{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ZT4G4LAHP7B6N5I2WKP57AG3AE","short_pith_number":"pith:ZT4G4LAH","canonical_record":{"source":{"id":"2208.08984","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-18T17:55:37Z","cross_cats_sorted":[],"title_canon_sha256":"c7973e9b44b81b6d3d5e72ebeca63119603854c0070652c5ae6a77cf7fec85df","abstract_canon_sha256":"ddfcb468b3b4bc805e04e93ebd14cf6322d62a23c3a738bd2e82aab012dbbc8d"},"schema_version":"1.0"},"canonical_sha256":"ccf86e2c077fc3e6f51ab29fdf80db010b7d79a97752ad5b90948e0b57e60059","source":{"kind":"arxiv","id":"2208.08984","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.08984","created_at":"2026-07-05T06:18:36Z"},{"alias_kind":"arxiv_version","alias_value":"2208.08984v2","created_at":"2026-07-05T06:18:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.08984","created_at":"2026-07-05T06:18:36Z"},{"alias_kind":"pith_short_12","alias_value":"ZT4G4LAHP7B6","created_at":"2026-07-05T06:18:36Z"},{"alias_kind":"pith_short_16","alias_value":"ZT4G4LAHP7B6N5I2","created_at":"2026-07-05T06:18:36Z"},{"alias_kind":"pith_short_8","alias_value":"ZT4G4LAH","created_at":"2026-07-05T06:18:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ZT4G4LAHP7B6N5I2WKP57AG3AE","target":"record","payload":{"canonical_record":{"source":{"id":"2208.08984","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-18T17:55:37Z","cross_cats_sorted":[],"title_canon_sha256":"c7973e9b44b81b6d3d5e72ebeca63119603854c0070652c5ae6a77cf7fec85df","abstract_canon_sha256":"ddfcb468b3b4bc805e04e93ebd14cf6322d62a23c3a738bd2e82aab012dbbc8d"},"schema_version":"1.0"},"canonical_sha256":"ccf86e2c077fc3e6f51ab29fdf80db010b7d79a97752ad5b90948e0b57e60059","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:36.166069Z","signature_b64":"ES0dPRhkeDDmrn7iIiBMM0xMcz2TP7rNWSlPryA7lHbVP1jncYBqxhkOMay0iqF34ca1rsW33RSvn7k+OV2oAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccf86e2c077fc3e6f51ab29fdf80db010b7d79a97752ad5b90948e0b57e60059","last_reissued_at":"2026-07-05T06:18:36.165574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:36.165574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.08984","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:18:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PO71/RzObtB5OhWfk960D40W5iFgBUMZNnPHFasFFSBrqVTaCb1a79lcnDUfk6Bmsfk+VbyndYew3Mot4VsTBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T22:22:01.001448Z"},"content_sha256":"244cac0cd579ff185132cc5cb2ba1b1596e3bbfc27d535413803f39e4c74446a","schema_version":"1.0","event_id":"sha256:244cac0cd579ff185132cc5cb2ba1b1596e3bbfc27d535413803f39e4c74446a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ZT4G4LAHP7B6N5I2WKP57AG3AE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Open-Vocabulary Universal Image Segmentation with MaskCLIP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jieke Wang, Zheng Ding, Zhuowen Tu","submitted_at":"2022-08-18T17:55:37Z","abstract_excerpt":"In this paper, we tackle an emerging computer vision task, open-vocabulary universal image segmentation, that aims to perform semantic/instance/panoptic segmentation (background semantic labeling + foreground instance segmentation) for arbitrary categories of text-based descriptions in inference time. We first build a baseline method by directly adopting pre-trained CLIP models without finetuning or distillation. We then develop MaskCLIP, a Transformer-based approach with a MaskCLIP Visual Encoder, which is an encoder-only module that seamlessly integrates mask tokens with a pre-trained ViT CL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.08984","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/2208.08984/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":"2026-07-05T06:18:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kI4WMh0hdPvcABUAUcmbSSaWHpqZf26k4REs5G35NPuCoqDAbI7jHjUkdyFzxCMt3Zc3qWDHQrfop/hl6uc1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T22:22:01.001991Z"},"content_sha256":"e97d59a95d56d5db5fb6f70c68e4619f0db3c56e94a961b6edcec47003f485a2","schema_version":"1.0","event_id":"sha256:e97d59a95d56d5db5fb6f70c68e4619f0db3c56e94a961b6edcec47003f485a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZT4G4LAHP7B6N5I2WKP57AG3AE/bundle.json","state_url":"https://pith.science/pith/ZT4G4