{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VXNRBCWTNTENASKZCM4PJVURI3","short_pith_number":"pith:VXNRBCWT","schema_version":"1.0","canonical_sha256":"addb108ad36cc8d049591338f4d69146f71a525c0455c76ed81aa72588273cc7","source":{"kind":"arxiv","id":"2506.07850","version":1},"attestation_state":"computed","paper":{"title":"SAM2Auto: Auto Annotation Using FLASH","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arash Rocky, Q.M. Jonathan Wu","submitted_at":"2025-06-09T15:15:15Z","abstract_excerpt":"Vision-Language Models (VLMs) lag behind Large Language Models due to the scarcity of annotated datasets, as creating paired visual-textual annotations is labor-intensive and expensive. To address this bottleneck, we introduce SAM2Auto, the first fully automated annotation pipeline for video datasets requiring no human intervention or dataset-specific training. Our approach consists of two key components: SMART-OD, a robust object detection system that combines automatic mask generation with open-world object detection capabilities, and FLASH (Frame-Level Annotation and Segmentation Handler), "},"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":"2506.07850","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T15:15:15Z","cross_cats_sorted":[],"title_canon_sha256":"364d6a08f719a153c3547e522627b3e856734c8cfca2c9fbf88aa9b2a4b02653","abstract_canon_sha256":"1e09c6f23c50564251c02960b42dc6e8358a8db82dc28cf364555f74130c0e72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:34.415452Z","signature_b64":"vseYgCPZEsopYurFB/pa743iY4zLm279s3u/qHV/uewY3UZ1cQxwUdzcIeGZJTe28NacC5Ww2VQvwcSAyNMLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"addb108ad36cc8d049591338f4d69146f71a525c0455c76ed81aa72588273cc7","last_reissued_at":"2026-07-05T11:18:34.414970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:34.414970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAM2Auto: Auto Annotation Using FLASH","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arash Rocky, Q.M. Jonathan Wu","submitted_at":"2025-06-09T15:15:15Z","abstract_excerpt":"Vision-Language Models (VLMs) lag behind Large Language Models due to the scarcity of annotated datasets, as creating paired visual-textual annotations is labor-intensive and expensive. To address this bottleneck, we introduce SAM2Auto, the first fully automated annotation pipeline for video datasets requiring no human intervention or dataset-specific training. Our approach consists of two key components: SMART-OD, a robust object detection system that combines automatic mask generation with open-world object detection capabilities, and FLASH (Frame-Level Annotation and Segmentation Handler), "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07850","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/2506.07850/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":"2506.07850","created_at":"2026-07-05T11:18:34.415026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07850v1","created_at":"2026-07-05T11:18:34.415026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07850","created_at":"2026-07-05T11:18:34.415026+00:00"},{"alias_kind":"pith_short_12","alias_value":"VXNRBCWTNTEN","created_at":"2026-07-05T11:18:34.415026+00:00"},{"alias_kind":"pith_short_16","alias_value":"VXNRBCWTNTENASKZ","created_at":"2026-07-05T11:18:34.415026+00:00"},{"alias_kind":"pith_short_8","alias_value":"VXNRBCWT","created_at":"2026-07-05T11:18:34.415026+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13497","citing_title":"SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VXNRBCWTNTENASKZCM4PJVURI3","json":"https://pith.science/pith/VXNRBCWTNTENASKZCM4PJVURI3.json","graph_json":"https://pith.science/api/pith-number/VXNRBCWTNTENASKZCM4PJVURI3/graph.json","events_json":"https://pith.science/api/pith-number/VXNRBCWTNTENASKZCM4PJVURI3/events.json","paper":"https://pith.science/paper/VXNRBCWT"},"agent_actions":{"view_html":"https://pith.science/pith/VXNRBCWTNTENASKZCM4PJVURI3","download_json":"https://pith.science/pith/VXNRBCWTNTENASKZCM4PJVURI3.json","view_paper":"https://pith.science/paper/VXNRBCWT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07850&json=true","fetch_graph":"https://pith.science/api/pith-number/VXNRBCWTNTENASKZCM4PJVURI3/graph.json","fetch_events":"https://pith.science/api/pith-number/VXNRBCWTNTENASKZCM4PJVURI3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VXNRBCWTNTENASKZCM4PJVURI3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VXNRBCWTNTENASKZCM4PJVURI3/action/storage_attestation","attest_author":"https://pith.science/pith/VXNRBCWTNTENASKZCM4PJVURI3/action/author_attestation","sign_citation":"https://pith.science/pith/VXNRBCWTNTENASKZCM4PJVURI3/action/citation_signature","submit_replication":"https://pith.science/pith/VXNRBCWTNTENASKZCM4PJVURI3/action/replication_record"}},"created_at":"2026-07-05T11:18:34.415026+00:00","updated_at":"2026-07-05T11:18:34.415026+00:00"}