{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZSDLNSN76V4MO3JU7YQRBBGY3M","short_pith_number":"pith:ZSDLNSN7","canonical_record":{"source":{"id":"2112.14757","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-29T18:56:18Z","cross_cats_sorted":[],"title_canon_sha256":"a5c8a9d12b4fd2719906c638d7c15b915530f42e05fd38f8af8d43f9736423e2","abstract_canon_sha256":"f527c77888452b2364a8b41f3520e3da9762cc710c1256c9df5512a20c1573b7"},"schema_version":"1.0"},"canonical_sha256":"cc86b6c9bff578c76d34fe211084d8db2b5a41fe8df38d2fbf26881516a566ac","source":{"kind":"arxiv","id":"2112.14757","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.14757","created_at":"2026-07-05T05:29:00Z"},{"alias_kind":"arxiv_version","alias_value":"2112.14757v2","created_at":"2026-07-05T05:29:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.14757","created_at":"2026-07-05T05:29:00Z"},{"alias_kind":"pith_short_12","alias_value":"ZSDLNSN76V4M","created_at":"2026-07-05T05:29:00Z"},{"alias_kind":"pith_short_16","alias_value":"ZSDLNSN76V4MO3JU","created_at":"2026-07-05T05:29:00Z"},{"alias_kind":"pith_short_8","alias_value":"ZSDLNSN7","created_at":"2026-07-05T05:29:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZSDLNSN76V4MO3JU7YQRBBGY3M","target":"record","payload":{"canonical_record":{"source":{"id":"2112.14757","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-29T18:56:18Z","cross_cats_sorted":[],"title_canon_sha256":"a5c8a9d12b4fd2719906c638d7c15b915530f42e05fd38f8af8d43f9736423e2","abstract_canon_sha256":"f527c77888452b2364a8b41f3520e3da9762cc710c1256c9df5512a20c1573b7"},"schema_version":"1.0"},"canonical_sha256":"cc86b6c9bff578c76d34fe211084d8db2b5a41fe8df38d2fbf26881516a566ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:29:00.256130Z","signature_b64":"Q3jNMN/1E5jZKuXdvJET1mrdYJ5NvU0llw4TnFNF8nFdO1q3BcZApYCyKBFsLgjJllPrXBKOhBdGKVhUHpTHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc86b6c9bff578c76d34fe211084d8db2b5a41fe8df38d2fbf26881516a566ac","last_reissued_at":"2026-07-05T05:29:00.255744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:29:00.255744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.14757","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":"2026-07-05T05:29:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R4INj/jr3dC/O+fN1DupsgJtq3z53AHO7WMX8aqPhXSpwc7XXVgStFnmowknhPCYVO/CeFG58IXYLo1jKkQ8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T13:47:38.486664Z"},"content_sha256":"adb3a1daf9b8daec0deda5df238d104a04ad07771437be661bd0350d9126b851","schema_version":"1.0","event_id":"sha256:adb3a1daf9b8daec0deda5df238d104a04ad07771437be661bd0350d9126b851"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZSDLNSN76V4MO3JU7YQRBBGY3M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangyun Wei, Han Hu, Mengde Xu, Xiang Bai, Yue Cao, Yutong Lin, Zheng Zhang","submitted_at":"2021-12-29T18:56:18Z","abstract_excerpt":"Recently, open-vocabulary image classification by vision language pre-training has demonstrated incredible achievements, that the model can classify arbitrary categories without seeing additional annotated images of that category. However, it is still unclear how to make the open-vocabulary recognition work well on broader vision problems. This paper targets open-vocabulary semantic segmentation by building it on an off-the-shelf pre-trained vision-language model, i.e., CLIP. However, semantic segmentation and the CLIP model perform on different visual granularity, that semantic segmentation p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.14757","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/2112.14757/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":"2026-07-05T05:29:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PCjNuUZF69xkxmzOs++5sXLR83B472SnLPZyQjuo4/r14C2E4GZbuQ2sirhbwJ9zgsyO6045Onuf0QSeLlN8BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T13:47:38.487236Z"},"content_sha256":"0d2c290979f5be151e49455e4855a987b25f49c2c0b5a82561414f13389a8a6b","schema_version":"1.0","event_id":"sha256:0d2c290979f5be151e49455e4855a987b25f49c2c0b5a82561414f13389a8a6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZSDLNSN76V4MO3JU7YQRBBGY3M/bundle.json","state_url":"https://pith.science/pith