{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6YKIA2WYKBIN3MW5K2LPZUNZ7X","short_pith_number":"pith:6YKIA2WY","schema_version":"1.0","canonical_sha256":"f614806ad85050ddb2dd5696fcd1b9fdc4a2d6d34c48e16f2686959695ea9fc2","source":{"kind":"arxiv","id":"2602.21013","version":2},"attestation_state":"computed","paper":{"title":"Notes-to-Self: Scratchpad Augmented VLAs for Memory Dependent Manipulation Tasks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Apratim Bhattacharyya, Daniel Dijkman, Roland Memisevic, Sanjay Haresh","submitted_at":"2026-02-24T15:30:55Z","abstract_excerpt":"Many dexterous manipulation tasks are non-markovian in nature, yet little attention has been paid to this fact in the recent upsurge of the vision-language-action (VLA) paradigm. Although they are successful in bringing internet-scale semantic understanding to robotics, existing VLAs are primarily \"stateless\" and struggle with memory-dependent long horizon tasks. In this work, we explore a way to impart both spatial and temporal memory to a VLA by incorporating a language scratchpad. The scratchpad makes it possible to memorize task-specific information, such as object positions, and it allows"},"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":"2602.21013","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-24T15:30:55Z","cross_cats_sorted":[],"title_canon_sha256":"3e34db63656fb48c96058054a9a715b753e93d9da4a0a35c7a3c27c98b204826","abstract_canon_sha256":"d745e30478b9ddf0c771ca864edb6a1318718e86219709b24883ee26e0229472"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:03:35.736262Z","signature_b64":"hZn2IGkzlykqeRpVQgHJH3vNqF9oQHTMGqfW22uryJJ9TdU7AmskxudIpanKYib/vBtm64lVxAmG9iiq2g9bAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f614806ad85050ddb2dd5696fcd1b9fdc4a2d6d34c48e16f2686959695ea9fc2","last_reissued_at":"2026-06-01T02:03:35.735066Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:03:35.735066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Notes-to-Self: Scratchpad Augmented VLAs for Memory Dependent Manipulation Tasks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Apratim Bhattacharyya, Daniel Dijkman, Roland Memisevic, Sanjay Haresh","submitted_at":"2026-02-24T15:30:55Z","abstract_excerpt":"Many dexterous manipulation tasks are non-markovian in nature, yet little attention has been paid to this fact in the recent upsurge of the vision-language-action (VLA) paradigm. Although they are successful in bringing internet-scale semantic understanding to robotics, existing VLAs are primarily \"stateless\" and struggle with memory-dependent long horizon tasks. In this work, we explore a way to impart both spatial and temporal memory to a VLA by incorporating a language scratchpad. The scratchpad makes it possible to memorize task-specific information, such as object positions, and it allows"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.21013","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/2602.21013/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":"2602.21013","created_at":"2026-06-01T02:03:35.735234+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.21013v2","created_at":"2026-06-01T02:03:35.735234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.21013","created_at":"2026-06-01T02:03:35.735234+00:00"},{"alias_kind":"pith_short_12","alias_value":"6YKIA2WYKBIN","created_at":"2026-06-01T02:03:35.735234+00:00"},{"alias_kind":"pith_short_16","alias_value":"6YKIA2WYKBIN3MW5","created_at":"2026-06-01T02:03:35.735234+00:00"},{"alias_kind":"pith_short_8","alias_value":"6YKIA2WY","created_at":"2026-06-01T02:03:35.735234+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/6YKIA2WYKBIN3MW5K2LPZUNZ7X","json":"https://pith.science/pith/6YKIA2WYKBIN3MW5K2LPZUNZ7X.json","graph_json":"https://pith.science/api/pith-number/6YKIA2WYKBIN3MW5K2LPZUNZ7X/graph.json","events_json":"https://pith.science/api/pith-number/6YKIA2WYKBIN3MW5K2LPZUNZ7X/events.json","paper":"https://pith.science/paper/6YKIA2WY"},"agent_actions":{"view_html":"https://pith.science/pith/6YKIA2WYKBIN3MW5K2LPZUNZ7X","download_json":"https://pith.science/pith/6YKIA2WYKBIN3MW5K2LPZUNZ7X.json","view_paper":"https://pith.science/paper/6YKIA2WY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.21013&json=true","fetch_graph":"https://pith.science/api/pith-number/6YKIA2WYKBIN3MW5K2LPZUNZ7X/graph.json","fetch_events":"https://pith.science/api/pith-number/6YKIA2WYKBIN3MW5K2LPZUNZ7X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6YKIA2WYKBIN3MW5K2LPZUNZ7X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6YKIA2WYKBIN3MW5K2LPZUNZ7X/action/storage_attestation","attest_author":"https://pith.science/pith/6YKIA2WYKBIN3MW5K2LPZUNZ7X/action/author_attestation","sign_citation":"https://pith.science/pith/6YKIA2WYKBIN3MW5K2LPZUNZ7X/action/citation_signature","submit_replication":"https://pith.science/pith/6YKIA2WYKBIN3MW5K2LPZUNZ7X/action/replication_record"}},"created_at":"2026-06-01T02:03:35.735234+00:00","updated_at":"2026-06-01T02:03:35.735234+00:00"}