{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MFZOVF5YJ7YONQAS5DVMACUZJV","short_pith_number":"pith:MFZOVF5Y","schema_version":"1.0","canonical_sha256":"6172ea97b84ff0e6c012e8eac00a994d5fb1658e9de00945ca25d6d23f2622b9","source":{"kind":"arxiv","id":"2603.11917","version":2},"attestation_state":"computed","paper":{"title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haotong Qin, Michele Magno, Nicola Farronato, Pietro Bonazzi, Stefan Zihlmann","submitted_at":"2026-03-12T13:31:43Z","abstract_excerpt":"Real-time, on-device segmentation is critical for latency-sensitive and privacy-aware applications such as smart glasses and Internet-of-Things devices. We introduce PicoSAM3, a lightweight promptable visual segmentation model optimized for edge and in-sensor execution, including deployment on the Sony IMX500 vision sensor. PicoSAM3 has 1.3M parameters and combines a dense CNN architecture with region of interest prompt encoding, Efficient Channel Attention, and knowledge distillation from SAM2 and SAM3. On COCO and LVIS, PicoSAM3 achieves 65.45% and 64.01% mIoU, respectively, outperforming ex"},"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":"2603.11917","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-12T13:31:43Z","cross_cats_sorted":[],"title_canon_sha256":"0564328441ad31bde2d437fda7b747e2e821bc12bfa1d03f1131f3fdcb50fca0","abstract_canon_sha256":"92c4888ef11f0fd5ab32f6912acf75e4c1d913a1543eba69742efb32ed754be3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:40.826033Z","signature_b64":"Aj9utiE7yRres6BPc2G61tLd5HlxdKHydG0Dn3q5MjHDvu7Yte4qo2Y8b1arCi8jil9jXb8w8GjrizPQ2AozDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6172ea97b84ff0e6c012e8eac00a994d5fb1658e9de00945ca25d6d23f2622b9","last_reissued_at":"2026-06-09T02:08:40.824969Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:40.824969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haotong Qin, Michele Magno, Nicola Farronato, Pietro Bonazzi, Stefan Zihlmann","submitted_at":"2026-03-12T13:31:43Z","abstract_excerpt":"Real-time, on-device segmentation is critical for latency-sensitive and privacy-aware applications such as smart glasses and Internet-of-Things devices. We introduce PicoSAM3, a lightweight promptable visual segmentation model optimized for edge and in-sensor execution, including deployment on the Sony IMX500 vision sensor. PicoSAM3 has 1.3M parameters and combines a dense CNN architecture with region of interest prompt encoding, Efficient Channel Attention, and knowledge distillation from SAM2 and SAM3. On COCO and LVIS, PicoSAM3 achieves 65.45% and 64.01% mIoU, respectively, outperforming ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.11917","kind":"arxiv","version":2},"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/2603.11917/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":"2603.11917","created_at":"2026-06-09T02:08:40.825123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.11917v2","created_at":"2026-06-09T02:08:40.825123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.11917","created_at":"2026-06-09T02:08:40.825123+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFZOVF5YJ7YO","created_at":"2026-06-09T02:08:40.825123+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFZOVF5YJ7YONQAS","created_at":"2026-06-09T02:08:40.825123+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFZOVF5Y","created_at":"2026-06-09T02:08:40.825123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.01271","citing_title":"Exploiting In-Sensor Computing for Energy-Efficient Earth Observation","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MFZOVF5YJ7YONQAS5DVMACUZJV","json":"https://pith.science/pith/MFZOVF5YJ7YONQAS5DVMACUZJV.json","graph_json":"https://pith.science/api/pith-number/MFZOVF5YJ7YONQAS5DVMACUZJV/graph.json","events_json":"https://pith.science/api/pith-number/MFZOVF5YJ7YONQAS5DVMACUZJV/events.json","paper":"https://pith.science/paper/MFZOVF5Y"},"agent_actions":{"view_html":"https://pith.science/pith/MFZOVF5YJ7YONQAS5DVMACUZJV","download_json":"https://pith.science/pith/MFZOVF5YJ7YONQAS5DVMACUZJV.json","view_paper":"https://pith.science/paper/MFZOVF5Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.11917&json=true","fetch_graph":"https://pith.science/api/pith-number/MFZOVF5YJ7YONQAS5DVMACUZJV/graph.json","fetch_events":"https://pith.science/api/pith-number/MFZOVF5YJ7YONQAS5DVMACUZJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFZOVF5YJ7YONQAS5DVMACUZJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFZOVF5YJ7YONQAS5DVMACUZJV/action/storage_attestation","attest_author":"https://pith.science/pith/MFZOVF5YJ7YONQAS5DVMACUZJV/action/author_attestation","sign_citation":"https://pith.science/pith/MFZOVF5YJ7YONQAS5DVMACUZJV/action/citation_signature","submit_replication":"https://pith.science/pith/MFZOVF5YJ7YONQAS5DVMACUZJV/action/replication_record"}},"created_at":"2026-06-09T02:08:40.825123+00:00","updated_at":"2026-06-09T02:08:40.825123+00:00"}