{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AY5XT6KTKQWA3GSPZTQSOBQENK","short_pith_number":"pith:AY5XT6KT","schema_version":"1.0","canonical_sha256":"063b79f953542c0d9a4fcce12706046aa08868f66907d6a63558611721d48c94","source":{"kind":"arxiv","id":"2504.06468","version":1},"attestation_state":"computed","paper":{"title":"Agent-Arena: A General Framework for Evaluating Control Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.RO","authors_text":"Halid Abdulrahim Kadi, Kasim Terzi\\'c","submitted_at":"2025-04-08T22:20:50Z","abstract_excerpt":"Robotic research is inherently challenging, requiring expertise in diverse environments and control algorithms. Adapting algorithms to new environments often poses significant difficulties, compounded by the need for extensive hyper-parameter tuning in data-driven methods. To address these challenges, we present Agent-Arena, a Python framework designed to streamline the integration, replication, development, and testing of decision-making policies across a wide range of benchmark environments. Unlike existing frameworks, Agent-Arena is uniquely generalised to support all types of control algor"},"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":"2504.06468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-04-08T22:20:50Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"1ec766162a3ddf43f34ff5cffaec5dc29a36e7e0ec97968a6f6e145cd16a91f1","abstract_canon_sha256":"45d5acafa829901d7e5ba20b3ec250f0736d8c5d0f9c2a3f6d4b04e35e0534b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:27.467360Z","signature_b64":"NMROHZCC+Jlznq2t183Nb5o8jzx5n8gCnHBlAXT/3TKMZJCqAqmElBc+VucqFgamPvTwhkweD+4Jto0BgYEEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"063b79f953542c0d9a4fcce12706046aa08868f66907d6a63558611721d48c94","last_reissued_at":"2026-07-05T10:46:27.466876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:27.466876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agent-Arena: A General Framework for Evaluating Control Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.RO","authors_text":"Halid Abdulrahim Kadi, Kasim Terzi\\'c","submitted_at":"2025-04-08T22:20:50Z","abstract_excerpt":"Robotic research is inherently challenging, requiring expertise in diverse environments and control algorithms. Adapting algorithms to new environments often poses significant difficulties, compounded by the need for extensive hyper-parameter tuning in data-driven methods. To address these challenges, we present Agent-Arena, a Python framework designed to streamline the integration, replication, development, and testing of decision-making policies across a wide range of benchmark environments. Unlike existing frameworks, Agent-Arena is uniquely generalised to support all types of control algor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.06468","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/2504.06468/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":"2504.06468","created_at":"2026-07-05T10:46:27.466931+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.06468v1","created_at":"2026-07-05T10:46:27.466931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.06468","created_at":"2026-07-05T10:46:27.466931+00:00"},{"alias_kind":"pith_short_12","alias_value":"AY5XT6KTKQWA","created_at":"2026-07-05T10:46:27.466931+00:00"},{"alias_kind":"pith_short_16","alias_value":"AY5XT6KTKQWA3GSP","created_at":"2026-07-05T10:46:27.466931+00:00"},{"alias_kind":"pith_short_8","alias_value":"AY5XT6KT","created_at":"2026-07-05T10:46:27.466931+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29341","citing_title":"WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AY5XT6KTKQWA3GSPZTQSOBQENK","json":"https://pith.science/pith/AY5XT6KTKQWA3GSPZTQSOBQENK.json","graph_json":"https://pith.science/api/pith-number/AY5XT6KTKQWA3GSPZTQSOBQENK/graph.json","events_json":"https://pith.science/api/pith-number/AY5XT6KTKQWA3GSPZTQSOBQENK/events.json","paper":"https://pith.science/paper/AY5XT6KT"},"agent_actions":{"view_html":"https://pith.science/pith/AY5XT6KTKQWA3GSPZTQSOBQENK","download_json":"https://pith.science/pith/AY5XT6KTKQWA3GSPZTQSOBQENK.json","view_paper":"https://pith.science/paper/AY5XT6KT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.06468&json=true","fetch_graph":"https://pith.science/api/pith-number/AY5XT6KTKQWA3GSPZTQSOBQENK/graph.json","fetch_events":"https://pith.science/api/pith-number/AY5XT6KTKQWA3GSPZTQSOBQENK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AY5XT6KTKQWA3GSPZTQSOBQENK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AY5XT6KTKQWA3GSPZTQSOBQENK/action/storage_attestation","attest_author":"https://pith.science/pith/AY5XT6KTKQWA3GSPZTQSOBQENK/action/author_attestation","sign_citation":"https://pith.science/pith/AY5XT6KTKQWA3GSPZTQSOBQENK/action/citation_signature","submit_replication":"https://pith.science/pith/AY5XT6KTKQWA3GSPZTQSOBQENK/action/replication_record"}},"created_at":"2026-07-05T10:46:27.466931+00:00","updated_at":"2026-07-05T10:46:27.466931+00:00"}