{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:A3IJGP364V3NLALH52N3BIYU2E","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":"ace618e8e29052fda2eff2c0b2c64b9d91674cb26004beeff9409a6b716a4173","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-07T08:57:51Z","title_canon_sha256":"d4c5a26b755afea0011a78032f014bd3f7c3035107692159830ec5054a45dd25"},"schema_version":"1.0","source":{"id":"2606.08520","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08520","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08520v1","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08520","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"A3IJGP364V3N","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"A3IJGP364V3NLALH","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"A3IJGP36","created_at":"2026-06-09T01:05:38Z"}],"graph_snapshots":[{"event_id":"sha256:1ca686ec660e72012fc0ad5f0f6f9e00343aa42f2aaa63d80624e97fd5ac1907","target":"graph","created_at":"2026-06-09T01:05:38Z","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/2606.08520/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) are powerful general-purpose reasoners, yet converting them into robot control policies (VLAs) is surprisingly difficult. The root cause is a two-fold gap: VLMs are trained on internet-scale images with language-understanding objectives, while VLAs must perceive robot scenes and predict motor actions. Fine-tuning a VLM directly on robot action data forces the model to cross both gaps at once -- the learning curve is steep and the rich generalizations learned during pretraining tend to degrade rather than transfer. We argue that this gap can be bridged gradually wi","authors_text":"Chenchen Yang, Chenxin Li, Jingjing Gong, Lei Xiao, Linqi Yin, Pengfang Qian, Shenling Qiu, Shiduo Zhang, Xiang Wang, Xipeng Qiu, Xuanjing Huang, Yu-Gang Jiang, Zhaoyang Fu, Zhe Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-07T08:57:51Z","title":"Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08520","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":"sha256:4551517325076b7f11399a4f5e24dd01fc7ed0ab2d9e31e6cfa2b60dfe43ea6f","target":"record","created_at":"2026-06-09T01:05:38Z","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":"ace618e8e29052fda2eff2c0b2c64b9d91674cb26004beeff9409a6b716a4173","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-07T08:57:51Z","title_canon_sha256":"d4c5a26b755afea0011a78032f014bd3f7c3035107692159830ec5054a45dd25"},"schema_version":"1.0","source":{"id":"2606.08520","kind":"arxiv","version":1}},"canonical_sha256":"06d0933f7ee576d58167ee9bb0a314d10acfce3c43a1a0617ddab39ba3d0ba9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06d0933f7ee576d58167ee9bb0a314d10acfce3c43a1a0617ddab39ba3d0ba9b","first_computed_at":"2026-06-09T01:05:38.934812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:38.934812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HCnOI3DGPo4sg0c3xKIORpc+WlvNwaIm+T7hNPH36k32zwp/IFEhnC2QzFAmqcDZ3FA0YX65RvEWlBHTTzt8Aw==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:38.935248Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08520","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4551517325076b7f11399a4f5e24dd01fc7ed0ab2d9e31e6cfa2b60dfe43ea6f","sha256:1ca686ec660e72012fc0ad5f0f6f9e00343aa42f2aaa63d80624e97fd5ac1907"],"state_sha256":"b86caa4d73ce78bdaa23000fd249c0872eb3618236cb99d10bb7502f7f2b7fd6"}