{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PF2SNA4N6MTWAHIDFI6FDNDGMB","short_pith_number":"pith:PF2SNA4N","schema_version":"1.0","canonical_sha256":"797526838df327601d032a3c51b4666044f5d40c3fb5144d37d445a71e65a731","source":{"kind":"arxiv","id":"2603.04639","version":2},"attestation_state":"computed","paper":{"title":"RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chelsea Finn, Haoran Zhang, Hongze Fu, Jayjun Lee, Jianing Yang, Joyce Chai, Nima Fazeli, Yinpei Dai, Yuejiang Liu","submitted_at":"2026-03-04T21:59:32Z","abstract_excerpt":"Memory is critical for long-horizon and history-dependent robotic manipulation. Such tasks often involve counting repeated actions or manipulating objects that become temporarily occluded. Recent vision-language-action (VLA) models have begun to incorporate memory mechanisms; however, their evaluations remain confined to narrow, non-standardized settings. This limits their systematic understanding, comparison, and progress measurement. To address these challenges, we introduce RoboMME: a large-scale standardized benchmark for evaluating and advancing VLA models in long-horizon, history-depende"},"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":"2603.04639","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-03-04T21:59:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8da493ddd4b7d8234a3b98c163a9782cff0b03e307c24858ecec911624d52b21","abstract_canon_sha256":"8a0781ed9e2d9979ffa69e2ee3d878cbabc93728bed9c50b46e6e79a5c5885ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:27.426533Z","signature_b64":"ywkgVQaqtZ7h6lMTT0vSc3z+NEL6Mz5/2AxO6kkmxyCS3MGxPf7NGz9jrrTycQ4o6No17mbOquBn2SKQMv+BBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"797526838df327601d032a3c51b4666044f5d40c3fb5144d37d445a71e65a731","last_reissued_at":"2026-05-20T00:04:27.425669Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:27.425669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chelsea Finn, Haoran Zhang, Hongze Fu, Jayjun Lee, Jianing Yang, Joyce Chai, Nima Fazeli, Yinpei Dai, Yuejiang Liu","submitted_at":"2026-03-04T21:59:32Z","abstract_excerpt":"Memory is critical for long-horizon and history-dependent robotic manipulation. Such tasks often involve counting repeated actions or manipulating objects that become temporarily occluded. Recent vision-language-action (VLA) models have begun to incorporate memory mechanisms; however, their evaluations remain confined to narrow, non-standardized settings. This limits their systematic understanding, comparison, and progress measurement. To address these challenges, we introduce RoboMME: a large-scale standardized benchmark for evaluating and advancing VLA models in long-horizon, history-depende"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.04639","kind":"arxiv","version":2},"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/2603.04639/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":"2603.04639","created_at":"2026-05-20T00:04:27.425803+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.04639v2","created_at":"2026-05-20T00:04:27.425803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.04639","created_at":"2026-05-20T00:04:27.425803+00:00"},{"alias_kind":"pith_short_12","alias_value":"PF2SNA4N6MTW","created_at":"2026-05-20T00:04:27.425803+00:00"},{"alias_kind":"pith_short_16","alias_value":"PF2SNA4N6MTWAHID","created_at":"2026-05-20T00:04:27.425803+00:00"},{"alias_kind":"pith_short_8","alias_value":"PF2SNA4N","created_at":"2026-05-20T00:04:27.425803+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2603.13966","citing_title":"vla-eval: A Unified Evaluation Harness for Vision-Language-Action Models","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":238,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10921","citing_title":"RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PF2SNA4N6MTWAHIDFI6FDNDGMB","json":"https://pith.science/pith/PF2SNA4N6MTWAHIDFI6FDNDGMB.json","graph_json":"https://pith.science/api/pith-number/PF2SNA4N6MTWAHIDFI6FDNDGMB/graph.json","events_json":"https://pith.science/api/pith-number/PF2SNA4N6MTWAHIDFI6FDNDGMB/events.json","paper":"https://pith.science/paper/PF2SNA4N"},"agent_actions":{"view_html":"https://pith.science/pith/PF2SNA4N6MTWAHIDFI6FDNDGMB","download_json":"https://pith.science/pith/PF2SNA4N6MTWAHIDFI6FDNDGMB.json","view_paper":"https://pith.science/paper/PF2SNA4N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.04639&json=true","fetch_graph":"https://pith.science/api/pith-number/PF2SNA4N6MTWAHIDFI6FDNDGMB/graph.json","fetch_events":"https://pith.science/api/pith-number/PF2SNA4N6MTWAHIDFI6FDNDGMB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PF2SNA4N6MTWAHIDFI6FDNDGMB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PF2SNA4N6MTWAHIDFI6FDNDGMB/action/storage_attestation","attest_author":"https://pith.science/pith/PF2SNA4N6MTWAHIDFI6FDNDGMB/action/author_attestation","sign_citation":"https://pith.science/pith/PF2SNA4N6MTWAHIDFI6FDNDGMB/action/citation_signature","submit_replication":"https://pith.science/pith/PF2SNA4N6MTWAHIDFI6FDNDGMB/action/replication_record"}},"created_at":"2026-05-20T00:04:27.425803+00:00","updated_at":"2026-05-20T00:04:27.425803+00:00"}