{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IG54WQMXVLQTSSSLDU6K5NPB2G","short_pith_number":"pith:IG54WQMX","schema_version":"1.0","canonical_sha256":"41bbcb4197aae1394a4b1d3caeb5e1d189a627358407a02ade41a747745f74fe","source":{"kind":"arxiv","id":"2604.04690","version":2},"attestation_state":"computed","paper":{"title":"Pickalo: Leveraging 6D Pose Estimation for Low-Cost Industrial Bin Picking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Pickalo shows that a low-cost RGB-D pipeline with 6D pose estimation from synthetic data can reach 600 mean picks per hour and 96-99% grasp success in dense industrial bins.","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Alessandro Tarsi, Matteo Mastrogiuseppe, Saverio Taliani, Simone Cortinovis, Ugo Pattacini","submitted_at":"2026-04-06T13:56:57Z","abstract_excerpt":"Bin picking in real industrial environments remains challenging due to severe clutter, occlusions, and the high cost of traditional 3D sensing setups. We present Pickalo, a modular 6D pose-based bin-picking pipeline built entirely on low-cost hardware. A wrist-mounted RGB-D camera actively explores the scene from multiple viewpoints, while raw stereo streams are processed with BridgeDepth to obtain refined depth maps suitable for accurate collision reasoning. Object instances are segmented with a Mask-RCNN model trained purely on photorealistic synthetic data and localized using the zero-shot "},"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":true},"canonical_record":{"source":{"id":"2604.04690","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-06T13:56:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"57b1948998a1f1428e7da2ec6484466fdac285a1a1cc30958cce723d2d884409","abstract_canon_sha256":"c6f6defbfb7a65c437e66485b10b4933cb28f59783b4477debb0fff50ca8d83e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:20:58.334401Z","signature_b64":"+gymRSg1FqOvKsHDvkWoT9Zz1Pyz4vPi5hVdJlDt6DgG7yOorG8C1NitgjI0gl1G//fcd2doGXD8vavvPNX1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41bbcb4197aae1394a4b1d3caeb5e1d189a627358407a02ade41a747745f74fe","last_reissued_at":"2026-07-14T01:20:58.333415Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:20:58.333415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pickalo: Leveraging 6D Pose Estimation for Low-Cost Industrial Bin Picking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Pickalo shows that a low-cost RGB-D pipeline with 6D pose estimation from synthetic data can reach 600 mean picks per hour and 96-99% grasp success in dense industrial bins.","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Alessandro Tarsi, Matteo Mastrogiuseppe, Saverio Taliani, Simone Cortinovis, Ugo Pattacini","submitted_at":"2026-04-06T13:56:57Z","abstract_excerpt":"Bin picking in real industrial environments remains challenging due to severe clutter, occlusions, and the high cost of traditional 3D sensing setups. We present Pickalo, a modular 6D pose-based bin-picking pipeline built entirely on low-cost hardware. A wrist-mounted RGB-D camera actively explores the scene from multiple viewpoints, while raw stereo streams are processed with BridgeDepth to obtain refined depth maps suitable for accurate collision reasoning. Object instances are segmented with a Mask-RCNN model trained purely on photorealistic synthetic data and localized using the zero-shot "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Deployed on a UR5e with a parallel-jaw gripper and an Intel RealSense D435i, Pickalo achieves up to 600 mean picks per hour with 96-99% grasp success and robust performance over 30-minute runs on densely filled euroboxes.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the Mask-RCNN model trained purely on photorealistic synthetic data combined with the zero-shot SAM-6D estimator will produce sufficiently accurate 6D poses in real cluttered, occluded industrial scenes without additional real-world fine-tuning or domain adaptation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Pickalo delivers up to 600 picks per hour at 96-99% success using only low-cost RGB-D hardware, synthetic-trained Mask-RCNN, and SAM-6D pose estimation on a UR5e robot in dense eurobox scenes.