-4084-abff-ac611d9b1bfc","resolution":{"observed_at":"2026-08-14T14:42:16.349624Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.05028","last_updated":"2020-06-09T03:15:34Z","snapshot_observed_at":"2026-08-13T22:29:00.733086Z","submitted_at":"2020-06-09T03:15:34Z","title":"Online Page Migration with ML Advice","version":1},"cited_work":{"arxiv_id":"2006.05028","doi":null,"metadata_source":"pith","pith_arxiv_id":"2006.05028","snapshot_observed_at":"2026-08-14T14:42:15.422151Z","title":"Online Page Migration with ML Advice","venue":"cs.DS","work_id":"fb15b241-bfe8-4b68-98c6-353507345bf0","year":2020},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.005279Z"},"links":{"cited_paper":"/paper/2006.05028","citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:c8a85f3d6531e7e574d651b98816f56977d53797f0b027f4a6886a83a7b73693","observation_id":"4b7a2636-2440-4df2-bd0c-cf5745d7a236","resolution":{"observed_at":"2026-08-14T14:42:15.427873Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.329317Z","title":"An experimental study of polylogarithmic, fully dynamic, connectivity algorithms","venue":null,"work_id":"f688a835-baf1-4ab8-8231-c7ed0b95e2fc","year":2002},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.010551Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:725e73a2cd4ad9ae80b3ebbfe1c4e46b464836e8d640ddc036da960f05733637","observation_id":"3544f945-fed2-4811-a71e-9e8b62ef062a","resolution":{"observed_at":"2026-08-14T14:42:16.334365Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.313772Z","title":"ISAC-instance-specific algorithm configuration","venue":null,"work_id":"9066a6fd-6604-4c89-a535-50a05d218ff8","year":2010},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.015441Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:643a3476bb9cb811bf9773d4bf5c3762fca8174bb764c632fb491abc4e122918","observation_id":"609a3c49-529f-4793-ae1e-b1bcc3ddaf35","resolution":{"observed_at":"2026-08-14T14:42:16.318892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.298845Z","title":"Aligning alignments exactly","venue":null,"work_id":"8eef608b-26ea-4788-82d2-92bfcbacbb26","year":2004},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.020640Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:62f3d1b0c8388609aa6ca8182f54c0ee4212f88b6f8002e3c582d60d355b2970","observation_id":"dfeca0e1-984c-4cde-843a-dd7bbddad1f7","resolution":{"observed_at":"2026-08-14T14:42:16.303730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.283501Z","title":"Inverse sequence alignment from partial examples","venue":null,"work_id":"90c0072f-fddd-47c6-88e0-e74cfa665221","year":2007},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.025398Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:b2380a3c67da7eb219d4658de831142e17dab8945f494dddce7c6eae3e23f236","observation_id":"b2b7b739-0ef9-4c20-a63b-965589b676d8","resolution":{"observed_at":"2026-08-14T14:42:16.288365Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.267982Z","title":"Efficiency through procrastina- tion: Approximately optimal algorithm configuration with runtime guarantees","venue":null,"work_id":"68d44255-5a20-4154-93b1-aa37f158bcda","year":2017},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.030133Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:08f6aede10b067fd5e51ff07ac2a90fdb909daf91bcb23af593bac731c3fed4d","observation_id":"f70a5d3f-42f6-4ca5-9cfd-e985deea2a51","resolution":{"observed_at":"2026-08-14T14:42:16.272892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.252695Z","title":"Procrastinat- ing with confidence: Near-optimal, anytime, adaptive algorithm configuration","venue":null,"work_id":"c571f282-26c5-40ba-a91f-fc7ad926d90f","year":2019},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.035093Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:2b7ca7776a855d3c093ee0f480d442a34fe84a3886a8563fcce23b8186e5f26f","observation_id":"051f292e-0e30-43e2-90e9-3ea4f441bbe5","resolution":{"observed_at":"2026-08-14T14:42:16.257684Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.16378","last_updated":"2021-03-30T14:19:30Z","snapshot_observed_at":"2026-08-16T10:28:39.944633Z","submitted_at":"2021-03-30T14:19:30Z","title":"End-to-End Constrained Optimization Learning: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.16378","snapshot_observed_at":"2026-08-14T14:42:15.039889Z","title":"End-to-end constrained optimization learning: A survey","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.039889Z"},"links":{"cited_paper":"/paper/2103.16378","citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:46368ac21f1d5f977858cd6c8f380890a3e821f6b13b768976b366f940eadbba","observation_id":"762a20f5-4a1d-4dce-87c9-e650264fb1a9","resolution":{"observed_at":"2026-08-14T14:42:15.039889Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.237032Z","title":"An automatic method of solving discrete programming