{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W4XUSKKN2YBGV3IKUXLMZKTSOS","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":"90dd3a865e4e1ea5648bdb68c58977f249a75d525ab80b646e333f395bcc6406","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-20T10:16:18Z","title_canon_sha256":"1198cbfe09c582ee3bed2d312a0c3b1c2c32a9aa8a6c66f4365994af5b5e9970"},"schema_version":"1.0","source":{"id":"2502.14420","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14420","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14420v2","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14420","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"W4XUSKKN2YBG","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"pith_short_16","alias_value":"W4XUSKKN2YBGV3IK","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"pith_short_8","alias_value":"W4XUSKKN","created_at":"2026-07-05T10:17:54Z"}],"graph_snapshots":[{"event_id":"sha256:2a9f9c11cb257e868776c145c8c709f145a3f06fa991528e3b274f6adddc4d7f","target":"graph","created_at":"2026-07-05T10:17:54Z","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/2502.14420/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans possess a unified cognitive ability to perceive, comprehend, and interact with the physical world. Why can't large language models replicate this holistic understanding? Through a systematic analysis of existing training paradigms in vision-language-action models (VLA), we identify two key challenges: spurious forgetting, where robot training overwrites crucial visual-text alignments, and task interference, where competing control and understanding tasks degrade performance when trained jointly. To overcome these limitations, we propose ChatVLA, a novel framework featuring Phased Alignm","authors_text":"Chaomin Shen, Feifei Feng, Junjie Wen, Minjie Zhu, Ning Liu, Ran Cheng, Weibin Meng, Yaxin Peng, Yichen Zhu, Zhiyuan Xu, Zhongyi Zhou","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-20T10:16:18Z","title":"ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14420","kind":"arxiv","version":2},"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":"sha256:38f232663d4fc332f488fb13b4656680bab61968860451f56d634ecfd5df5867","target":"record","created_at":"2026-07-05T10:17:54Z","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":"90dd3a865e4e1ea5648bdb68c58977f249a75d525ab80b646e333f395bcc6406","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-20T10:16:18Z","title_canon_sha256":"1198cbfe09c582ee3bed2d312a0c3b1c2c32a9aa8a6c66f4365994af5b5e9970"},"schema_version":"1.0","source":{"id":"2502.14420","kind":"arxiv","version":2}},"canonical_sha256":"b72f49294dd6026aed0aa5d6ccaa7274ab5a79ba182ec2136ca9c9e5740be861","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b72f49294dd6026aed0aa5d6ccaa7274ab5a79ba182ec2136ca9c9e5740be861","first_computed_at":"2026-07-05T10:17:54.958886Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:54.958886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ljq2l8ct+1XqxDgOK2DKSncR1dv9S8DMmyMVUzD1CabMR554S6QPHWrWGob5/hfM4Y3ViSoMrQxwAmFeLaA6AA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:54.959329Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14420","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38f232663d4fc332f488fb13b4656680bab61968860451f56d634ecfd5df5867","sha256:2a9f9c11cb257e868776c145c8c709f145a3f06fa991528e3b274f6adddc4d7f"],"state_sha256":"260557684bade7c94f20ce1f243f805c0b65fee2b48455159b145a068a9d982c"}