{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ES5WRPJU2BRISHQSZOWIKIDOYJ","short_pith_number":"pith:ES5WRPJU","schema_version":"1.0","canonical_sha256":"24bb68bd34d062891e12cbac85206ec25c3ad9004a0c44612bd6d751ebab8b49","source":{"kind":"arxiv","id":"2407.13513","version":1},"attestation_state":"computed","paper":{"title":"Instance Selection for Dynamic Algorithm Configuration with Reinforcement Learning: Improving Generalization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya Mohan, Ana Nikolikj, Carolin Benjamins, Gjorgjina Cenikj, Marius Lindauer, Tome Eftimov","submitted_at":"2024-07-18T13:44:43Z","abstract_excerpt":"Dynamic Algorithm Configuration (DAC) addresses the challenge of dynamically setting hyperparameters of an algorithm for a diverse set of instances rather than focusing solely on individual tasks. Agents trained with Deep Reinforcement Learning (RL) offer a pathway to solve such settings. However, the limited generalization performance of these agents has significantly hindered the application in DAC. Our hypothesis is that a potential bias in the training instances limits generalization capabilities. We take a step towards mitigating this by selecting a representative subset of training insta"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.13513","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-18T13:44:43Z","cross_cats_sorted":[],"title_canon_sha256":"5cc68ba92ea8a74c98e3a2be4412335133b1d70a8dc6eba5713d281c5ff34016","abstract_canon_sha256":"78f1c49f9c9451469d3438f9c9053f47d6b4a563a12f3942746f67dc73cd50ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:40.051886Z","signature_b64":"XCTCJ15WsYsjOvDFcV16N0pCEHJiUYDpigSG6E34BCXTqMDvsihoLEabIfIkRum9bR+SfvJ5d1pP8jzqchprDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24bb68bd34d062891e12cbac85206ec25c3ad9004a0c44612bd6d751ebab8b49","last_reissued_at":"2026-07-05T08:45:40.051398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:40.051398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instance Selection for Dynamic Algorithm Configuration with Reinforcement Learning: Improving Generalization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya Mohan, Ana Nikolikj, Carolin Benjamins, Gjorgjina Cenikj, Marius Lindauer, Tome Eftimov","submitted_at":"2024-07-18T13:44:43Z","abstract_excerpt":"Dynamic Algorithm Configuration (DAC) addresses the challenge of dynamically setting hyperparameters of an algorithm for a diverse set of instances rather than focusing solely on individual tasks. Agents trained with Deep Reinforcement Learning (RL) offer a pathway to solve such settings. However, the limited generalization performance of these agents has significantly hindered the application in DAC. Our hypothesis is that a potential bias in the training instances limits generalization capabilities. We take a step towards mitigating this by selecting a representative subset of training insta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13513","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.13513/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.13513","created_at":"2026-07-05T08:45:40.051451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.13513v1","created_at":"2026-07-05T08:45:40.051451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13513","created_at":"2026-07-05T08:45:40.051451+00:00"},{"alias_kind":"pith_short_12","alias_value":"ES5WRPJU2BRI","created_at":"2026-07-05T08:45:40.051451+00:00"},{"alias_kind":"pith_short_16","alias_value":"ES5WRPJU2BRISHQS","created_at":"2026-07-05T08:45:40.051451+00:00"},{"alias_kind":"pith_short_8","alias_value":"ES5WRPJU","created_at":"2026-07-05T08:45:40.051451+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ES5WRPJU2BRISHQSZOWIKIDOYJ","json":"https://pith.science/pith/ES5WRPJU2BRISHQSZOWIKIDOYJ.json","graph_json":"https://pith.science/api/pith-number/ES5WRPJU2BRISHQSZOWIKIDOYJ/graph.json","events_json":"https://pith.science/api/pith-number/ES5WRPJU2BRISHQSZOWIKIDOYJ/events.json","paper":"https://pith.science/paper/ES5WRPJU"},"agent_actions":{"view_html":"https://pith.science/pith/ES5WRPJU2BRISHQSZOWIKIDOYJ","download_json":"https://pith.science/pith/ES5WRPJU2BRISHQSZOWIKIDOYJ.json","view_paper":"https://pith.science/paper/ES5WRPJU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.13513&json=true","fetch_graph":"https://pith.science/api/pith-number/ES5WRPJU2BRISHQSZOWIKIDOYJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ES5WRPJU2BRISHQSZOWIKIDOYJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ES5WRPJU2BRISHQSZOWIKIDOYJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ES5WRPJU2BRISHQSZOWIKIDOYJ/action/storage_attestation","attest_author":"https://pith.science/pith/ES5WRPJU2BRISHQSZOWIKIDOYJ/action/author_attestation","sign_citation":"https://pith.science/pith/ES5WRPJU2BRISHQSZOWIKIDOYJ/action/citation_signature","submit_replication":"https://pith.science/pith/ES5WRPJU2BRISHQSZOWIKIDOYJ/action/replication_record"}},"created_at":"2026-07-05T08:45:40.051451+00:00","updated_at":"2026-07-05T08:45:40.051451+00:00"}