/ZSDLNSN76V4MO3JU7YQRBBGY3M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZSDLNSN76V4MO3JU7YQRBBGY3M/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":"2026-08-19T13:47:38Z","links":{"resolver":"https://pith.science/pith/ZSDLNSN76V4MO3JU7YQRBBGY3M","bundle":"https://pith.science/pith/ZSDLNSN76V4MO3JU7YQRBBGY3M/bundle.json","state":"https://pith.science/pith/ZSDLNSN76V4MO3JU7YQRBBGY3M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZSDLNSN76V4MO3JU7YQRBBGY3M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZSDLNSN76V4MO3JU7YQRBBGY3M","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":"f527c77888452b2364a8b41f3520e3da9762cc710c1256c9df5512a20c1573b7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-29T18:56:18Z","title_canon_sha256":"a5c8a9d12b4fd2719906c638d7c15b915530f42e05fd38f8af8d43f9736423e2"},"schema_version":"1.0","source":{"id":"2112.14757","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.14757","created_at":"2026-07-05T05:29:00Z"},{"alias_kind":"arxiv_version","alias_value":"2112.14757v2","created_at":"2026-07-05T05:29:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.14757","created_at":"2026-07-05T05:29:00Z"},{"alias_kind":"pith_short_12","alias_value":"ZSDLNSN76V4M","created_at":"2026-07-05T05:29:00Z"},{"alias_kind":"pith_short_16","alias_value":"ZSDLNSN76V4MO3JU","created_at":"2026-07-05T05:29:00Z"},{"alias_kind":"pith_short_8","alias_value":"ZSDLNSN7","created_at":"2026-07-05T05:29:00Z"}],"graph_snapshots":[{"event_id":"sha256:0d2c290979f5be151e49455e4855a987b25f49c2c0b5a82561414f13389a8a6b","target":"graph","created_at":"2026-07-05T05:29:00Z","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/2112.14757/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, open-vocabulary image classification by vision language pre-training has demonstrated incredible achievements, that the model can classify arbitrary categories without seeing additional annotated images of that category. However, it is still unclear how to make the open-vocabulary recognition work well on broader vision problems. This paper targets open-vocabulary semantic segmentation by building it on an off-the-shelf pre-trained vision-language model, i.e., CLIP. However, semantic segmentation and the CLIP model perform on different visual granularity, that semantic segmentation p","authors_text":"Fangyun Wei, Han Hu, Mengde Xu, Xiang Bai, Yue Cao, Yutong Lin, Zheng Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-29T18:56:18Z","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.14757","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:adb3a1daf9b8daec0deda5df238d104a04ad07771437be661bd0350d9126b851","target":"record","created_at":"2026-07-05T05:29:00Z","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":"f527c77888452b2364a8b41f3520e3da9762cc710c1256c9df5512a20c1573b7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-29T18:56:18Z","title_canon_sha256":"a5c8a9d12b4fd2719906c638d7c15b915530f42e05fd38f8af8d43f9736423e2"},"schema_version":"1.0","source":{"id":"2112.14757","kind":"arxiv","version":2}},"canonical_sha256":"cc86b6c9bff578c76d34fe211084d8db2b5a41fe8df38d2fbf26881516a566ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc86b6c9bff578c76d34fe211084d8db2b5a41fe8df38d2fbf26881516a566ac","first_computed_at":"2026-07-05T05:29:00.255744Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:29:00.255744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q3jNMN/1E5jZKuXdvJET1mrdYJ5NvU0llw4TnFNF8nFdO1q3BcZApYCyKBFsLgjJllPrXBKOhBdGKVhUHpTHBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:29:00.256130Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.14757","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:adb3a1daf9b8daec0deda5df238d104a04ad07771437be661bd0350d9126b851","sha256:0d2c290979f5be151e49455e4855a987b25f49c2c0b5a82561414f13389a8a6b"],"state_sha256":"a5530276ecee9f00408df4eba1048b4f2f7f35657075cb781fd4fe360d5974f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2+xtgxYgZKlO1NVdH61Dnh1OZ4jyhY/OqKxa0wSstiwERxAJ66MzCV05xgnFU/cMmBsIIdXetiXZQPoie9WnBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T13:47:38.492098Z","bundle_sha256":"4fa4d517ada4f415ca459c5353701e3506cf69e86abbf1c1432e19a6b1a095d5"}}