{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5EJ4AAG5E6H55AWMVXZTLBPUCB","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":"e86efb3c17b8c5c319ba79fb5a1c488a58566626466793612b44f3135e75dc42","cross_cats_sorted":["cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T06:59:39Z","title_canon_sha256":"692a1c6d16329bc9caf6437846ebde790a73fa43ab58e03c1947bc00e6d25772"},"schema_version":"1.0","source":{"id":"2607.14635","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14635","created_at":"2026-07-17T01:21:22Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14635v1","created_at":"2026-07-17T01:21:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14635","created_at":"2026-07-17T01:21:22Z"},{"alias_kind":"pith_short_12","alias_value":"5EJ4AAG5E6H5","created_at":"2026-07-17T01:21:22Z"},{"alias_kind":"pith_short_16","alias_value":"5EJ4AAG5E6H55AWM","created_at":"2026-07-17T01:21:22Z"},{"alias_kind":"pith_short_8","alias_value":"5EJ4AAG5","created_at":"2026-07-17T01:21:22Z"}],"graph_snapshots":[{"event_id":"sha256:c0823f728d0f8bcc92ae21b68d6bb03062daa77074423298a7245a3f08ca28e0","target":"graph","created_at":"2026-07-17T01:21:22Z","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/2607.14635/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Action supervision in vision-language-action (VLA) models is often treated as a downstream objective for learning action prediction. In this paper, we study it instead as a force that shapes inherited multimodal representations. We show that this shaping has a dual effect: it is necessary for forming action-compatible representations, but when action supervision is applied too directly to the inherited multimodal pathway, it can also destabilize representations that support language-side processing and object grounding. To address this tension, we introduce Action QFormer, a query-based action","authors_text":"Haoyi Niu, Koushil Sreenath, Wenhao Tang, Yi Wu, Yufeng Ji, Zhongyu Li","cross_cats":["cs.CV","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T06:59:39Z","title":"Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14635","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:da711ff30ce8cd0c46279f0650cb9f95c80fd897745941d15b27f7eafb4462bb","target":"record","created_at":"2026-07-17T01:21:22Z","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":"e86efb3c17b8c5c319ba79fb5a1c488a58566626466793612b44f3135e75dc42","cross_cats_sorted":["cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T06:59:39Z","title_canon_sha256":"692a1c6d16329bc9caf6437846ebde790a73fa43ab58e03c1947bc00e6d25772"},"schema_version":"1.0","source":{"id":"2607.14635","kind":"arxiv","version":1}},"canonical_sha256":"e913c000dd278fde82ccadf33585f4106e4484f02fe4bec90af617727f9f2de0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e913c000dd278fde82ccadf33585f4106e4484f02fe4bec90af617727f9f2de0","first_computed_at":"2026-07-17T01:21:22.102204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T01:21:22.102204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iAcKCr9YAX1N0CD57xMZby/rdHcUMY4jjPxlFhKgdWMM7CqJCr61QKxUkXDS1GrOxcxas+R/ZKNOp+4DblT0DQ==","signature_status":"signed_v1","signed_at":"2026-07-17T01:21:22.103025Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.14635","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da711ff30ce8cd0c46279f0650cb9f95c80fd897745941d15b27f7eafb4462bb","sha256:c0823f728d0f8bcc92ae21b68d6bb03062daa77074423298a7245a3f08ca28e0"],"state_sha256":"17e7651fd5b507463ec2cfb86aaaf2c7c9324010026e71d2b9880c08d921ca60"}