{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2RMSC66MC2JXGJFWMBV5Q2QEYA","short_pith_number":"pith:2RMSC66M","schema_version":"1.0","canonical_sha256":"d459217bcc16937324b6606bd86a04c026ee336136e3f49b92734fb0d035ef93","source":{"kind":"arxiv","id":"2605.29505","version":1},"attestation_state":"computed","paper":{"title":"ESAM++: Efficient Online 3D Perception on the Edge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Colaco, Ehsan Adeli, Lavisha Aggarwal, Marc Niethammer, Qin Liu, Saptarashmi Bandyopadhyay, Vikas Bahirwani","submitted_at":"2026-05-28T07:29:02Z","abstract_excerpt":"Online 3D scene perception in real time is essential for robotics, AR/VR, and autonomous systems, particularly in edge computing scenarios where computational resources are limited and privacy is crucial. Recent state-of-the-art methods like EmbodiedSAM (ESAM) demonstrate the promise of online 3D perception by leveraging the Segment Anything Model (SAM) for real-time, fine-grained, and generalized 3D instance segmentation. However, ESAM still relies on a computationally expensive 3D sparse UNet for point cloud feature extraction, which accounts for the majority of the 3D inference time, hinder"},"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":"2605.29505","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T07:29:02Z","cross_cats_sorted":[],"title_canon_sha256":"0da27d9d55305fd8b3f77d1a90ea56e77014824374187b138b98e7e39e7e615d","abstract_canon_sha256":"8b48d33345ab40f80eac677a36e82253e4944b4158620807fd6c21df748010f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:43.449546Z","signature_b64":"efaQRpZyNaHuXwZRAVEPzaMuUCiKqGBWQa4yfHAz4GHQiPkmvV/QzDnIfZv0QT/uf91D23xeXiFXTccEOA8xBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d459217bcc16937324b6606bd86a04c026ee336136e3f49b92734fb0d035ef93","last_reissued_at":"2026-05-29T01:05:43.448747Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:43.448747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ESAM++: Efficient Online 3D Perception on the Edge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Colaco, Ehsan Adeli, Lavisha Aggarwal, Marc Niethammer, Qin Liu, Saptarashmi Bandyopadhyay, Vikas Bahirwani","submitted_at":"2026-05-28T07:29:02Z","abstract_excerpt":"Online 3D scene perception in real time is essential for robotics, AR/VR, and autonomous systems, particularly in edge computing scenarios where computational resources are limited and privacy is crucial. Recent state-of-the-art methods like EmbodiedSAM (ESAM) demonstrate the promise of online 3D perception by leveraging the Segment Anything Model (SAM) for real-time, fine-grained, and generalized 3D instance segmentation. However, ESAM still relies on a computationally expensive 3D sparse UNet for point cloud feature extraction, which accounts for the majority of the 3D inference time, hinder"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29505","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/2605.29505/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":"2605.29505","created_at":"2026-05-29T01:05:43.448866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29505v1","created_at":"2026-05-29T01:05:43.448866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29505","created_at":"2026-05-29T01:05:43.448866+00:00"},{"alias_kind":"pith_short_12","alias_value":"2RMSC66MC2JX","created_at":"2026-05-29T01:05:43.448866+00:00"},{"alias_kind":"pith_short_16","alias_value":"2RMSC66MC2JXGJFW","created_at":"2026-05-29T01:05:43.448866+00:00"},{"alias_kind":"pith_short_8","alias_value":"2RMSC66M","created_at":"2026-05-29T01:05:43.448866+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/2RMSC66MC2JXGJFWMBV5Q2QEYA","json":"https://pith.science/pith/2RMSC66MC2JXGJFWMBV5Q2QEYA.json","graph_json":"https://pith.science/api/pith-number/2RMSC66MC2JXGJFWMBV5Q2QEYA/graph.json","events_json":"https://pith.science/api/pith-number/2RMSC66MC2JXGJFWMBV5Q2QEYA/events.json","paper":"https://pith.science/paper/2RMSC66M"},"agent_actions":{"view_html":"https://pith.science/pith/2RMSC66MC2JXGJFWMBV5Q2QEYA","download_json":"https://pith.science/pith/2RMSC66MC2JXGJFWMBV5Q2QEYA.json","view_paper":"https://pith.science/paper/2RMSC66M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29505&json=true","fetch_graph":"https://pith.science/api/pith-number/2RMSC66MC2JXGJFWMBV5Q2QEYA/graph.json","fetch_events":"https://pith.science/api/pith-number/2RMSC66MC2JXGJFWMBV5Q2QEYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2RMSC66MC2JXGJFWMBV5Q2QEYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2RMSC66MC2JXGJFWMBV5Q2QEYA/action/storage_attestation","attest_author":"https://pith.science/pith/2RMSC66MC2JXGJFWMBV5Q2QEYA/action/author_attestation","sign_citation":"https://pith.science/pith/2RMSC66MC2JXGJFWMBV5Q2QEYA/action/citation_signature","submit_replication":"https://pith.science/pith/2RMSC66MC2JXGJFWMBV5Q2QEYA/action/replication_record"}},"created_at":"2026-05-29T01:05:43.448866+00:00","updated_at":"2026-05-29T01:05:43.448866+00:00"}