problems","venue":null,"work_id":"ef265f21-e586-4639-a61c-a670b15cd315","year":1960},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.045094Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:58afe256d1f27dc85e095fc544a7b3abcfe70da68b4e9e73174485243b993b9d","observation_id":"67e28948-fcea-4132-a50e-4016a8f41be3","resolution":{"observed_at":"2026-08-14T14:42:16.242313Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.11743","last_updated":"2021-07-02T01:59:10Z","snapshot_observed_at":"2026-07-06T10:17:10.235209Z","submitted_at":"2020-11-23T21:38:57Z","title":"Learnable and Instance-Robust Predictions for Online Matching, Flows and Load Balancing","version":2},"cited_work":{"arxiv_id":"2011.11743","doi":null,"metadata_source":"pith","pith_arxiv_id":"2011.11743","snapshot_observed_at":"2026-08-14T14:42:15.381066Z","title":"Learnable and Instance-Robust Predictions for Online Matching, Flows and Load Balancing","venue":"cs.LG","work_id":"3786881d-8fc5-46b4-9545-3a340c98cd09","year":2020},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.049855Z"},"links":{"cited_paper":"/paper/2011.11743","citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:4bc6c143ecda26b7ecb86e377b8f509f3db7743680de40751286c3e373c35e14","observation_id":"3e029a16-758b-43aa-814e-00c03e22058c","resolution":{"observed_at":"2026-08-14T14:42:15.386862Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.220976Z","title":"Empirical hardness models: Methodology and a case study on combinatorial auctions","venue":null,"work_id":"33cc51bb-fe00-4e27-a42c-99d22f9b2c1f","year":null},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.054609Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:ffa65a357868fcc232c3c41abb7a6721b7fddc25bc693aae683f84b585ec2d23","observation_id":"dba54c12-cc73-49cc-8762-1636b52a0637","resolution":{"observed_at":"2026-08-14T14:42:16.226259Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1126/science.11813","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:15.339299Z","title":"van Berkum, Louise Williams, Maxim Imakaev, Tobias Ragoczy, Agnes Telling, Ido Amit, Bryan R","venue":null,"work_id":"fdee26a7-ec46-47d9-92cc-6d3b407526e6","year":2009},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.059682Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:3eee02a77fa3c62e4984308bdb985426c75e2253416106b6addb1c7898719520","observation_id":"3e4e252d-f3c2-4f94-832d-cf92a5fcc7ce","resolution":{"observed_at":"2026-08-14T14:42:15.346187Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.205664Z","title":"Methods for boosting revenue in combinatorial auctions","venue":null,"work_id":"764cad48-a752-4653-8bae-f97235f86465","year":2004},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.064566Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:d303cb83dd3b69070260fdd3f878f06103d64cf8e2a5cb3c8cd56fad9fb7c68d","observation_id":"21676874-eb48-433b-95b6-b03275674a02","resolution":{"observed_at":"2026-08-14T14:42:16.210592Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.189559Z","title":"Approximating revenue-maximizing combinato- rial auctions","venue":null,"work_id":"2b6babb7-a4fe-4a6d-b8f5-0508ace5a1b9","year":2005},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.069192Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:5cfa1c9833ba85210ca64c1bb7213b1fce03c305c0bc6dff4caf6c500b235377","observation_id":"2f37a9f3-c1e4-4cf6-958d-badd64044339","resolution":{"observed_at":"2026-08-14T14:42:16.195157Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.174076Z","title":"A computational study of search strategies for mixed integer programming","venue":null,"work_id":"2dfd7dc7-4aaf-430c-a40f-a4ec9f4f45db","year":1999},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.073857Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:b86a26d5e42091de2fde6cf8a1d2a617b63b8fd4e254e40b29becf955d113f46","observation_id":"a569b518-21b4-4210-a60b-98020fb3b927","resolution":{"observed_at":"2026-08-14T14:42:16.179450Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.158421Z","title":"Breaking TADs: how alterations of chromatin domains result in disease","venue":null,"work_id":"da01aa74-d499-45f4-b5b1-f32da05a3da5","year":2016},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.078475Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:d30c2ac4046dbaf973b21f2225e93ffc481434861a354553c7c15b7f150e6a5e","observation_id":"66170b18-d5a3-4ba4-bd41-531d6c12094d","resolution":{"observed_at":"2026-08-14T14:42:16.163557Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.142249Z","title":"Competitive caching with machine learned advice","venue":null,"work_id":"5922c784-b8f8-4394-ae53-d97e44d151bf","year":2018},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.083323Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:3d56d5930a610c77680ea32a3e1a7e03e90eaa5f6a9c18a136884b436024540e","observation_id":"450f4bf7-30c8-4b8a-86ed-79f3f2a3cf04","resolution":{"observed_at":"2026-08-14T14:42:16.147323Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.126649Z","title":"A