{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VXNRBCWTNTENASKZCM4PJVURI3","short_pith_number":"pith:VXNRBCWT","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"},"canonical_sha256":"addb108ad36cc8d049591338f4d69146f71a525c0455c76ed81aa72588273cc7","source":{"kind":"arxiv","id":"2506.07850","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07850","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07850v1","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07850","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"pith_short_12","alias_value":"VXNRBCWTNTEN","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"pith_short_16","alias_value":"VXNRBCWTNTENASKZ","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"pith_short_8","alias_value":"VXNRBCWT","created_at":"2026-07-05T11:18:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VXNRBCWTNTENASKZCM4PJVURI3","target":"record","payload":{"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"},"canonical_sha256":"addb108ad36cc8d049591338f4d69146f71a525c0455c76ed81aa72588273cc7","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"},"source_kind":"arxiv","source_id":"2506.07850","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Vx+nukTSt53z2dYbDyQHbcFXONZ/1gfI/iDiPFkOx8ypOZ0UXHzs/w42lyO5By9nF97duJi0mRYly6agdH6Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:09:12.685799Z"},"content_sha256":"efa4b8a4c6efbba1f88b2f64e1073fe7203d7bd97fdd8b5a244c222a4a80afa9","schema_version":"1.0","event_id":"sha256:efa4b8a4c6efbba1f88b2f64e1073fe7203d7bd97fdd8b5a244c222a4a80afa9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VXNRBCWTNTENASKZCM4PJVURI3","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Btn/sAC7xVUBlHGwFFMtDckGxf3B6R9JkXk7ieCyz3kGfgYeE+VUN64+aYFMKB4jQ7y5aKtRMH59e+8uQyzWBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:09:12.686399Z"},"content_sha256":"a59cadbd42ae0353cce79d84497d119b55715be0fc514a7e7ab7dd88c7ac6efd","schema_version":"1.0","event_id":"sha256:a59cadbd42ae0353cce79d84497d119b55715be0fc514a7e7ab7dd88c7ac6efd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VXNRBCWTNTENASKZCM4PJVURI3/bundle.json","state_url":"https://pith.science/pith/VXNRBCWTNTENASKZCM4PJVURI3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VXNRBCWTNTENASKZCM4PJVURI3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T22:09:12Z","links":{"resolver":"https://pith.science/pith/VXNRBCWTNTENASKZCM4PJVURI3","bundle":"https://pith.science/pith/VXNRBCWTNTENASKZCM4PJVURI3/bundle.json","state":"https://pith.science/pith/VXNRBCWTNTENASKZCM4PJVURI3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VXNRBCWTNTENASKZCM4PJVURI3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VXNRBCWTNTENASKZCM4PJVURI3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1e09c6f23c50564251c02960b42dc6e8358a8db82dc28cf364555f74130c0e72","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T15:15:15Z","title_canon_sha256":"364d6a08f719a153c3547e522627b3e856734c8cfca2c9fbf88aa9b2a4b02653"},"schema_version":"1.0","source":{"id":"2506.07850","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07850","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07850v1","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07850","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"pith_short_12","alias_value":"VXNRBCWTNTEN","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"pith_short_16","alias_value":"VXNRBCWTNTENASKZ","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"pith_short_8","alias_value":"VXNRBCWT","created_at":"2026-07-05T11:18:34Z"}],"graph_snapshots":[{"event_id":"sha256:a59cadbd42ae0353cce79d84497d119b55715be0fc514a7e7ab7dd88c7ac6efd","target":"graph","created_at":"2026-07-05T11:18:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.07850/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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), ","authors_text":"Arash Rocky, Q.M. Jonathan Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T15:15:15Z","title":"SAM2Auto: Auto Annotation Using FLASH"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07850","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:efa4b8a4c6efbba1f88b2f64e1073fe7203d7bd97fdd8b5a244c222a4a80afa9","target":"record","created_at":"2026-07-05T11:18:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1e09c6f23c50564251c02960b42dc6e8358a8db82dc28cf364555f74130c0e72","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T15:15:15Z","title_canon_sha256":"364d6a08f719a153c3547e522627b3e856734c8cfca2c9fbf88aa9b2a4b02653"},"schema_version":"1.0","source":{"id":"2506.07850","kind":"arxiv","version":1}},"canonical_sha256":"addb108ad36cc8d049591338f4d69146f71a525c0455c76ed81aa72588273cc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"addb108ad36cc8d049591338f4d69146f71a525c0455c76ed81aa72588273cc7","first_computed_at":"2026-07-05T11:18:34.414970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:34.414970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vseYgCPZEsopYurFB/pa743iY4zLm279s3u/qHV/uewY3UZ1cQxwUdzcIeGZJTe28NacC5Ww2VQvwcSAyNMLAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:34.415452Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07850","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efa4b8a4c6efbba1f88b2f64e1073fe7203d7bd97fdd8b5a244c222a4a80afa9","sha256:a59cadbd42ae0353cce79d84497d119b55715be0fc514a7e7ab7dd88c7ac6efd"],"state_sha256":"a41d8cf4d18b0f829bb868d9006b5628cbb411f1f83261b2372a35ccede9a9dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8CkrKyV+W9Vvl13/bMp5Rw9l8aJOhxCCxMpRYC66lUwQjGfaFVVxssGpbyOjbXCRL3eJKMLNHMK1fkrCsdVFCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:09:12.690630Z","bundle_sha256":"5892e5769d4cf6d04f0482f61fcf02566e7b3f45d8b45bfa5302e0f54f962b92"}}