{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ACXLWRPL7JTKGBLLW5KOXC6CC3","short_pith_number":"pith:ACXLWRPL","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"},"canonical_sha256":"00aebb45ebfa66a3056bb754eb8bc216f37650b2963545e60a9502272165a69c","source":{"kind":"arxiv","id":"2510.14836","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.14836","created_at":"2026-06-10T01:09:45Z"},{"alias_kind":"arxiv_version","alias_value":"2510.14836v3","created_at":"2026-06-10T01:09:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.14836","created_at":"2026-06-10T01:09:45Z"},{"alias_kind":"pith_short_12","alias_value":"ACXLWRPL7JTK","created_at":"2026-06-10T01:09:45Z"},{"alias_kind":"pith_short_16","alias_value":"ACXLWRPL7JTKGBLL","created_at":"2026-06-10T01:09:45Z"},{"alias_kind":"pith_short_8","alias_value":"ACXLWRPL","created_at":"2026-06-10T01:09:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ACXLWRPL7JTKGBLLW5KOXC6CC3","target":"record","payload":{"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"},"canonical_sha256":"00aebb45ebfa66a3056bb754eb8bc216f37650b2963545e60a9502272165a69c","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"},"source_kind":"arxiv","source_id":"2510.14836","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-10T01:09:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yfXyCOj0/64bsyHolK7URxmt8B1a1qwswoG0PD2wZtxNtPij+VKCERyqCZLf7DU75eSHo0F+UPqb+73LUfSBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T10:28:21.053772Z"},"content_sha256":"df187f025d294425dad83945e6b1f585598aef5b79907d8864126c97f07f172e","schema_version":"1.0","event_id":"sha256:df187f025d294425dad83945e6b1f585598aef5b79907d8864126c97f07f172e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ACXLWRPL7JTKGBLLW5KOXC6CC3","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-10T01:09:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oFRv403kIvsG/dTQjZqRgHwE6lQm2rpFu4Mv+tYCehO7zyijJJfXiLR9sRPJYdC6+JBJAly11yDhoDsxK6vlCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T10:28:21.054593Z"},"content_sha256":"3be78c1e94ebbc3d461b48483ef47db5676d675b798a5831cbb5bea88ac37c0e","schema_version":"1.0","event_id":"sha256:3be78c1e94ebbc3d461b48483ef47db5676d675b798a5831cbb5bea88ac37c0e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ACXLWRPL7JTKGBLLW5KOXC6CC3/bundle.json","state_url":"https://pith.science/pith/ACXLWRPL7JTKGBLLW5KOXC6CC3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ACXLWRPL7JTKGBLLW5KOXC6CC3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-10T10:28:21Z","links":{"resolver":"https://pith.science/pith/ACXLWRPL7JTKGBLLW5KOXC6CC3","bundle":"https://pith.science/pith/ACXLWRPL7JTKGBLLW5KOXC6CC3/bundle.json","state":"https://pith.science/pith/ACXLWRPL7JTKGBLLW5KOXC6CC3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ACXLWRPL7JTKGBLLW5KOXC6CC3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ACXLWRPL7JTKGBLLW5KOXC6CC3","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":"69a3c1aec7ef353604a4972e1dd22d23fc941b38f0c8bd5882e3ffa590b15599","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-16T16:11:18Z","title_canon_sha256":"73da9489e91798e830d193bfe60d3b05a59c5034376e8f91cc50f45464a3cced"},"schema_version":"1.0","source":{"id":"2510.14836","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.14836","created_at":"2026-06-10T01:09:45Z"},{"alias_kind":"arxiv_version","alias_value":"2510.14836v3","created_at":"2026-06-10T01:09:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.14836","created_at":"2026-06-10T01:09:45Z"},{"alias_kind":"pith_short_12","alias_value":"ACXLWRPL7JTK","created_at":"2026-06-10T01:09:45Z"},{"alias_kind":"pith_short_16","alias_value":"ACXLWRPL7JTKGBLL","created_at":"2026-06-10T01:09:45Z"},{"alias_kind":"pith_short_8","alias_value":"ACXLWRPL","created_at":"2026-06-10T01:09:45Z"}],"graph_snapshots":[{"event_id":"sha256:3be78c1e94ebbc3d461b48483ef47db5676d675b798a5831cbb5bea88ac37c0e","target":"graph","created_at":"2026-06-10T01:09:45Z","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/2510.14836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dongbin Zhao, Haoran Li, Mingcai Zhou, Yixuan Li, Yuhui Chen, Zhengtao Zhang","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-16T16:11:18Z","title":"QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.14836","kind":"arxiv","version":3},"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:df187f025d294425dad83945e6b1f585598aef5b79907d8864126c97f07f172e","target":"record","created_at":"2026-06-10T01:09:45Z","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":"69a3c1aec7ef353604a4972e1dd22d23fc941b38f0c8bd5882e3ffa590b15599","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-16T16:11:18Z","title_canon_sha256":"73da9489e91798e830d193bfe60d3b05a59c5034376e8f91cc50f45464a3cced"},"schema_version":"1.0","source":{"id":"2510.14836","kind":"arxiv","version":3}},"canonical_sha256":"00aebb45ebfa66a3056bb754eb8bc216f37650b2963545e60a9502272165a69c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00aebb45ebfa66a3056bb754eb8bc216f37650b2963545e60a9502272165a69c","first_computed_at":"2026-06-10T01:09:45.250591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:09:45.250591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T1wA3tCUhUaOotNxNJRuSJhP2CCKr8Nfy0X/Lvh7HHLEBfeNEt5KIhOChoQ2SmxewzJno/vy3YwpEGGA6n70DQ==","signature_status":"signed_v1","signed_at":"2026-06-10T01:09:45.251656Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.14836","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df187f025d294425dad83945e6b1f585598aef5b79907d8864126c97f07f172e","sha256:3be78c1e94ebbc3d461b48483ef47db5676d675b798a5831cbb5bea88ac37c0e"],"state_sha256":"1bf053c8845444eb1a05d6c4ed93d214c9830d7f8e4b051ba27dc552515b0e34"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UYh9RtnRRxZ2GAlz1e4AKjBjzpOWvgl4uONANkDH6S+oWkfKPEEQqGP/LRAno8ppH7JQQlSnfet+3Gg3ChbSAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T10:28:21.059667Z","bundle_sha256":"638beb0e6f307259d8758c11127d37fb5e3f42ae05e79b099ecd81e22fd1fa16"}}