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Pickalo shows that a low-cost RGB-D pipeline with 6D pose estimation from synthetic data can reach 600 mean picks per hour and 96-99% grasp success in dense industrial bins.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"940a1acdcad114930c13ece3d1e3d5194ca6e29f487a3057381ba27099d10f66"},"source":{"id":"2604.04690","kind":"arxiv","version":2},"verdict":{"id":"436d8ded-74bc-459a-a3e4-111253467cb0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T19:19:46.145365Z","strongest_claim":"Deployed on a UR5e with a parallel-jaw gripper and an Intel RealSense D435i, Pickalo achieves up to 600 mean picks per hour with 96-99% grasp success and robust performance over 30-minute runs on densely filled euroboxes.","one_line_summary":"Pickalo delivers up to 600 picks per hour at 96-99% success using only low-cost RGB-D hardware, synthetic-trained Mask-RCNN, and SAM-6D pose estimation on a UR5e robot in dense eurobox scenes.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the Mask-RCNN model trained purely on photorealistic synthetic data combined with the zero-shot SAM-6D estimator will produce sufficiently accurate 6D poses in real cluttered, occluded industrial scenes without additional real-world fine-tuning or domain adaptation.","pith_extraction_headline":"Pickalo shows that a low-cost RGB-D pipeline with 6D pose estimation from synthetic data can reach 600 mean picks per hour and 96-99% grasp success in dense industrial bins."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.04690/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":1,"snapshot_sha256":"c276baf688a1e497a710a420bc38b6cded535f6584673ae49257119fea7a2e35"},"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":"2604.04690","created_at":"2026-07-14T01:20:58.333872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.04690v2","created_at":"2026-07-14T01:20:58.333872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.04690","created_at":"2026-07-14T01:20:58.333872+00:00"},{"alias_kind":"pith_short_12","alias_value":"IG54WQMXVLQT","created_at":"2026-07-14T01:20:58.333872+00:00"},{"alias_kind":"pith_short_16","alias_value":"IG54WQMXVLQTSSSL","created_at":"2026-07-14T01:20:58.333872+00:00"},{"alias_kind":"pith_short_8","alias_value":"IG54WQMX","created_at":"2026-07-14T01:20:58.333872+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IG54WQMXVLQTSSSLDU6K5NPB2G","json":"https://pith.science/pith/IG54WQMXVLQTSSSLDU6K5NPB2G.json","graph_json":"https://pith.science/api/pith-number/IG54WQMXVLQTSSSLDU6K5NPB2G/graph.json","events_json":"https://pith.science/api/pith-number/IG54WQMXVLQTSSSLDU6K5NPB2G/events.json","paper":"https://pith.science/paper/IG54WQMX"},"agent_actions":{"view_html":"https://pith.science/pith/IG54WQMXVLQTSSSLDU6K5NPB2G","download_json":"https://pith.science/pith/IG54WQMXVLQTSSSLDU6K5NPB2G.json","view_paper":"https://pith.science/paper/IG54WQMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.04690&json=true","fetch_graph":"https://pith.science/api/pith-number/IG54WQMXVLQTSSSLDU6K5NPB2G/graph.json","fetch_events":"https://pith.science/api/pith-number/IG54WQMXVLQTSSSLDU6K5NPB2G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IG54WQMXVLQTSSSLDU6K5NPB2G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IG54WQMXVLQTSSSLDU6K5NPB2G/action/storage_attestation","attest_author":"https://pith.science/pith/IG54WQMXVLQTSSSLDU6K5NPB2G/action/author_attestation","sign_citation":"https://pith.science/pith/IG54WQMXVLQTSSSLDU6K5NPB2G/action/citation_signature","submit_replication":"https://pith.science/pith/IG54WQMXVLQTSSSLDU6K5NPB2G/action/replication_record"}},"created_at":"2026-07-14T01:20:58.333872+00:00","updated_at":"2026-07-14T01:20:58.333872+00:00"}