{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:N6BQEGEBRY76ECFZMFMW6ACT4L","short_pith_number":"pith:N6BQEGEB","canonical_record":{"source":{"id":"2210.04150","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-09T02:57:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ab5e61143bfc259f5649667d38bdc36db4845ebc76d4f28f7a57fd47ae138a0d","abstract_canon_sha256":"61aa96df243ab1dfa327f09a525430978b6ce1a7c54bbce94ee3464805499422"},"schema_version":"1.0"},"canonical_sha256":"6f830218818e3fe208b961596f0053e2f87fa7e98a10268ee4f301534de1d88f","source":{"kind":"arxiv","id":"2210.04150","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04150","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04150v3","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04150","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"pith_short_12","alias_value":"N6BQEGEBRY76","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"pith_short_16","alias_value":"N6BQEGEBRY76ECFZ","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"pith_short_8","alias_value":"N6BQEGEB","created_at":"2026-07-05T05:56:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:N6BQEGEBRY76ECFZMFMW6ACT4L","target":"record","payload":{"canonical_record":{"source":{"id":"2210.04150","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-09T02:57:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ab5e61143bfc259f5649667d38bdc36db4845ebc76d4f28f7a57fd47ae138a0d","abstract_canon_sha256":"61aa96df243ab1dfa327f09a525430978b6ce1a7c54bbce94ee3464805499422"},"schema_version":"1.0"},"canonical_sha256":"6f830218818e3fe208b961596f0053e2f87fa7e98a10268ee4f301534de1d88f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:54.845042Z","signature_b64":"U1WZduw0Aba2f1/CI8gN2o9HnD8/WnsCrkLVsEJYRQPXcTPAqQ1qgGkdV8TNy7Fd0qhNsypXmdIyk0ORs15/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f830218818e3fe208b961596f0053e2f87fa7e98a10268ee4f301534de1d88f","last_reissued_at":"2026-07-05T05:56:54.844558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:54.844558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.04150","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:56:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DeOLZ37s6S8FCJEh7N+0RqXSxHBdUS2/v3B0jDhtCm50k2X4tiaDBJWOIMmf0av77A+dgYdrZblAZpkqrsZ6Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:55:23.771895Z"},"content_sha256":"7efca2c9cc24573574ff80864b5524a2868aa817f7a73169fff3aa4668bba163","schema_version":"1.0","event_id":"sha256:7efca2c9cc24573574ff80864b5524a2868aa817f7a73169fff3aa4668bba163"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:N6BQEGEBRY76ECFZMFMW6ACT4L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bichen Wu, Diana Marculescu, Feng Liang, Hang Zhang, Kunpeng Li, Peizhao Zhang, Peter Vajda, Xiaoliang Dai, Yinan Zhao","submitted_at":"2022-10-09T02:57:32Z","abstract_excerpt":"Open-vocabulary semantic segmentation aims to segment an image into semantic regions according to text descriptions, which may not have been seen during training. Recent two-stage methods first generate class-agnostic mask proposals and then leverage pre-trained vision-language models, e.g., CLIP, to classify masked regions. We identify the performance bottleneck of this paradigm to be the pre-trained CLIP model, since it does not perform well on masked images. To address this, we propose to finetune CLIP on a collection of masked image regions and their corresponding text descriptions. We col"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04150","kind":"arxiv","version":3},"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/2210.04150/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":"2026-07-05T05:56:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6tHcrpgtHMQFS8H9iQeZekhHCwlKzpGLYOTjuCHNFB37cVTyQHRcKlx62MHQM8isOlB8XrABtDUCzMQQBqLSAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:55:23.772408Z"},"content_sha256":"390b2caa4dc89771ae95ac99d91e21cd6c67d9ecd62988b91306eb715540fad6","schema_version":"1.0","event_id":"sha256:390b2caa4dc89771ae95ac99d91e21cd6c67d9ecd62988b91306eb715540fad6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N6BQEGEBRY76ECFZMFMW6ACT4L/bundle.json","state_url":"https://pith.science/pith/N6BQEGEBRY76ECFZMFMW6ACT4L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N6BQEGEBRY76ECFZMFMW6ACT4L/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":"2026-08-08T04:55:23Z","links":{"resolver":"https://pith.science/pith/N6BQEGEBRY76ECFZMFMW6ACT4L","bundle":"https://pith.science/pith/N6BQEGEBRY76ECFZMFMW6ACT4L/bundle.json","state":"https://pith.science/pith/N6BQEGEBRY76ECFZMFMW6ACT4L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N6BQEGEBRY76ECFZMFMW6ACT4L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:N6BQEGEBRY76ECFZMFMW6ACT4L","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":"61aa96df243ab1dfa327f09a525430978b6ce1a7c54bbce94ee3464805499422","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-09T02:57:32Z","title_canon_sha256":"ab5e61143bfc259f5649667d38bdc36db4845ebc76d4f28f7a57fd47ae138a0d"},"schema_version":"1.0","source":{"id":"2210.04150","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04150","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04150v3","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04150","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"pith_short_12","alias_value":"N6BQEGEBRY76","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"pith_short_16","alias_value":"N6BQEGEBRY76ECFZ","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"pith_short_8","alias_value":"N6BQEGEB","created_at":"2026-07-05T05:56:54Z"}],"graph_snapshots":[{"event_id":"sha256:390b2caa4dc89771ae95ac99d91e21cd6c67d9ecd62988b91306eb715540fad6","target":"graph","created_at":"2026-07-05T05:56:54Z","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/2210.04150/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-vocabulary semantic segmentation aims to segment an image into semantic regions according to text descriptions, which may not have been seen during training. Recent two-stage methods first generate class-agnostic mask proposals and then leverage pre-trained vision-language models, e.g., CLIP, to classify masked regions. We identify the performance bottleneck of this paradigm to be the pre-trained CLIP model, since it does not perform well on masked images. To address this, we propose to finetune CLIP on a collection of masked image regions and their corresponding text descriptions. We col","authors_text":"Bichen Wu, Diana Marculescu, Feng Liang, Hang Zhang, Kunpeng Li, Peizhao Zhang, Peter Vajda, Xiaoliang Dai, Yinan Zhao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-09T02:57:32Z","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04150","kind":"arxiv","version":3},"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":"sha256:7efca2c9cc24573574ff80864b5524a2868aa817f7a73169fff3aa4668bba163","target":"record","created_at":"2026-07-05T05:56:54Z","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":"61aa96df243ab1dfa327f09a525430978b6ce1a7c54bbce94ee3464805499422","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-09T02:57:32Z","title_canon_sha256":"ab5e61143bfc259f5649667d38bdc36db4845ebc76d4f28f7a57fd47ae138a0d"},"schema_version":"1.0","source":{"id":"2210.04150","kind":"arxiv","version":3}},"canonical_sha256":"6f830218818e3fe208b961596f0053e2f87fa7e98a10268ee4f301534de1d88f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f830218818e3fe208b961596f0053e2f87fa7e98a10268ee4f301534de1d88f","first_computed_at":"2026-07-05T05:56:54.844558Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:56:54.844558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U1WZduw0Aba2f1/CI8gN2o9HnD8/WnsCrkLVsEJYRQPXcTPAqQ1qgGkdV8TNy7Fd0qhNsypXmdIyk0ORs15/DA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:56:54.845042Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.04150","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7efca2c9cc24573574ff80864b5524a2868aa817f7a73169fff3aa4668bba163","sha256:390b2caa4dc89771ae95ac99d91e21cd6c67d9ecd62988b91306eb715540fad6"],"state_sha256":"a80cb9f97175a0c2619e50cebd31767a1f8e4a5d0e0fb61240376c317240048a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O6vv1P8wUHLltnlKIuT0B9S/bjsAcG2skm5TGBKAw/cW7LbtaktJe6oSH/jgeQnFZcLztkBU9LSd8vE9kncvCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:55:23.776733Z","bundle_sha256":"9542b88c86ddde6a04c1144e597e7910d779fd6fd0170acef6b1ca234fb0bbdc"}}