guide to experimental algorithmics","venue":null,"work_id":"3c7f00b1-fe8f-45ca-8419-d341e9f812a7","year":2012},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.088149Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:69f7109fe2a45ce1ee770f45804b1fc1e8b7863a30c34d1a4da06759383f468a","observation_id":"1d442fe9-481c-427f-b7d8-cbcd348dfad4","resolution":{"observed_at":"2026-08-14T14:42:16.131539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.111603Z","title":"Roberts’ theorem with neutrality: A social welfare ordering approach","venue":null,"work_id":"3993d7a3-4ff9-443a-a8bb-eb1aeaa2eee2","year":2012},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.092781Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:8d6488920a716b62b8178adf3490cd4c0b154cfc87d89f2c05361110c9a10973","observation_id":"9bb80893-ee7b-412b-913b-1fd6fe978cd3","resolution":{"observed_at":"2026-08-14T14:42:16.116531Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.095952Z","title":"A model for learned bloom filters and optimizing by sandwiching","venue":null,"work_id":"b00893b0-8ffa-4b92-a9d3-a6887259346b","year":2018},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.097830Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:67e7ec14dce8fa8d9b908f57be79e460026a6d80455b1f2b88336bd2c24ddc3d","observation_id":"61a08065-3471-4897-be03-67a8876b1fdc","resolution":{"observed_at":"2026-08-14T14:42:16.100933Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.079877Z","title":"Learning theory and algorithms for revenue optimization in second price auctions with reserve","venue":null,"work_id":"d898ca9c-aba9-4ec8-913a-4dc60ff64a81","year":2014},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.102790Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:da357ea70b4e26c1b46e557755de3dfc89a82b734aa3b6987068f6209f229eb8","observation_id":"56a52cd8-3adb-4635-87f8-fa9aee501776","resolution":{"observed_at":"2026-08-14T14:42:16.085185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.063725Z","title":"Learning simple auctions","venue":null,"work_id":"05ca32d3-ddbf-4f4e-9e17-c3f3a5ad7bd3","year":2016},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.107849Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:30c39d3c078591794c2f4255edd09e4bf37cc994dc1cbddb5eaa131b196b73d9","observation_id":"d100c98a-ae14-47b6-a151-7dc1b1b66547","resolution":{"observed_at":"2026-08-14T14:42:16.069045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.048458Z","title":"Efficiency and budget balance in general quasi-linear domains","venue":null,"work_id":"c5f5b5d1-7bda-4c5a-838c-693a6efa6086","year":2019},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.112556Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:89ebcac637172de61b35e020568635fdb2233181f8d3bd0bd69ea1194259c011","observation_id":"c1219b90-d6a1-4bd7-a1cd-24e4d60aac5f","resolution":{"observed_at":"2026-08-14T14:42:16.053289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.031208Z","title":"Finding biologically accurate clusterings in hierarchical tree decompositions using the variation of information","venue":null,"work_id":"7a5edcbf-1cf2-4659-968c-a9674ea30655","year":2009},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.117515Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:4d40e853c25a46b60daa17756727e67bd3df3d2f5dca736df1e697a65235b57e","observation_id":"468bdf21-5e08-4d89-924d-616281ed3b54","resolution":{"observed_at":"2026-08-14T14:42:16.036883Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:16.013623Z","title":"Fast algorithm for predicting the secondary structure of single-stranded RNA","venue":null,"work_id":"1af1018d-5aa6-4a23-a78b-a7d09a7934cb","year":1980},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.122540Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:8a2f99782d22c489781a939d54e03d303b5bc770eae7012ecfd310b816ed326a","observation_id":"1039cbd0-ba4d-4325-b0ca-a133fe2d4844","resolution":{"observed_at":"2026-08-14T14:42:16.018824Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:15.997598Z","title":"Parametric inference for biological sequence analysis","venue":null,"work_id":"f34fcb30-4c00-482e-8928-c94db072e524","year":2004},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.127487Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:b759f33f829b92fdc21105972287ce955339ac9ab942ada86d3931cca87e5ba8","observation_id":"11eada1f-8eb4-49a0-bb6e-726192c32034","resolution":{"observed_at":"2026-08-14T14:42:16.002765Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:42:15.132274Z","title":"Tropical geometry of statistical models","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.132274Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:7106c86de66adb03dfe804591558a2752deff85f670d26c701b646beafc06486","observation_id":"2020dbeb-20eb-459a-b4d9-b6f9f27837f4","resolution":{"observed_at":"2026-08-14T14:42:15.132274Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:15.980693Z","title":"Convergence