{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CBBIGAGT6NG6Z5C3QC7TJIELHY","short_pith_number":"pith:CBBIGAGT","canonical_record":{"source":{"id":"2112.12143","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-22T18:57:54Z","cross_cats_sorted":[],"title_canon_sha256":"d6f689b314cc5a77be5f4eb5d8f7e49138189d848d7d24cb342aab22e7ab625c","abstract_canon_sha256":"68fbc467c8dd9b2137f2d900f64c3678b74f37c7c6aaed2fd823baf03001d837"},"schema_version":"1.0"},"canonical_sha256":"10428300d3f34decf45b80bf34a08b3e36422882745150838088772e0be4fbf0","source":{"kind":"arxiv","id":"2112.12143","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.12143","created_at":"2026-07-05T04:42:16Z"},{"alias_kind":"arxiv_version","alias_value":"2112.12143v2","created_at":"2026-07-05T04:42:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.12143","created_at":"2026-07-05T04:42:16Z"},{"alias_kind":"pith_short_12","alias_value":"CBBIGAGT6NG6","created_at":"2026-07-05T04:42:16Z"},{"alias_kind":"pith_short_16","alias_value":"CBBIGAGT6NG6Z5C3","created_at":"2026-07-05T04:42:16Z"},{"alias_kind":"pith_short_8","alias_value":"CBBIGAGT","created_at":"2026-07-05T04:42:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CBBIGAGT6NG6Z5C3QC7TJIELHY","target":"record","payload":{"canonical_record":{"source":{"id":"2112.12143","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-22T18:57:54Z","cross_cats_sorted":[],"title_canon_sha256":"d6f689b314cc5a77be5f4eb5d8f7e49138189d848d7d24cb342aab22e7ab625c","abstract_canon_sha256":"68fbc467c8dd9b2137f2d900f64c3678b74f37c7c6aaed2fd823baf03001d837"},"schema_version":"1.0"},"canonical_sha256":"10428300d3f34decf45b80bf34a08b3e36422882745150838088772e0be4fbf0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:42:16.058442Z","signature_b64":"qe9zBoGwyFDdf8rtnH0rcWIRBf67j8OVc1qndHeeJfw9JNUQ1QP2Ish7Kwpy3xm5/KLBkachMHFmpYNP2gJdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10428300d3f34decf45b80bf34a08b3e36422882745150838088772e0be4fbf0","last_reissued_at":"2026-07-05T04:42:16.057970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:42:16.057970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.12143","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":"2026-07-05T04:42:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OoN3I48QDsFoB/8LJW0SjsR/MNnBt6S19WSD6w5rX4wQV9s+7Mppcr615M0uXuF/pz5Twe1exwK5IyL9aS+6Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:50:41.251670Z"},"content_sha256":"887355c3cb435fe7bec1fa1087a95116ea2301e234c27e90c8c94b1d641847de","schema_version":"1.0","event_id":"sha256:887355c3cb435fe7bec1fa1087a95116ea2301e234c27e90c8c94b1d641847de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CBBIGAGT6NG6Z5C3QC7TJIELHY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Open-Vocabulary Image Segmentation with Image-Level Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Golnaz Ghiasi, Tsung-Yi Lin, Xiuye Gu, Yin Cui","submitted_at":"2021-12-22T18:57:54Z","abstract_excerpt":"We design an open-vocabulary image segmentation model to organize an image into meaningful regions indicated by arbitrary texts. Recent works (CLIP and ALIGN), despite attaining impressive open-vocabulary classification accuracy with image-level caption labels, are unable to segment visual concepts with pixels. We argue that these models miss an important step of visual grouping, which organizes pixels into groups before learning visual-semantic alignments. We propose OpenSeg to address the above issue while still making use of scalable image-level supervision of captions. First, it learns to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.12143","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/2112.12143/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":"2026-07-05T04:42:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rtbZz0VLwFiTsh+npVt2U5Ol0nzmFhXTPUTlyu3jq1plT/fJxMB7JvavW0Lrxtjg+sYRj0T94ZmLaBztXnzdDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:50:41.252162Z"},"content_sha256":"d040d8acef1802d337089b088c1eb9f7bfdcb8872b469af82e6af24e9368faa4","schema_version":"1.0","event_id":"sha256:d040d8acef1802d337089b088c1eb9f7bfdcb8872b469af82e6af24e9368faa4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CBBIGAGT6NG6Z5C3QC7TJIELHY/bundle.json","state_url":"https://pith.science/pith/