{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AORWD4HZU7EOZUP5OET32TP5KM","short_pith_number":"pith:AORWD4HZ","schema_version":"1.0","canonical_sha256":"03a361f0f9a7c8ecd1fd7127bd4dfd53372ceffb0dedfa11e8656b2252c53ce2","source":{"kind":"arxiv","id":"2606.12499","version":1},"attestation_state":"computed","paper":{"title":"Action-Effect Memory Pretraining for Robot Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Boyang Cai, Jiaxi Li, Qiwei Liang, Renjing Xu, Sitong Zhuang, Xianpeng Wang, Yijing Zhou, Yunyang Mo","submitted_at":"2026-06-10T13:58:14Z","abstract_excerpt":"We present AEM, an Action-Effect Memory pretraining framework for robot manipulation that learns compact temporal representations from vision-action history. Unlike prior robot representation pretraining methods that mainly focus on single-frame visual encoding, AEM targets the temporal nature of manipulation, where the current observation alone is often insufficient under partial observability. AEM models manipulation as an action-driven interaction process by interleaving visual and action features and applying masked modeling to recover missing content from incomplete histories, thereby lea"},"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":"2606.12499","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-10T13:58:14Z","cross_cats_sorted":[],"title_canon_sha256":"bbf91d22400000df1bb89659f896e8b47ac0ef8b95d07addd5e96e4b5d686ffb","abstract_canon_sha256":"43d0e35c907a868c67f0000e7f22f7c4b4a43145cc4435746d7eee46421ae92a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T00:07:52.533253Z","signature_b64":"7WWdzT9wJ288VziO4Ttiyzrx9L3eh3rvQ+lLKzRGHynyqksN0xpBc9BqpvrvGi8VLYM/lZNio/gfqhP0et55DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03a361f0f9a7c8ecd1fd7127bd4dfd53372ceffb0dedfa11e8656b2252c53ce2","last_reissued_at":"2026-06-12T00:07:52.532722Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T00:07:52.532722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Action-Effect Memory Pretraining for Robot Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Boyang Cai, Jiaxi Li, Qiwei Liang, Renjing Xu, Sitong Zhuang, Xianpeng Wang, Yijing Zhou, Yunyang Mo","submitted_at":"2026-06-10T13:58:14Z","abstract_excerpt":"We present AEM, an Action-Effect Memory pretraining framework for robot manipulation that learns compact temporal representations from vision-action history. Unlike prior robot representation pretraining methods that mainly focus on single-frame visual encoding, AEM targets the temporal nature of manipulation, where the current observation alone is often insufficient under partial observability. AEM models manipulation as an action-driven interaction process by interleaving visual and action features and applying masked modeling to recover missing content from incomplete histories, thereby lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12499","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/2606.12499/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":"2606.12499","created_at":"2026-06-12T00:07:52.532810+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12499v1","created_at":"2026-06-12T00:07:52.532810+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12499","created_at":"2026-06-12T00:07:52.532810+00:00"},{"alias_kind":"pith_short_12","alias_value":"AORWD4HZU7EO","created_at":"2026-06-12T00:07:52.532810+00:00"},{"alias_kind":"pith_short_16","alias_value":"AORWD4HZU7EOZUP5","created_at":"2026-06-12T00:07:52.532810+00:00"},{"alias_kind":"pith_short_8","alias_value":"AORWD4HZ","created_at":"2026-06-12T00:07:52.532810+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/AORWD4HZU7EOZUP5OET32TP5KM","json":"https://pith.science/pith/AORWD4HZU7EOZUP5OET32TP5KM.json","graph_json":"https://pith.science/api/pith-number/AORWD4HZU7EOZUP5OET32TP5KM/graph.json","events_json":"https://pith.science/api/pith-number/AORWD4HZU7EOZUP5OET32TP5KM/events.json","paper":"https://pith.science/paper/AORWD4HZ"},"agent_actions":{"view_html":"https://pith.science/pith/AORWD4HZU7EOZUP5OET32TP5KM","download_json":"https://pith.science/pith/AORWD4HZU7EOZUP5OET32TP5KM.json","view_paper":"https://pith.science/paper/AORWD4HZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12499&json=true","fetch_graph":"https://pith.science/api/pith-number/AORWD4HZU7EOZUP5OET32TP5KM/graph.json","fetch_events":"https://pith.science/api/pith-number/AORWD4HZU7EOZUP5OET32TP5KM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AORWD4HZU7EOZUP5OET32TP5KM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AORWD4HZU7EOZUP5OET32TP5KM/action/storage_attestation","attest_author":"https://pith.science/pith/AORWD4HZU7EOZUP5OET32TP5KM/action/author_attestation","sign_citation":"https://pith.science/pith/AORWD4HZU7EOZUP5OET32TP5KM/action/citation_signature","submit_replication":"https://pith.science/pith/AORWD4HZU7EOZUP5OET32TP5KM/action/replication_record"}},"created_at":"2026-06-12T00:07:52.532810+00:00","updated_at":"2026-06-12T00:07:52.532810+00:00"}