of Stochastic Processes","venue":null,"work_id":"6a315f1b-7105-49cc-885f-0d6ded5e1c66","year":1984},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.137363Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:52e62a6f6b3e54a571d6630b91003e74e4a7ba5ec3211ddc2fb35bfc667e3cd0","observation_id":"2a9bf340-7e13-4aab-bb92-11781e9cea7b","resolution":{"observed_at":"2026-08-14T14:42:15.986144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.06069","last_updated":"2020-11-24T21:06:00Z","snapshot_observed_at":"2026-08-13T21:04:17.375889Z","submitted_at":"2020-11-11T20:59:36Z","title":"Ecole: A Gym-like Library for Machine Learning in Combinatorial Optimization Solvers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.06069","snapshot_observed_at":"2026-08-14T14:42:15.142088Z","title":"Ecole: A gym-like library for machine learning in combinatorial optimization solvers","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.142088Z"},"links":{"cited_paper":"/paper/2011.06069","citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:53f136551ec4abc6faea4e19e7fda911dbef50df4988bf086cb066ed7909c9d5","observation_id":"9b4d3234-18fb-450a-9e4f-296079db6d46","resolution":{"observed_at":"2026-08-14T14:42:15.142088Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:15.963220Z","title":"Improving online algorithms via ML pre- dictions","venue":null,"work_id":"d992c746-e617-4d0a-8859-d819a6cb11fb","year":2018},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.147246Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:e255921035bf6f375ffcc3fe2426bccbc9ff5f0cf1c77effb19848a35a41e70a","observation_id":"c5cb38d7-e1b2-4ebd-b80d-7784f0a2ab7e","resolution":{"observed_at":"2026-08-14T14:42:15.968297Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:15.947599Z","title":"The characterization of implementable social choice rules","venue":null,"work_id":"c5ff8d09-8638-41ec-ac4f-8312dc7963e4","year":1979},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.152204Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:b0e662a739d0be6ae0198bfb0fa170ef80571cb23a792b3e7ef3739847e3a52a","observation_id":"e0c82d1b-4380-441f-b3a8-45f25c4ce40c","resolution":{"observed_at":"2026-08-14T14:42:15.952586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:42:15.157003Z","title":"Very-large-scale generalized combinatorial multi-attribute auctions: Lessons from conducting $60 billion of sourcing","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.157003Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:c40936fd6cbea3f03cfb168e09d0459b84afe56488931489a587c47bffc901e6","observation_id":"50dd0fe6-6970-4c3d-bba1-ff125fa7fc7c","resolution":{"observed_at":"2026-08-14T14:42:15.157003Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:15.921646Z","title":"Automated design of revenue-maximizing com- binatorial auctions","venue":null,"work_id":"78bad434-cb4d-4c3f-8a86-5988338f1420","year":2015},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.161567Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:95f0d01e9784e6322c1cd7132520baf62ee58b921e5da5d908df0639efc84778","observation_id":"cf3f5db0-b159-41d7-8f03-f03eb7d5a12c","resolution":{"observed_at":"2026-08-14T14:42:15.926802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:15.905675Z","title":"Michael Sauder, Jonathan W","venue":null,"work_id":"47c60f45-b99c-443c-bc25-2623181c0d67","year":2000},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.166186Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:190eb16b67a996e63e7ab13ba770cb72904a3c0a90cc043e198f71960080ce5b","observation_id":"5fb484bf-4db3-4f11-9d67-3d7f751a799a","resolution":{"observed_at":"2026-08-14T14:42:15.910606Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:15.889172Z","title":"On the density of families of sets","venue":null,"work_id":"5e4d7260-3f5b-4e73-be3b-ba062a725781","year":1972},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.170812Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:25e5cb8ca847e2e753747cf30dcf225ea2c1560cb87847a338300e957a72fb22","observation_id":"1ebaebe9-907b-4184-af91-32f41f043936","resolution":{"observed_at":"2026-08-14T14:42:15.893953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:15.873268Z","title":"Guiding high-performance SAT solvers with unsat-core predictions","venue":null,"work_id":"a55290f6-62b3-40ec-873e-22b8601b0c05","year":2019},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.175857Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:cbeaec471e6345725c54f6ac088153b4bf0d715059117613524d7ad8f0bb9c9b","observation_id":"8a1cb5cc-9b23-4825-b1a5-50e22f792084","resolution":{"observed_at":"2026-08-14T14:42:15.878382Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:42:15.180598Z","title":"Understanding machine learning: From theory to