{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5EJ4AAG5E6H55AWMVXZTLBPUCB","short_pith_number":"pith:5EJ4AAG5","schema_version":"1.0","canonical_sha256":"e913c000dd278fde82ccadf33585f4106e4484f02fe4bec90af617727f9f2de0","source":{"kind":"arxiv","id":"2607.14635","version":1},"attestation_state":"computed","paper":{"title":"Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.AI","authors_text":"Haoyi Niu, Koushil Sreenath, Wenhao Tang, Yi Wu, Yufeng Ji, Zhongyu Li","submitted_at":"2026-07-16T06:59:39Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.14635","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T06:59:39Z","cross_cats_sorted":["cs.CV","cs.RO"],"title_canon_sha256":"692a1c6d16329bc9caf6437846ebde790a73fa43ab58e03c1947bc00e6d25772","abstract_canon_sha256":"e86efb3c17b8c5c319ba79fb5a1c488a58566626466793612b44f3135e75dc42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:21:22.103025Z","signature_b64":"iAcKCr9YAX1N0CD57xMZby/rdHcUMY4jjPxlFhKgdWMM7CqJCr61QKxUkXDS1GrOxcxas+R/ZKNOp+4DblT0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e913c000dd278fde82ccadf33585f4106e4484f02fe4bec90af617727f9f2de0","last_reissued_at":"2026-07-17T01:21:22.102204Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:21:22.102204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.AI","authors_text":"Haoyi Niu, Koushil Sreenath, Wenhao Tang, Yi Wu, Yufeng Ji, Zhongyu Li","submitted_at":"2026-07-16T06:59:39Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14635","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.14635/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.14635","created_at":"2026-07-17T01:21:22.102645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14635v1","created_at":"2026-07-17T01:21:22.102645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14635","created_at":"2026-07-17T01:21:22.102645+00:00"},{"alias_kind":"pith_short_12","alias_value":"5EJ4AAG5E6H5","created_at":"2026-07-17T01:21:22.102645+00:00"},{"alias_kind":"pith_short_16","alias_value":"5EJ4AAG5E6H55AWM","created_at":"2026-07-17T01:21:22.102645+00:00"},{"alias_kind":"pith_short_8","alias_value":"5EJ4AAG5","created_at":"2026-07-17T01:21:22.102645+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5EJ4AAG5E6H55AWMVXZTLBPUCB","json":"https://pith.science/pith/5EJ4AAG5E6H55AWMVXZTLBPUCB.json","graph_json":"https://pith.science/api/pith-number/5EJ4AAG5E6H55AWMVXZTLBPUCB/graph.json","events_json":"https://pith.science/api/pith-number/5EJ4AAG5E6H55AWMVXZTLBPUCB/events.json","paper":"https://pith.science/paper/5EJ4AAG5"},"agent_actions":{"view_html":"https://pith.science/pith/5EJ4AAG5E6H55AWMVXZTLBPUCB","download_json":"https://pith.science/pith/5EJ4AAG5E6H55AWMVXZTLBPUCB.json","view_paper":"https://pith.science/paper/5EJ4AAG5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14635&json=true","fetch_graph":"https://pith.science/api/pith-number/5EJ4AAG5E6H55AWMVXZTLBPUCB/graph.json","fetch_events":"https://pith.science/api/pith-number/5EJ4AAG5E6H55AWMVXZTLBPUCB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5EJ4AAG5E6H55AWMVXZTLBPUCB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5EJ4AAG5E6H55AWMVXZTLBPUCB/action/storage_attestation","attest_author":"https://pith.science/pith/5EJ4AAG5E6H55AWMVXZTLBPUCB/action/author_attestation","sign_citation":"https://pith.science/pith/5EJ4AAG5E6H55AWMVXZTLBPUCB/action/citation_signature","submit_replication":"https://pith.science/pith/5EJ4AAG5E6H55AWMVXZTLBPUCB/action/replication_record"}},"created_at":"2026-07-17T01:21:22.102645+00:00","updated_at":"2026-07-17T01:21:22.102645+00:00"}