{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AAJ5LLTZBPTBNTJDWNPOQDPM3M","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":"950860d3567ac25c9b87688990b554819feb133cdc294861fb939ad94ec6f609","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-15T04:13:54Z","title_canon_sha256":"f46f36d48be6c255094abbd306bc1b5602e1e8952e92c590fee9358e31fde849"},"schema_version":"1.0","source":{"id":"2607.13429","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.13429","created_at":"2026-07-16T00:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"2607.13429v1","created_at":"2026-07-16T00:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13429","created_at":"2026-07-16T00:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"AAJ5LLTZBPTB","created_at":"2026-07-16T00:22:17Z"},{"alias_kind":"pith_short_16","alias_value":"AAJ5LLTZBPTBNTJD","created_at":"2026-07-16T00:22:17Z"},{"alias_kind":"pith_short_8","alias_value":"AAJ5LLTZ","created_at":"2026-07-16T00:22:17Z"}],"graph_snapshots":[{"event_id":"sha256:1732ccbc753b86abdd9afa6df16fdaf7391433d7edd59c73fb52d6002a6a32f9","target":"graph","created_at":"2026-07-16T00:22:17Z","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/2607.13429/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Finetuning a pretrained vision-language model (VLM) on robot demonstrations via behavior cloning (BC) has become the standard recipe for vision-language-action (VLA) policies. However, BC finetuning progressively overwrites the pretrained representations that support visual and semantic generalization. Co-training on web image-text data, a common remedy, does not prevent this; it applies language and action losses to separate observations, leaving VLAs with language-action misalignment that standard manipulation benchmarks do not expose. We propose Anchor-Align, which augments BC with two obje","authors_text":"Alex Baratian, Chahit Jain, Dwip Dalal, Heng Ji, Hyeonjeong Ha, Jeonghwan Kim, Shivansh Patel, Svetlana Lazebnik, Unnat Jain, Utkarsh Mishra","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-15T04:13:54Z","title":"Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13429","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":"sha256:259a5dfc12452aeb5e8608781d295fdbfb07cb26c38ca2dba231418d1ce5f128","target":"record","created_at":"2026-07-16T00:22:17Z","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":"950860d3567ac25c9b87688990b554819feb133cdc294861fb939ad94ec6f609","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-15T04:13:54Z","title_canon_sha256":"f46f36d48be6c255094abbd306bc1b5602e1e8952e92c590fee9358e31fde849"},"schema_version":"1.0","source":{"id":"2607.13429","kind":"arxiv","version":1}},"canonical_sha256":"0013d5ae790be616cd23b35ee80decdb1a6047d94dc0eb413b6e87e45296668a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0013d5ae790be616cd23b35ee80decdb1a6047d94dc0eb413b6e87e45296668a","first_computed_at":"2026-07-16T00:22:17.795817Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T00:22:17.795817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JTdEwe8zihqVJRd1DIWlcwerkTfMZGFmy2c1sGb6/9h8FHY20IxqsI+4B3rzjOft3PLLabbZTC/8PFhCsEnKBQ==","signature_status":"signed_v1","signed_at":"2026-07-16T00:22:17.796826Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.13429","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:259a5dfc12452aeb5e8608781d295fdbfb07cb26c38ca2dba231418d1ce5f128","sha256:1732ccbc753b86abdd9afa6df16fdaf7391433d7edd59c73fb52d6002a6a32f9"],"state_sha256":"d7bc568a31c57616dcea75cf14146935aa652c745bcd16c40cdc571253efcc4e"}