algorithms","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.180598Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:6ee078274bd09f80bb138253cbe9541a2111fd269145f72aafae52887abe8bc3","observation_id":"6c528ba4-da44-4f0e-ac7a-bc425d28f2e6","resolution":{"observed_at":"2026-08-14T14:42:15.180598Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:15.847069Z","title":"Lorm: Learning to optimize for resource management in wireless networks with few training samples","venue":null,"work_id":"e98ecf5b-70d3-4ff8-989a-da1ed4fe4db0","year":2019},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.185611Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:d0a179ad9cbd24f13539b239c503fc79078b9a0233bfce33bf5617a70734b39f","observation_id":"6765b5f1-a310-45c6-8895-831572c9266e","resolution":{"observed_at":"2026-08-14T14:42:15.852172Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:15.830934Z","title":"A general large neighborhood search framework for solving integer programs","venue":null,"work_id":"17248043-5a66-40bb-a812-aa4f373ee295","year":2020},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.190448Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:0c4e4f79f6e171d2b4fe5e52721145f8087edc06d8e9f1e5916b31608ce53a51","observation_id":"738f5e62-bcb9-4cd3-8f30-89d4f086e284","resolution":{"observed_at":"2026-08-14T14:42:15.836086Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:15.814216Z","title":"Reinforcement learning for integer program- ming: Learning to cut","venue":null,"work_id":"a56cb828-295d-433f-a705-1b1c8cffc1b6","year":2020},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.195453Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:d1fb874c4a0f574775f5fa97db5fc1669039f1a163bc7f28d7e834025678229e","observation_id":"2a71cb88-aafa-463b-b701-03a77d581602","resolution":{"observed_at":"2026-08-14T14:42:15.820262Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:15.798730Z","title":"On the zeros of finite sums of exponential functions","venue":null,"work_id":"f2393216-4442-4f04-9e2d-800f54325932","year":2006},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.200379Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:b98991929e7dc45a26ca2808bece61f5a7706a26890b4e07f522a0e4edd476e3","observation_id":"375f6840-7ac7-4b55-b2da-363ff7cbf326","resolution":{"observed_at":"2026-08-14T14:42:15.803692Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:15.783215Z","title":"On the uniform convergence of relative frequencies of events to their probabilities","venue":null,"work_id":"cde8f300-a6b2-4415-a746-8491f4a4b6c6","year":1971},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.204761Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:9cb530c698abac5c8cf33d4dab1bb074d5194cfbd0cae211250d1ddd8eb19d92","observation_id":"0fae430e-3bdc-46be-b5ef-074022db4b96","resolution":{"observed_at":"2026-08-14T14:42:15.788175Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:15.766861Z","title":"Counterspeculation, auctions, and competitive sealed tenders","venue":null,"work_id":"d8213e07-f322-43e5-9f8c-1aacf97ec936","year":1961},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.209438Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:0637ac177a8dd93cbbc7d6cdf3f6dabf2c49d4e3e412ba199c6e58d995691e43","observation_id":"9a08fefe-81b4-4331-95ed-b4de5d4fcdac","resolution":{"observed_at":"2026-08-14T14:42:15.771793Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:15.751692Z","title":"On the complexity of multiple sequence alignment","venue":null,"work_id":"72cac2eb-19bc-40bc-9369-5eb14b9f6053","year":1994},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.214236Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:ba3c3ff873710540c86f0a3c31298667ffef7054bd02014775efc75c47b1d179","observation_id":"b26a789c-4088-4728-bfff-7bf99a5b551a","resolution":{"observed_at":"2026-08-14T14:42:15.756405Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:42:15.736066Z","title":"Some biological sequence metrics","venue":null,"work_id":"0db55750-ffff-4b81-a647-d6a8f64f015f","year":1976},"citing_paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design","version":4},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-14T14:42:15.218877Z"},"links":{"citing_paper":"/paper/1908.02894"},"observation_digest":"sha256:5bf9001beae6f5abb39268892655c86a7c963842a6dd71228328eff58f0836e8","observation_id":"e5c33913-c3f0-4c5c-ac9e-f9073e70bc17","resolution":{"observed_at":"2026-08-14T14:42:15.740913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1908.02894","last_updated":"2021-04-25T22:01:32Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T10:28:58.923632Z","submitted_at":"2019-08-08T01:08:08Z","title":"How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":1,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":42,"verified_exact":4,"verified_fuzzy":52},"total_outbound_references":115},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 100 of 115 outbound references and 1 inbound Pith citation observation for arXiv:1908.02894."}