{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MAWHW5A6N4H2C3YNMAZM5FDWFQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2b10c477291d267d5968c2090ed413c1ee1a768d0bfbb31b419ce9f64c7bec31","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-02T17:33:37Z","title_canon_sha256":"35322e9aa1105b8c9245d62a01a624a84440751d043472481c4f6c41240536fa"},"schema_version":"1.0","source":{"id":"2607.02466","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02466","created_at":"2026-07-03T01:17:59Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02466v1","created_at":"2026-07-03T01:17:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02466","created_at":"2026-07-03T01:17:59Z"},{"alias_kind":"pith_short_12","alias_value":"MAWHW5A6N4H2","created_at":"2026-07-03T01:17:59Z"},{"alias_kind":"pith_short_16","alias_value":"MAWHW5A6N4H2C3YN","created_at":"2026-07-03T01:17:59Z"},{"alias_kind":"pith_short_8","alias_value":"MAWHW5A6","created_at":"2026-07-03T01:17:59Z"}],"graph_snapshots":[{"event_id":"sha256:0d3be97a7e0eb03b9d79d72782cd7add2e0e65f2c31580bd44162f5d167d91d2","target":"graph","created_at":"2026-07-03T01:17:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.02466/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models are fundamentally bottlenecked by the scarcity of expert demonstrations -- triplets of observations, instructions, and actions that are costly to collect at scale. We argue that this bottleneck stems from conflating two distinct learning objectives: acquiring physical competence (how to move) and acquiring semantic alignment (what to do). Crucially, only the latter requires language supervision. Building on this Decomposition Hypothesis, we propose Task-Agnostic Pretraining (TAP), a two-stage framework that first learns transferable motor priors from cheap, ","authors_text":"Jingjing Gong, Junhao Shi, Li Ji, Siyin Wang, Xiaopeng Yu, Xipeng Qiu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-02T17:33:37Z","title":"Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02466","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4a7300f4f802bb32a0c7844dda0c38c6f4eed022383fc4fce846e5e96959b378","target":"record","created_at":"2026-07-03T01:17:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2b10c477291d267d5968c2090ed413c1ee1a768d0bfbb31b419ce9f64c7bec31","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-02T17:33:37Z","title_canon_sha256":"35322e9aa1105b8c9245d62a01a624a84440751d043472481c4f6c41240536fa"},"schema_version":"1.0","source":{"id":"2607.02466","kind":"arxiv","version":1}},"canonical_sha256":"602c7b741e6f0fa16f0d6032ce94762c0539df780894edc3b652b5c928a6d569","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"602c7b741e6f0fa16f0d6032ce94762c0539df780894edc3b652b5c928a6d569","first_computed_at":"2026-07-03T01:17:59.921001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:59.921001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TD8/XOuSKJPYlMpYimxAqZTpQzucVM3VTz8hcZNrQPvmwE5Tnyhz/akMO7+60sOsxfvhFDFkSKWg9XNEvfjpCg==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:59.921413Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02466","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a7300f4f802bb32a0c7844dda0c38c6f4eed022383fc4fce846e5e96959b378","sha256:0d3be97a7e0eb03b9d79d72782cd7add2e0e65f2c31580bd44162f5d167d91d2"],"state_sha256":"442804dc5993aa4212d38eb09dcc377b0a828ce5de949c9e032ae1b287b8c18d"}