{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WZYG6SN7B2PXRJGQN47FJCDKJX","short_pith_number":"pith:WZYG6SN7","schema_version":"1.0","canonical_sha256":"b6706f49bf0e9f78a4d06f3e54886a4dfa7f2cd218aaab53c42f3c8b5759f466","source":{"kind":"arxiv","id":"2408.04736","version":1},"attestation_state":"computed","paper":{"title":"Towards Using Multiple Iterated, Reproduced, and Replicated Experiments with Robots (MIRRER) for Evaluation and Benchmarking","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Adam Norton, Brian Flynn (New England Robotics Validation, Experimentation (NERVE) Center, University of Massachusetts Lowell)","submitted_at":"2024-08-08T19:33:23Z","abstract_excerpt":"The robotics research field lacks formalized definitions and frameworks for evaluating advanced capabilities including generalizability (the ability for robots to perform tasks under varied contexts) and reproducibility (the performance of a reproduced robot capability in different labs under the same experimental conditions). This paper presents an initial conceptual framework, MIRRER, that unites the concepts of performance evaluation, benchmarking, and reproduced/replicated experimentation in order to facilitate comparable robotics research. Several open issues with the application of the f"},"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":"2408.04736","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2024-08-08T19:33:23Z","cross_cats_sorted":[],"title_canon_sha256":"e2ec9bd0bc0283a003d5ce336860923a03fd18ccea15c91be967051cb18f09c5","abstract_canon_sha256":"e05e05bd49c0265e2974d576a34cdef4d1e13550618fffccb81cfd0bda11c2ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:42.873542Z","signature_b64":"usZL/yUKfLv2+Pwioio1hILml7e9K4E5PDU3W76ZvNj2Z0mc4pgRsr0Y8qmP6QTamjKZufKcLsb3/EPWekpaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6706f49bf0e9f78a4d06f3e54886a4dfa7f2cd218aaab53c42f3c8b5759f466","last_reissued_at":"2026-07-05T08:53:42.873081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:42.873081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Using Multiple Iterated, Reproduced, and Replicated Experiments with Robots (MIRRER) for Evaluation and Benchmarking","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Adam Norton, Brian Flynn (New England Robotics Validation, Experimentation (NERVE) Center, University of Massachusetts Lowell)","submitted_at":"2024-08-08T19:33:23Z","abstract_excerpt":"The robotics research field lacks formalized definitions and frameworks for evaluating advanced capabilities including generalizability (the ability for robots to perform tasks under varied contexts) and reproducibility (the performance of a reproduced robot capability in different labs under the same experimental conditions). This paper presents an initial conceptual framework, MIRRER, that unites the concepts of performance evaluation, benchmarking, and reproduced/replicated experimentation in order to facilitate comparable robotics research. Several open issues with the application of the f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04736","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/2408.04736/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":"2408.04736","created_at":"2026-07-05T08:53:42.873136+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.04736v1","created_at":"2026-07-05T08:53:42.873136+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04736","created_at":"2026-07-05T08:53:42.873136+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZYG6SN7B2PX","created_at":"2026-07-05T08:53:42.873136+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZYG6SN7B2PXRJGQ","created_at":"2026-07-05T08:53:42.873136+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZYG6SN7","created_at":"2026-07-05T08:53:42.873136+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/WZYG6SN7B2PXRJGQN47FJCDKJX","json":"https://pith.science/pith/WZYG6SN7B2PXRJGQN47FJCDKJX.json","graph_json":"https://pith.science/api/pith-number/WZYG6SN7B2PXRJGQN47FJCDKJX/graph.json","events_json":"https://pith.science/api/pith-number/WZYG6SN7B2PXRJGQN47FJCDKJX/events.json","paper":"https://pith.science/paper/WZYG6SN7"},"agent_actions":{"view_html":"https://pith.science/pith/WZYG6SN7B2PXRJGQN47FJCDKJX","download_json":"https://pith.science/pith/WZYG6SN7B2PXRJGQN47FJCDKJX.json","view_paper":"https://pith.science/paper/WZYG6SN7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.04736&json=true","fetch_graph":"https://pith.science/api/pith-number/WZYG6SN7B2PXRJGQN47FJCDKJX/graph.json","fetch_events":"https://pith.science/api/pith-number/WZYG6SN7B2PXRJGQN47FJCDKJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZYG6SN7B2PXRJGQN47FJCDKJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZYG6SN7B2PXRJGQN47FJCDKJX/action/storage_attestation","attest_author":"https://pith.science/pith/WZYG6SN7B2PXRJGQN47FJCDKJX/action/author_attestation","sign_citation":"https://pith.science/pith/WZYG6SN7B2PXRJGQN47FJCDKJX/action/citation_signature","submit_replication":"https://pith.science/pith/WZYG6SN7B2PXRJGQN47FJCDKJX/action/replication_record"}},"created_at":"2026-07-05T08:53:42.873136+00:00","updated_at":"2026-07-05T08:53:42.873136+00:00"}