{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KN7G42GNP2O5YJF5PJFV6MDZLO","short_pith_number":"pith:KN7G42GN","schema_version":"1.0","canonical_sha256":"537e6e68cd7e9ddc24bd7a4b5f30795b9bb53aafbac436bb8e47519f0aae1695","source":{"kind":"arxiv","id":"2508.08113","version":1},"attestation_state":"computed","paper":{"title":"AimBot: A Simple Auxiliary Visual Cue to Enhance Spatial Awareness of Visuomotor Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Amir Zadeh, Chuan Li, Jayjun Lee, Jed Yang, Joyce Chai, Nima Fazeli, Yichi Zhang, Yinpei Dai, Ziqiao Ma","submitted_at":"2025-08-11T15:53:23Z","abstract_excerpt":"In this paper, we propose AimBot, a lightweight visual augmentation technique that provides explicit spatial cues to improve visuomotor policy learning in robotic manipulation. AimBot overlays shooting lines and scope reticles onto multi-view RGB images, offering auxiliary visual guidance that encodes the end-effector's state. The overlays are computed from depth images, camera extrinsics, and the current end-effector pose, explicitly conveying spatial relationships between the gripper and objects in the scene. AimBot incurs minimal computational overhead (less than 1 ms) and requires no chang"},"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":"2508.08113","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-11T15:53:23Z","cross_cats_sorted":[],"title_canon_sha256":"41adbe8f1768695e050d03196d7a276838ff5cbefde52d27211498be15c02d72","abstract_canon_sha256":"0cd967ffe74b009f0bd17b7f7d92368cd992d3f3d1218d68e51854f35c807556"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:08.460164Z","signature_b64":"4lyYI3pet7nTnjsgQMLVBF1REzaSR3sY9/tzfVgMsV+inLOXcFWtwPRSNX1+QJbrOFQP/NvrjmqBmjAO/mVOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"537e6e68cd7e9ddc24bd7a4b5f30795b9bb53aafbac436bb8e47519f0aae1695","last_reissued_at":"2026-07-05T11:52:08.459652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:08.459652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AimBot: A Simple Auxiliary Visual Cue to Enhance Spatial Awareness of Visuomotor Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Amir Zadeh, Chuan Li, Jayjun Lee, Jed Yang, Joyce Chai, Nima Fazeli, Yichi Zhang, Yinpei Dai, Ziqiao Ma","submitted_at":"2025-08-11T15:53:23Z","abstract_excerpt":"In this paper, we propose AimBot, a lightweight visual augmentation technique that provides explicit spatial cues to improve visuomotor policy learning in robotic manipulation. AimBot overlays shooting lines and scope reticles onto multi-view RGB images, offering auxiliary visual guidance that encodes the end-effector's state. The overlays are computed from depth images, camera extrinsics, and the current end-effector pose, explicitly conveying spatial relationships between the gripper and objects in the scene. AimBot incurs minimal computational overhead (less than 1 ms) and requires no chang"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08113","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/2508.08113/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":"2508.08113","created_at":"2026-07-05T11:52:08.459731+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.08113v1","created_at":"2026-07-05T11:52:08.459731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08113","created_at":"2026-07-05T11:52:08.459731+00:00"},{"alias_kind":"pith_short_12","alias_value":"KN7G42GNP2O5","created_at":"2026-07-05T11:52:08.459731+00:00"},{"alias_kind":"pith_short_16","alias_value":"KN7G42GNP2O5YJF5","created_at":"2026-07-05T11:52:08.459731+00:00"},{"alias_kind":"pith_short_8","alias_value":"KN7G42GN","created_at":"2026-07-05T11:52:08.459731+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07101","citing_title":"GeoProp: Grounding Robot State in Vision for Generalist Manipulation","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12369","citing_title":"GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2603.04639","citing_title":"RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12162","citing_title":"X-Imitator: Spatial-Aware Imitation Learning via Bidirectional Action-Pose Interaction","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12369","citing_title":"GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KN7G42GNP2O5YJF5PJFV6MDZLO","json":"https://pith.science/pith/KN7G42GNP2O5YJF5PJFV6MDZLO.json","graph_json":"https://pith.science/api/pith-number/KN7G42GNP2O5YJF5PJFV6MDZLO/graph.json","events_json":"https://pith.science/api/pith-number/KN7G42GNP2O5YJF5PJFV6MDZLO/events.json","paper":"https://pith.science/paper/KN7G42GN"},"agent_actions":{"view_html":"https://pith.science/pith/KN7G42GNP2O5YJF5PJFV6MDZLO","download_json":"https://pith.science/pith/KN7G42GNP2O5YJF5PJFV6MDZLO.json","view_paper":"https://pith.science/paper/KN7G42GN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.08113&json=true","fetch_graph":"https://pith.science/api/pith-number/KN7G42GNP2O5YJF5PJFV6MDZLO/graph.json","fetch_events":"https://pith.science/api/pith-number/KN7G42GNP2O5YJF5PJFV6MDZLO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KN7G42GNP2O5YJF5PJFV6MDZLO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KN7G42GNP2O5YJF5PJFV6MDZLO/action/storage_attestation","attest_author":"https://pith.science/pith/KN7G42GNP2O5YJF5PJFV6MDZLO/action/author_attestation","sign_citation":"https://pith.science/pith/KN7G42GNP2O5YJF5PJFV6MDZLO/action/citation_signature","submit_replication":"https://pith.science/pith/KN7G42GNP2O5YJF5PJFV6MDZLO/action/replication_record"}},"created_at":"2026-07-05T11:52:08.459731+00:00","updated_at":"2026-07-05T11:52:08.459731+00:00"}