{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:II2TTPUOIAFDDDLQJXYZDALMKG","short_pith_number":"pith:II2TTPUO","schema_version":"1.0","canonical_sha256":"423539be8e400a318d704df191816c51ade997f48e09603f43045a3086122eff","source":{"kind":"arxiv","id":"2608.04765","version":1},"attestation_state":"computed","paper":{"title":"Explicit Language Memory for Long-Horizon Planning in Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Houze Xu, Jizhong Li, Ziyi Ye","submitted_at":"2026-08-05T12:32:15Z","abstract_excerpt":"Vision-language-action (VLA) models provide a unified paradigm for connecting visual perception, language understanding, and robotic control. However, existing VLA models still face major challenges in long-horizon tasks: sparse expert demonstrations constrain cross-task compositional generalization; the non-Markovian nature of long-horizon tasks makes it difficult for policies conditioned only on current observations to maintain temporal consistency; limited closed-loop error correction allows execution errors to accumulate; and end-to-end action fine-tuning may weaken the high-level semantic"},"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":"2608.04765","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-08-05T12:32:15Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"de00fbc5b8626afd2705ee3df709e205513aa33723195ed94500e7b436b377af","abstract_canon_sha256":"f6daa70d2b3de238a0d2f1374241cd9d3bc426f636d7c86cf615c4a36d99fe67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:47:03.706341Z","signature_b64":"pED/DHZQjP1jzCBykdwaFyE0Sfh3bOU4D7ISIs2iCO8XXiVsD39oU5YDPFaFIR5LtGQ8eRpx/ALO//Xw7Q/LCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"423539be8e400a318d704df191816c51ade997f48e09603f43045a3086122eff","last_reissued_at":"2026-08-06T01:47:03.704904Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:47:03.704904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explicit Language Memory for Long-Horizon Planning in Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Houze Xu, Jizhong Li, Ziyi Ye","submitted_at":"2026-08-05T12:32:15Z","abstract_excerpt":"Vision-language-action (VLA) models provide a unified paradigm for connecting visual perception, language understanding, and robotic control. However, existing VLA models still face major challenges in long-horizon tasks: sparse expert demonstrations constrain cross-task compositional generalization; the non-Markovian nature of long-horizon tasks makes it difficult for policies conditioned only on current observations to maintain temporal consistency; limited closed-loop error correction allows execution errors to accumulate; and end-to-end action fine-tuning may weaken the high-level semantic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04765","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/2608.04765/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":"2608.04765","created_at":"2026-08-06T01:47:03.706732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04765v1","created_at":"2026-08-06T01:47:03.706732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04765","created_at":"2026-08-06T01:47:03.706732+00:00"},{"alias_kind":"pith_short_12","alias_value":"II2TTPUOIAFD","created_at":"2026-08-06T01:47:03.706732+00:00"},{"alias_kind":"pith_short_16","alias_value":"II2TTPUOIAFDDDLQ","created_at":"2026-08-06T01:47:03.706732+00:00"},{"alias_kind":"pith_short_8","alias_value":"II2TTPUO","created_at":"2026-08-06T01:47:03.706732+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/II2TTPUOIAFDDDLQJXYZDALMKG","json":"https://pith.science/pith/II2TTPUOIAFDDDLQJXYZDALMKG.json","graph_json":"https://pith.science/api/pith-number/II2TTPUOIAFDDDLQJXYZDALMKG/graph.json","events_json":"https://pith.science/api/pith-number/II2TTPUOIAFDDDLQJXYZDALMKG/events.json","paper":"https://pith.science/paper/II2TTPUO"},"agent_actions":{"view_html":"https://pith.science/pith/II2TTPUOIAFDDDLQJXYZDALMKG","download_json":"https://pith.science/pith/II2TTPUOIAFDDDLQJXYZDALMKG.json","view_paper":"https://pith.science/paper/II2TTPUO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04765&json=true","fetch_graph":"https://pith.science/api/pith-number/II2TTPUOIAFDDDLQJXYZDALMKG/graph.json","fetch_events":"https://pith.science/api/pith-number/II2TTPUOIAFDDDLQJXYZDALMKG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/II2TTPUOIAFDDDLQJXYZDALMKG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/II2TTPUOIAFDDDLQJXYZDALMKG/action/storage_attestation","attest_author":"https://pith.science/pith/II2TTPUOIAFDDDLQJXYZDALMKG/action/author_attestation","sign_citation":"https://pith.science/pith/II2TTPUOIAFDDDLQJXYZDALMKG/action/citation_signature","submit_replication":"https://pith.science/pith/II2TTPUOIAFDDDLQJXYZDALMKG/action/replication_record"}},"created_at":"2026-08-06T01:47:03.706732+00:00","updated_at":"2026-08-06T01:47:03.706732+00:00"}