{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FPX52HWILQK57YXJDXIUVPWI5V","short_pith_number":"pith:FPX52HWI","canonical_record":{"source":{"id":"2306.00450","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-01T08:47:06Z","cross_cats_sorted":[],"title_canon_sha256":"c6ca68ac82b54e1c2b98949571867d320538f371709db38014ebe625186336ef","abstract_canon_sha256":"4c3c8c7b86bb8b191abfcc9acbd85899acebc4f491d03a7b9018dae31679883d"},"schema_version":"1.0"},"canonical_sha256":"2befdd1ec85c15dfe2e91dd14abec8ed457e59dcafcd3e4d8ed43b90ce5e85d0","source":{"kind":"arxiv","id":"2306.00450","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00450","created_at":"2026-07-05T06:16:26Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00450v1","created_at":"2026-07-05T06:16:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00450","created_at":"2026-07-05T06:16:26Z"},{"alias_kind":"pith_short_12","alias_value":"FPX52HWILQK5","created_at":"2026-07-05T06:16:26Z"},{"alias_kind":"pith_short_16","alias_value":"FPX52HWILQK57YXJ","created_at":"2026-07-05T06:16:26Z"},{"alias_kind":"pith_short_8","alias_value":"FPX52HWI","created_at":"2026-07-05T06:16:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FPX52HWILQK57YXJDXIUVPWI5V","target":"record","payload":{"canonical_record":{"source":{"id":"2306.00450","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-01T08:47:06Z","cross_cats_sorted":[],"title_canon_sha256":"c6ca68ac82b54e1c2b98949571867d320538f371709db38014ebe625186336ef","abstract_canon_sha256":"4c3c8c7b86bb8b191abfcc9acbd85899acebc4f491d03a7b9018dae31679883d"},"schema_version":"1.0"},"canonical_sha256":"2befdd1ec85c15dfe2e91dd14abec8ed457e59dcafcd3e4d8ed43b90ce5e85d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:26.631262Z","signature_b64":"SKyHiyHjgW1Va7VQHEBYwzukgJjlUAq9RE8WaF6O2heT3wPzW6zBB0rILZqNN0mysGHhckA6yveKBWgnuU9SBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2befdd1ec85c15dfe2e91dd14abec8ed457e59dcafcd3e4d8ed43b90ce5e85d0","last_reissued_at":"2026-07-05T06:16:26.630828Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:26.630828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.00450","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":"2026-07-05T06:16:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tx9O+dq5jKw5lrZrXnLS3s3AaFqvl3A7WdUt5a5DRejGkQeitswKiq+hT3LSI/+VhlfsTaNTs99IbUPkicfSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T00:25:33.896774Z"},"content_sha256":"5fd4101735f017a2fe196652dd7decec829cd32ac7ac6badf66d4a4c90d72f23","schema_version":"1.0","event_id":"sha256:5fd4101735f017a2fe196652dd7decec829cd32ac7ac6badf66d4a4c90d72f23"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FPX52HWILQK57YXJDXIUVPWI5V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring Open-Vocabulary Semantic Segmentation without Human Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernard Ghanem, Chenchen Zhu, Deyao Zhu, Fanyi Xiao, Guocheng Qian, Jun Chen, Mohamed Elhoseiny, Sean Chang Culatana, Zhicheng Yan","submitted_at":"2023-06-01T08:47:06Z","abstract_excerpt":"Semantic segmentation is a crucial task in computer vision that involves segmenting images into semantically meaningful regions at the pixel level. However, existing approaches often rely on expensive human annotations as supervision for model training, limiting their scalability to large, unlabeled datasets. To address this challenge, we present ZeroSeg, a novel method that leverages the existing pretrained vision-language (VL) model (e.g. CLIP) to train open-vocabulary zero-shot semantic segmentation models. Although acquired extensive knowledge of visual concepts, it is non-trivial to explo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00450","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/2306.00450/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":"2026-07-05T06:16:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yEhfpwOWvxA0ojZowlrJ+zSzlD2FbZh8etCmBiNzy+ydgWdGDpJtx/hGN8Q8tIBfZyG0wi9+mHEbpEHlMNL7AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T00:25:33.897137Z"},"content_sha256":"edd0592a7f65d0895bfd8ed98725a5ac85fbf19ad9af826cc0da675b7c1058f3","schema_version":"1.0","event_id":"sha256:edd0592a7f65d0895bfd8ed98725a5ac85fbf19ad9af826cc0da675b7c1058f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FPX52HWILQK57YXJDXIUVPWI5V/bundle.json","state_url":"https://pith.science