CBBIGAGT6NG6Z5C3QC7TJIELHY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CBBIGAGT6NG6Z5C3QC7TJIELHY/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":"2026-08-19T17:50:41Z","links":{"resolver":"https://pith.science/pith/CBBIGAGT6NG6Z5C3QC7TJIELHY","bundle":"https://pith.science/pith/CBBIGAGT6NG6Z5C3QC7TJIELHY/bundle.json","state":"https://pith.science/pith/CBBIGAGT6NG6Z5C3QC7TJIELHY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CBBIGAGT6NG6Z5C3QC7TJIELHY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CBBIGAGT6NG6Z5C3QC7TJIELHY","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":"68fbc467c8dd9b2137f2d900f64c3678b74f37c7c6aaed2fd823baf03001d837","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-22T18:57:54Z","title_canon_sha256":"d6f689b314cc5a77be5f4eb5d8f7e49138189d848d7d24cb342aab22e7ab625c"},"schema_version":"1.0","source":{"id":"2112.12143","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.12143","created_at":"2026-07-05T04:42:16Z"},{"alias_kind":"arxiv_version","alias_value":"2112.12143v2","created_at":"2026-07-05T04:42:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.12143","created_at":"2026-07-05T04:42:16Z"},{"alias_kind":"pith_short_12","alias_value":"CBBIGAGT6NG6","created_at":"2026-07-05T04:42:16Z"},{"alias_kind":"pith_short_16","alias_value":"CBBIGAGT6NG6Z5C3","created_at":"2026-07-05T04:42:16Z"},{"alias_kind":"pith_short_8","alias_value":"CBBIGAGT","created_at":"2026-07-05T04:42:16Z"}],"graph_snapshots":[{"event_id":"sha256:d040d8acef1802d337089b088c1eb9f7bfdcb8872b469af82e6af24e9368faa4","target":"graph","created_at":"2026-07-05T04:42:16Z","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/2112.12143/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We design an open-vocabulary image segmentation model to organize an image into meaningful regions indicated by arbitrary texts. Recent works (CLIP and ALIGN), despite attaining impressive open-vocabulary classification accuracy with image-level caption labels, are unable to segment visual concepts with pixels. We argue that these models miss an important step of visual grouping, which organizes pixels into groups before learning visual-semantic alignments. We propose OpenSeg to address the above issue while still making use of scalable image-level supervision of captions. First, it learns to ","authors_text":"Golnaz Ghiasi, Tsung-Yi Lin, Xiuye Gu, Yin Cui","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-22T18:57:54Z","title":"Scaling Open-Vocabulary Image Segmentation with Image-Level Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.12143","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":"sha256:887355c3cb435fe7bec1fa1087a95116ea2301e234c27e90c8c94b1d641847de","target":"record","created_at":"2026-07-05T04:42:16Z","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":"68fbc467c8dd9b2137f2d900f64c3678b74f37c7c6aaed2fd823baf03001d837","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-22T18:57:54Z","title_canon_sha256":"d6f689b314cc5a77be5f4eb5d8f7e49138189d848d7d24cb342aab22e7ab625c"},"schema_version":"1.0","source":{"id":"2112.12143","kind":"arxiv","version":2}},"canonical_sha256":"10428300d3f34decf45b80bf34a08b3e36422882745150838088772e0be4fbf0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10428300d3f34decf45b80bf34a08b3e36422882745150838088772e0be4fbf0","first_computed_at":"2026-07-05T04:42:16.057970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:42:16.057970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qe9zBoGwyFDdf8rtnH0rcWIRBf67j8OVc1qndHeeJfw9JNUQ1QP2Ish7Kwpy3xm5/KLBkachMHFmpYNP2gJdBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:42:16.058442Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.12143","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:887355c3cb435fe7bec1fa1087a95116ea2301e234c27e90c8c94b1d641847de","sha256:d040d8acef1802d337089b088c1eb9f7bfdcb8872b469af82e6af24e9368faa4"],"state_sha256":"f988f0dac6dee5f4e986e03ddf90bca7bc500106771139ec7ad258d887383a01"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4WpdBjtfw4Udmvh+KfBJLVJWX5nTzvWDH90ZnntgPFbsEenjR351ZREoncLAiAgUhqOf5LJ7Xg4mGyGHYYIOCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T17:50:41.259341Z","bundle_sha256":"8e6e3eeb1f343267b9c4b1402a043043e1ac2f8753265472a741ea0382811bd5"}}