LAHP7B6N5I2WKP57AG3AE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZT4G4LAHP7B6N5I2WKP57AG3AE/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":"2026-08-23T22:22:01Z","links":{"resolver":"https://pith.science/pith/ZT4G4LAHP7B6N5I2WKP57AG3AE","bundle":"https://pith.science/pith/ZT4G4LAHP7B6N5I2WKP57AG3AE/bundle.json","state":"https://pith.science/pith/ZT4G4LAHP7B6N5I2WKP57AG3AE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZT4G4LAHP7B6N5I2WKP57AG3AE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZT4G4LAHP7B6N5I2WKP57AG3AE","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":"ddfcb468b3b4bc805e04e93ebd14cf6322d62a23c3a738bd2e82aab012dbbc8d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-18T17:55:37Z","title_canon_sha256":"c7973e9b44b81b6d3d5e72ebeca63119603854c0070652c5ae6a77cf7fec85df"},"schema_version":"1.0","source":{"id":"2208.08984","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.08984","created_at":"2026-07-05T06:18:36Z"},{"alias_kind":"arxiv_version","alias_value":"2208.08984v2","created_at":"2026-07-05T06:18:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.08984","created_at":"2026-07-05T06:18:36Z"},{"alias_kind":"pith_short_12","alias_value":"ZT4G4LAHP7B6","created_at":"2026-07-05T06:18:36Z"},{"alias_kind":"pith_short_16","alias_value":"ZT4G4LAHP7B6N5I2","created_at":"2026-07-05T06:18:36Z"},{"alias_kind":"pith_short_8","alias_value":"ZT4G4LAH","created_at":"2026-07-05T06:18:36Z"}],"graph_snapshots":[{"event_id":"sha256:e97d59a95d56d5db5fb6f70c68e4619f0db3c56e94a961b6edcec47003f485a2","target":"graph","created_at":"2026-07-05T06:18:36Z","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/2208.08984/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we tackle an emerging computer vision task, open-vocabulary universal image segmentation, that aims to perform semantic/instance/panoptic segmentation (background semantic labeling + foreground instance segmentation) for arbitrary categories of text-based descriptions in inference time. We first build a baseline method by directly adopting pre-trained CLIP models without finetuning or distillation. We then develop MaskCLIP, a Transformer-based approach with a MaskCLIP Visual Encoder, which is an encoder-only module that seamlessly integrates mask tokens with a pre-trained ViT CL","authors_text":"Jieke Wang, Zheng Ding, Zhuowen Tu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-18T17:55:37Z","title":"Open-Vocabulary Universal Image Segmentation with MaskCLIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.08984","kind":"arxiv","version":2},"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":"sha256:244cac0cd579ff185132cc5cb2ba1b1596e3bbfc27d535413803f39e4c74446a","target":"record","created_at":"2026-07-05T06:18:36Z","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":"ddfcb468b3b4bc805e04e93ebd14cf6322d62a23c3a738bd2e82aab012dbbc8d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-18T17:55:37Z","title_canon_sha256":"c7973e9b44b81b6d3d5e72ebeca63119603854c0070652c5ae6a77cf7fec85df"},"schema_version":"1.0","source":{"id":"2208.08984","kind":"arxiv","version":2}},"canonical_sha256":"ccf86e2c077fc3e6f51ab29fdf80db010b7d79a97752ad5b90948e0b57e60059","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ccf86e2c077fc3e6f51ab29fdf80db010b7d79a97752ad5b90948e0b57e60059","first_computed_at":"2026-07-05T06:18:36.165574Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:18:36.165574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ES0dPRhkeDDmrn7iIiBMM0xMcz2TP7rNWSlPryA7lHbVP1jncYBqxhkOMay0iqF34ca1rsW33RSvn7k+OV2oAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:18:36.166069Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.08984","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:244cac0cd579ff185132cc5cb2ba1b1596e3bbfc27d535413803f39e4c74446a","sha256:e97d59a95d56d5db5fb6f70c68e4619f0db3c56e94a961b6edcec47003f485a2"],"state_sha256":"0138e7e0a5ad71f29c7bb8cb32a0efd63c83f28f99d079a873eb3d776eb2a570"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DfqMzCFIVs9A3cpwLNnw7EWHfY5sUJ0coxDBmekzVakZuvPtWtAhdudTn/ZkS9crvPRPTvOQnPOkrBDz0hm5CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T22:22:01.007431Z","bundle_sha256":"fa02cfc3b85fdf957bfa78693dce9bcf9be56840d4604425ea0c4bf4b50fc058"}}