/pith/FPX52HWILQK57YXJDXIUVPWI5V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FPX52HWILQK57YXJDXIUVPWI5V/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":"2026-07-22T00:25:33Z","links":{"resolver":"https://pith.science/pith/FPX52HWILQK57YXJDXIUVPWI5V","bundle":"https://pith.science/pith/FPX52HWILQK57YXJDXIUVPWI5V/bundle.json","state":"https://pith.science/pith/FPX52HWILQK57YXJDXIUVPWI5V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FPX52HWILQK57YXJDXIUVPWI5V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FPX52HWILQK57YXJDXIUVPWI5V","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":"4c3c8c7b86bb8b191abfcc9acbd85899acebc4f491d03a7b9018dae31679883d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-01T08:47:06Z","title_canon_sha256":"c6ca68ac82b54e1c2b98949571867d320538f371709db38014ebe625186336ef"},"schema_version":"1.0","source":{"id":"2306.00450","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00450","created_at":"2026-07-05T06:16:26Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00450v1","created_at":"2026-07-05T06:16:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00450","created_at":"2026-07-05T06:16:26Z"},{"alias_kind":"pith_short_12","alias_value":"FPX52HWILQK5","created_at":"2026-07-05T06:16:26Z"},{"alias_kind":"pith_short_16","alias_value":"FPX52HWILQK57YXJ","created_at":"2026-07-05T06:16:26Z"},{"alias_kind":"pith_short_8","alias_value":"FPX52HWI","created_at":"2026-07-05T06:16:26Z"}],"graph_snapshots":[{"event_id":"sha256:edd0592a7f65d0895bfd8ed98725a5ac85fbf19ad9af826cc0da675b7c1058f3","target":"graph","created_at":"2026-07-05T06:16:26Z","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/2306.00450/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Semantic segmentation is a crucial task in computer vision that involves segmenting images into semantically meaningful regions at the pixel level. However, existing approaches often rely on expensive human annotations as supervision for model training, limiting their scalability to large, unlabeled datasets. To address this challenge, we present ZeroSeg, a novel method that leverages the existing pretrained vision-language (VL) model (e.g. CLIP) to train open-vocabulary zero-shot semantic segmentation models. Although acquired extensive knowledge of visual concepts, it is non-trivial to explo","authors_text":"Bernard Ghanem, Chenchen Zhu, Deyao Zhu, Fanyi Xiao, Guocheng Qian, Jun Chen, Mohamed Elhoseiny, Sean Chang Culatana, Zhicheng Yan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-01T08:47:06Z","title":"Exploring Open-Vocabulary Semantic Segmentation without Human Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00450","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":"sha256:5fd4101735f017a2fe196652dd7decec829cd32ac7ac6badf66d4a4c90d72f23","target":"record","created_at":"2026-07-05T06:16:26Z","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":"4c3c8c7b86bb8b191abfcc9acbd85899acebc4f491d03a7b9018dae31679883d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-01T08:47:06Z","title_canon_sha256":"c6ca68ac82b54e1c2b98949571867d320538f371709db38014ebe625186336ef"},"schema_version":"1.0","source":{"id":"2306.00450","kind":"arxiv","version":1}},"canonical_sha256":"2befdd1ec85c15dfe2e91dd14abec8ed457e59dcafcd3e4d8ed43b90ce5e85d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2befdd1ec85c15dfe2e91dd14abec8ed457e59dcafcd3e4d8ed43b90ce5e85d0","first_computed_at":"2026-07-05T06:16:26.630828Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:16:26.630828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SKyHiyHjgW1Va7VQHEBYwzukgJjlUAq9RE8WaF6O2heT3wPzW6zBB0rILZqNN0mysGHhckA6yveKBWgnuU9SBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:16:26.631262Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.00450","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fd4101735f017a2fe196652dd7decec829cd32ac7ac6badf66d4a4c90d72f23","sha256:edd0592a7f65d0895bfd8ed98725a5ac85fbf19ad9af826cc0da675b7c1058f3"],"state_sha256":"ced7b91b16b625fa0bd0f3b2fa61f7b80c51d67e9a29ab407fbaabf89ff03406"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S+w4hJQKupk6eVWDp1Z6RhT5D4+TV1QE8ErC4Wm6Q2zmRTDoCA92xvm+agdpFmJdKUm3ux3Socz6n43PEZ9iCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-22T00:25:33.899269Z","bundle_sha256":"7f21cbf2c6353f689880be2e5d3c8643727c47800154870c879c55c6e72ffeba"}}