{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WRSHVJNTUMVVW66Q2GUXJORA5U","short_pith_number":"pith:WRSHVJNT","canonical_record":{"source":{"id":"2412.04533","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T17:42:37Z","cross_cats_sorted":[],"title_canon_sha256":"21cce572c7a531c838ec9dda94207ca4e8fe3c9799c4acf50b8e3e1c419d3841","abstract_canon_sha256":"a0ae306c61dcdb8eb53161a239275689628f8666daa0cf5bfed57fe09cd85082"},"schema_version":"1.0"},"canonical_sha256":"b4647aa5b3a32b5b7bd0d1a974ba20ed0e4fe94cf9048a88ee132cb6e57587c9","source":{"kind":"arxiv","id":"2412.04533","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04533","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04533v2","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04533","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"pith_short_12","alias_value":"WRSHVJNTUMVV","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"pith_short_16","alias_value":"WRSHVJNTUMVVW66Q","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"pith_short_8","alias_value":"WRSHVJNT","created_at":"2026-07-05T10:27:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WRSHVJNTUMVVW66Q2GUXJORA5U","target":"record","payload":{"canonical_record":{"source":{"id":"2412.04533","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T17:42:37Z","cross_cats_sorted":[],"title_canon_sha256":"21cce572c7a531c838ec9dda94207ca4e8fe3c9799c4acf50b8e3e1c419d3841","abstract_canon_sha256":"a0ae306c61dcdb8eb53161a239275689628f8666daa0cf5bfed57fe09cd85082"},"schema_version":"1.0"},"canonical_sha256":"b4647aa5b3a32b5b7bd0d1a974ba20ed0e4fe94cf9048a88ee132cb6e57587c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:21.193841Z","signature_b64":"v9wHV88hEAQuplcAk4a9uC+tgA45PRB5E3cAFNb2acEP3Gt/mBoAFUXgdZjA7gOWoyAzbHDeqLdcq6746+tFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4647aa5b3a32b5b7bd0d1a974ba20ed0e4fe94cf9048a88ee132cb6e57587c9","last_reissued_at":"2026-07-05T10:27:21.192950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:21.192950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.04533","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":"2026-07-05T10:27:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XbNIq9FkCGreGm/CWFAGNizan6IGDR4ISgueunRCwtKwrH+h28c17r9zSyxptcqvudOFXz5eOtZbnK/qWt8mBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:16:34.788044Z"},"content_sha256":"f77df118e8a30e4ca60afdfceda1ee3332c25d2da90252eebad1f282252f4e61","schema_version":"1.0","event_id":"sha256:f77df118e8a30e4ca60afdfceda1ee3332c25d2da90252eebad1f282252f4e61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WRSHVJNTUMVVW66Q2GUXJORA5U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Feng, Tianheng Cheng, Wenyu Liu, Xinggang Wang, Yongkang Li","submitted_at":"2024-12-05T17:42:37Z","abstract_excerpt":"Recent open-vocabulary segmentation methods adopt mask generators to predict segmentation masks and leverage pre-trained vision-language models, e.g., CLIP, to classify these masks via mask pooling. Although these approaches show promising results, it is counterintuitive that accurate masks often fail to yield accurate classification results through pooling CLIP image embeddings within the mask regions. In this paper, we reveal the performance limitations of mask pooling and introduce Mask-Adapter, a simple yet effective method to address these challenges in open-vocabulary segmentation. Compa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04533","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/2412.04533/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":"2026-07-05T10:27:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ek2+XT/o3o8zICxzgDZeKuGW4awAvrGLUIzHrWn1ZGflNg9eGZJ5B1gShu9fVIqDicte3rIpQvBwahKzrBrlCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:16:34.788969Z"},"content_sha256":"fb99f865ca869f1dc58b3a29575adced423c2c1111f034fcc0165d1c23298ea1","schema_version":"1.0","event_id":"sha256:fb99f865ca869f1dc58b3a29575adced423c2c1111f034fcc0165d1c23298ea1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WRSHVJNTUMVVW66Q2GUXJORA5U/bundle.json","state_url":"https://pith.science/pith/WRSHVJNTUMVVW66Q2GUXJORA5U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WRSHVJNTUMVVW66Q2GUXJORA5U/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":"2026-08-10T10:16:34Z","links":{"resolver":"https://pith.science/pith/WRSHVJNTUMVVW66Q2GUXJORA5U","bundle":"https://pith.science/pith/WRSHVJNTUMVVW66Q2GUXJORA5U/bundle.json","state":"https://pith.science/pith/WRSHVJNTUMVVW66Q2GUXJORA5U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WRSHVJNTUMVVW66Q2GUXJORA5U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WRSHVJNTUMVVW66Q2GUXJORA5U","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":"a0ae306c61dcdb8eb53161a239275689628f8666daa0cf5bfed57fe09cd85082","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T17:42:37Z","title_canon_sha256":"21cce572c7a531c838ec9dda94207ca4e8fe3c9799c4acf50b8e3e1c419d3841"},"schema_version":"1.0","source":{"id":"2412.04533","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04533","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04533v2","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04533","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"pith_short_12","alias_value":"WRSHVJNTUMVV","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"pith_short_16","alias_value":"WRSHVJNTUMVVW66Q","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"pith_short_8","alias_value":"WRSHVJNT","created_at":"2026-07-05T10:27:21Z"}],"graph_snapshots":[{"event_id":"sha256:fb99f865ca869f1dc58b3a29575adced423c2c1111f034fcc0165d1c23298ea1","target":"graph","created_at":"2026-07-05T10:27:21Z","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/2412.04533/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent open-vocabulary segmentation methods adopt mask generators to predict segmentation masks and leverage pre-trained vision-language models, e.g., CLIP, to classify these masks via mask pooling. Although these approaches show promising results, it is counterintuitive that accurate masks often fail to yield accurate classification results through pooling CLIP image embeddings within the mask regions. In this paper, we reveal the performance limitations of mask pooling and introduce Mask-Adapter, a simple yet effective method to address these challenges in open-vocabulary segmentation. Compa","authors_text":"Bin Feng, Tianheng Cheng, Wenyu Liu, Xinggang Wang, Yongkang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T17:42:37Z","title":"Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04533","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:f77df118e8a30e4ca60afdfceda1ee3332c25d2da90252eebad1f282252f4e61","target":"record","created_at":"2026-07-05T10:27:21Z","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":"a0ae306c61dcdb8eb53161a239275689628f8666daa0cf5bfed57fe09cd85082","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T17:42:37Z","title_canon_sha256":"21cce572c7a531c838ec9dda94207ca4e8fe3c9799c4acf50b8e3e1c419d3841"},"schema_version":"1.0","source":{"id":"2412.04533","kind":"arxiv","version":2}},"canonical_sha256":"b4647aa5b3a32b5b7bd0d1a974ba20ed0e4fe94cf9048a88ee132cb6e57587c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4647aa5b3a32b5b7bd0d1a974ba20ed0e4fe94cf9048a88ee132cb6e57587c9","first_computed_at":"2026-07-05T10:27:21.192950Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:21.192950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v9wHV88hEAQuplcAk4a9uC+tgA45PRB5E3cAFNb2acEP3Gt/mBoAFUXgdZjA7gOWoyAzbHDeqLdcq6746+tFCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:21.193841Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04533","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f77df118e8a30e4ca60afdfceda1ee3332c25d2da90252eebad1f282252f4e61","sha256:fb99f865ca869f1dc58b3a29575adced423c2c1111f034fcc0165d1c23298ea1"],"state_sha256":"faaa4f0e7651458fcd609e6ed282c70d48c2a35d5f077b6985cf615e6f97bb0a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+W8EIiALDBYVDp1DWwLQO7wnkK4fhAVFVA/zDA3dAVG9Yd0p8JQjWCu170JW44Nj21wMOrBBnHUyCSbvpXmsAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T10:16:34.798985Z","bundle_sha256":"162c37b3dfb767bdc645e96886f42471e317cddd5623ec5f78b5328ade13731c"}}