{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZWK3CM34JIH2AI7I53AZJQSWBU","short_pith_number":"pith:ZWK3CM34","schema_version":"1.0","canonical_sha256":"cd95b1337c4a0fa023e8eec194c2560d3f2490c0b7590008c38b169eebaa02c0","source":{"kind":"arxiv","id":"2606.20679","version":1},"attestation_state":"computed","paper":{"title":"MemoryVAM: Integrating Memory into Video Action Model for Robot Manipulation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Chang Yu, Chenfanfu Jiang, Nishank Gite, Xiang Feng, Yin Yang, Yunuo Chen, Yuxin Jiang","submitted_at":"2026-06-13T08:54:52Z","abstract_excerpt":"Video-world-model policies learn action-relevant representations by predicting future observations. However, they condition on only a short observation window, which renders long-horizon manipulation non-Markovian when the correct action depends on earlier events that are no longer visible. We present MemoryVAM, an episodic memory mechanism for video-world-model policies. We employ a Recap-Cue (RC) module, in which a Perceiver-based Recap Compressor maps per-frame CLIP embeddings into compact memory tokens, and a lightweight Cue Gate estimates task completion from memory and language. These to"},"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":"2606.20679","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-13T08:54:52Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"4fe3768f684d6e061523ff7df5de348350e55a679f968892934a9505f3489193","abstract_canon_sha256":"35a7aea3065488abb0a874af3d5a9b21333b7ba2acc80a8eaaeb117d55dffd47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T00:11:53.535374Z","signature_b64":"oy+5agheJ5FEDDtMs+ViLeDnnZQXiRbjKQIHdVv3v16REq/d7dBcbyRpKn4atbvDNdcpW+juGw8JbIywxo4BBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd95b1337c4a0fa023e8eec194c2560d3f2490c0b7590008c38b169eebaa02c0","last_reissued_at":"2026-06-23T00:11:53.535012Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T00:11:53.535012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MemoryVAM: Integrating Memory into Video Action Model for Robot Manipulation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Chang Yu, Chenfanfu Jiang, Nishank Gite, Xiang Feng, Yin Yang, Yunuo Chen, Yuxin Jiang","submitted_at":"2026-06-13T08:54:52Z","abstract_excerpt":"Video-world-model policies learn action-relevant representations by predicting future observations. However, they condition on only a short observation window, which renders long-horizon manipulation non-Markovian when the correct action depends on earlier events that are no longer visible. We present MemoryVAM, an episodic memory mechanism for video-world-model policies. We employ a Recap-Cue (RC) module, in which a Perceiver-based Recap Compressor maps per-frame CLIP embeddings into compact memory tokens, and a lightweight Cue Gate estimates task completion from memory and language. These to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20679","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/2606.20679/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":"2606.20679","created_at":"2026-06-23T00:11:53.535073+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20679v1","created_at":"2026-06-23T00:11:53.535073+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20679","created_at":"2026-06-23T00:11:53.535073+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWK3CM34JIH2","created_at":"2026-06-23T00:11:53.535073+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWK3CM34JIH2AI7I","created_at":"2026-06-23T00:11:53.535073+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWK3CM34","created_at":"2026-06-23T00:11:53.535073+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/ZWK3CM34JIH2AI7I53AZJQSWBU","json":"https://pith.science/pith/ZWK3CM34JIH2AI7I53AZJQSWBU.json","graph_json":"https://pith.science/api/pith-number/ZWK3CM34JIH2AI7I53AZJQSWBU/graph.json","events_json":"https://pith.science/api/pith-number/ZWK3CM34JIH2AI7I53AZJQSWBU/events.json","paper":"https://pith.science/paper/ZWK3CM34"},"agent_actions":{"view_html":"https://pith.science/pith/ZWK3CM34JIH2AI7I53AZJQSWBU","download_json":"https://pith.science/pith/ZWK3CM34JIH2AI7I53AZJQSWBU.json","view_paper":"https://pith.science/paper/ZWK3CM34","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20679&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWK3CM34JIH2AI7I53AZJQSWBU/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWK3CM34JIH2AI7I53AZJQSWBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWK3CM34JIH2AI7I53AZJQSWBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWK3CM34JIH2AI7I53AZJQSWBU/action/storage_attestation","attest_author":"https://pith.science/pith/ZWK3CM34JIH2AI7I53AZJQSWBU/action/author_attestation","sign_citation":"https://pith.science/pith/ZWK3CM34JIH2AI7I53AZJQSWBU/action/citation_signature","submit_replication":"https://pith.science/pith/ZWK3CM34JIH2AI7I53AZJQSWBU/action/replication_record"}},"created_at":"2026-06-23T00:11:53.535073+00:00","updated_at":"2026-06-23T00:11:53.535073+00:00"}