{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ACXLWRPL7JTKGBLLW5KOXC6CC3","short_pith_number":"pith:ACXLWRPL","schema_version":"1.0","canonical_sha256":"00aebb45ebfa66a3056bb754eb8bc216f37650b2963545e60a9502272165a69c","source":{"kind":"arxiv","id":"2510.14836","version":3},"attestation_state":"computed","paper":{"title":"QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Dongbin Zhao, Haoran Li, Mingcai Zhou, Yixuan Li, Yuhui Chen, Zhengtao Zhang","submitted_at":"2025-10-16T16:11:18Z","abstract_excerpt":"Spatial perception and reasoning are crucial for Vision-Language-Action (VLA) models to accomplish fine-grained manipulation tasks. However, existing approaches often lack the ability to understand and reason over the essential 3D structures necessary for precise control. To address this limitation, we propose QDepth-VLA, a general framework that augments VLA models with an auxiliary depth prediction task. A dedicated depth expert is designed to predict quantized latent tokens of depth maps obtained from a VQ-VAE encoder, enabling the model to learn depth-aware representations that capture cri"},"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":"2510.14836","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-16T16:11:18Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"73da9489e91798e830d193bfe60d3b05a59c5034376e8f91cc50f45464a3cced","abstract_canon_sha256":"69a3c1aec7ef353604a4972e1dd22d23fc941b38f0c8bd5882e3ffa590b15599"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:09:45.251656Z","signature_b64":"T1wA3tCUhUaOotNxNJRuSJhP2CCKr8Nfy0X/Lvh7HHLEBfeNEt5KIhOChoQ2SmxewzJno/vy3YwpEGGA6n70DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00aebb45ebfa66a3056bb754eb8bc216f37650b2963545e60a9502272165a69c","last_reissued_at":"2026-06-10T01:09:45.250591Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:09:45.250591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Dongbin Zhao, Haoran Li, Mingcai Zhou, Yixuan Li, Yuhui Chen, Zhengtao Zhang","submitted_at":"2025-10-16T16:11:18Z","abstract_excerpt":"Spatial perception and reasoning are crucial for Vision-Language-Action (VLA) models to accomplish fine-grained manipulation tasks. However, existing approaches often lack the ability to understand and reason over the essential 3D structures necessary for precise control. To address this limitation, we propose QDepth-VLA, a general framework that augments VLA models with an auxiliary depth prediction task. A dedicated depth expert is designed to predict quantized latent tokens of depth maps obtained from a VQ-VAE encoder, enabling the model to learn depth-aware representations that capture cri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.14836","kind":"arxiv","version":3},"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/2510.14836/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":"2510.14836","created_at":"2026-06-10T01:09:45.250739+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.14836v3","created_at":"2026-06-10T01:09:45.250739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.14836","created_at":"2026-06-10T01:09:45.250739+00:00"},{"alias_kind":"pith_short_12","alias_value":"ACXLWRPL7JTK","created_at":"2026-06-10T01:09:45.250739+00:00"},{"alias_kind":"pith_short_16","alias_value":"ACXLWRPL7JTKGBLL","created_at":"2026-06-10T01:09:45.250739+00:00"},{"alias_kind":"pith_short_8","alias_value":"ACXLWRPL","created_at":"2026-06-10T01:09:45.250739+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.21862","citing_title":"EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2602.20231","citing_title":"UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Models","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ACXLWRPL7JTKGBLLW5KOXC6CC3","json":"https://pith.science/pith/ACXLWRPL7JTKGBLLW5KOXC6CC3.json","graph_json":"https://pith.science/api/pith-number/ACXLWRPL7JTKGBLLW5KOXC6CC3/graph.json","events_json":"https://pith.science/api/pith-number/ACXLWRPL7JTKGBLLW5KOXC6CC3/events.json","paper":"https://pith.science/paper/ACXLWRPL"},"agent_actions":{"view_html":"https://pith.science/pith/ACXLWRPL7JTKGBLLW5KOXC6CC3","download_json":"https://pith.science/pith/ACXLWRPL7JTKGBLLW5KOXC6CC3.json","view_paper":"https://pith.science/paper/ACXLWRPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.14836&json=true","fetch_graph":"https://pith.science/api/pith-number/ACXLWRPL7JTKGBLLW5KOXC6CC3/graph.json","fetch_events":"https://pith.science/api/pith-number/ACXLWRPL7JTKGBLLW5KOXC6CC3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ACXLWRPL7JTKGBLLW5KOXC6CC3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ACXLWRPL7JTKGBLLW5KOXC6CC3/action/storage_attestation","attest_author":"https://pith.science/pith/ACXLWRPL7JTKGBLLW5KOXC6CC3/action/author_attestation","sign_citation":"https://pith.science/pith/ACXLWRPL7JTKGBLLW5KOXC6CC3/action/citation_signature","submit_replication":"https://pith.science/pith/ACXLWRPL7JTKGBLLW5KOXC6CC3/action/replication_record"}},"created_at":"2026-06-10T01:09:45.250739+00:00","updated_at":"2026-06-10T01:09:45.250739+00:00"}