{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ERVMKQG55XA26LKSVIOKMA4NJL","short_pith_number":"pith:ERVMKQG5","canonical_record":{"source":{"id":"2412.19650","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T13:55:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a0fc6d9cf252111c77e2ae50b6eda87a90a6cbeb0ed97bd80cd4390bcf7e5544","abstract_canon_sha256":"420b08a32149f8343ac803ef6c8b7cf842906e8412d57688381f5e4de1ce6cdd"},"schema_version":"1.0"},"canonical_sha256":"246ac540ddedc1af2d52aa1ca6038d4adfd99ac98d7ba9fdae277a2f811095a9","source":{"kind":"arxiv","id":"2412.19650","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19650","created_at":"2026-07-05T09:54:39Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19650v1","created_at":"2026-07-05T09:54:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19650","created_at":"2026-07-05T09:54:39Z"},{"alias_kind":"pith_short_12","alias_value":"ERVMKQG55XA2","created_at":"2026-07-05T09:54:39Z"},{"alias_kind":"pith_short_16","alias_value":"ERVMKQG55XA26LKS","created_at":"2026-07-05T09:54:39Z"},{"alias_kind":"pith_short_8","alias_value":"ERVMKQG5","created_at":"2026-07-05T09:54:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ERVMKQG55XA26LKSVIOKMA4NJL","target":"record","payload":{"canonical_record":{"source":{"id":"2412.19650","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T13:55:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a0fc6d9cf252111c77e2ae50b6eda87a90a6cbeb0ed97bd80cd4390bcf7e5544","abstract_canon_sha256":"420b08a32149f8343ac803ef6c8b7cf842906e8412d57688381f5e4de1ce6cdd"},"schema_version":"1.0"},"canonical_sha256":"246ac540ddedc1af2d52aa1ca6038d4adfd99ac98d7ba9fdae277a2f811095a9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:39.234750Z","signature_b64":"GMIh8d7R1NCSgkudWuDmo0OA3vyfhpmJAUimNH4f5kDnb9v9vnmivXsxVm84vDT2l6HvUj/fbSNoPlIH6MIICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"246ac540ddedc1af2d52aa1ca6038d4adfd99ac98d7ba9fdae277a2f811095a9","last_reissued_at":"2026-07-05T09:54:39.234339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:39.234339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.19650","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":"2026-07-05T09:54:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h3bLFTd3wHfzcSxwGPlHOGQNcukhOPFAfsQ5ucyrbfhWuCjIABYJfRIvIV/tTgL8bWbt1mqspwWH2bcJqI4lCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T05:03:03.015949Z"},"content_sha256":"f3df42037b71ea008d53bf8c2f1b9301d6afe4de221d62d5dc7070ab7d2377f4","schema_version":"1.0","event_id":"sha256:f3df42037b71ea008d53bf8c2f1b9301d6afe4de221d62d5dc7070ab7d2377f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ERVMKQG55XA26LKSVIOKMA4NJL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Toward Modality Gap: Vision Prototype Learning for Weakly-supervised Semantic Segmentation with CLIP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Feilong Tang, Ge Zhang, Jionglong Su, Yingxue Su, Zhe Chen, Zhiyi Zhao, Zhongxing Xu, Zongyuan Ge","submitted_at":"2024-12-27T13:55:11Z","abstract_excerpt":"The application of Contrastive Language-Image Pre-training (CLIP) in Weakly Supervised Semantic Segmentation (WSSS) research powerful cross-modal semantic understanding capabilities. Existing methods attempt to optimize input text prompts for improved alignment of images and text, by finely adjusting text prototypes to facilitate semantic matching. Nevertheless, given the modality gap between text and vision spaces, the text prototypes employed by these methods have not effectively established a close correspondence with pixel-level vision features. In this work, our theoretical analysis indic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19650","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/2412.19650/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":"2026-07-05T09:54:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UwMwqhXOMoFMN4q+QkjQUlM4xQPE/rvqdFHoaSIOCumNT2ADGiLCmULTM/2xWgwY1Jh329FdY1iRcIQRJosmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T05:03:03.017036Z"},"content_sha256":"68ad16a883073b3e7c524dbf80f58b8beb43fd2a03e44f0918a4602ee2a7bfba","schema_version":"1.0","event_id":"sha256:68ad16a883073b3e7c524dbf80f58b8beb43fd2a03e44f0918a4602ee2a7bfba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ERVMKQG55XA26LKSVIOKMA4NJL/bundle.json","state_url":"https://pith.science/pith/ERVMKQG55XA26LKSVIOKMA4NJL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ERVMKQG55XA26LKSVIOKMA4NJL/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":"2026-08-12T05:03:03Z","links":{"resolver":"https://pith.science/pith/ERVMKQG55XA26LKSVIOKMA4NJL","bundle":"https://pith.science/pith/ERVMKQG55XA26LKSVIOKMA4NJL/bundle.json","state":"https://pith.science/pith/ERVMKQG55XA26LKSVIOKMA4NJL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ERVMKQG55XA26LKSVIOKMA4NJL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ERVMKQG55XA26LKSVIOKMA4NJL","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":"420b08a32149f8343ac803ef6c8b7cf842906e8412d57688381f5e4de1ce6cdd","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T13:55:11Z","title_canon_sha256":"a0fc6d9cf252111c77e2ae50b6eda87a90a6cbeb0ed97bd80cd4390bcf7e5544"},"schema_version":"1.0","source":{"id":"2412.19650","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19650","created_at":"2026-07-05T09:54:39Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19650v1","created_at":"2026-07-05T09:54:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19650","created_at":"2026-07-05T09:54:39Z"},{"alias_kind":"pith_short_12","alias_value":"ERVMKQG55XA2","created_at":"2026-07-05T09:54:39Z"},{"alias_kind":"pith_short_16","alias_value":"ERVMKQG55XA26LKS","created_at":"2026-07-05T09:54:39Z"},{"alias_kind":"pith_short_8","alias_value":"ERVMKQG5","created_at":"2026-07-05T09:54:39Z"}],"graph_snapshots":[{"event_id":"sha256:68ad16a883073b3e7c524dbf80f58b8beb43fd2a03e44f0918a4602ee2a7bfba","target":"graph","created_at":"2026-07-05T09:54:39Z","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/2412.19650/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The application of Contrastive Language-Image Pre-training (CLIP) in Weakly Supervised Semantic Segmentation (WSSS) research powerful cross-modal semantic understanding capabilities. Existing methods attempt to optimize input text prompts for improved alignment of images and text, by finely adjusting text prototypes to facilitate semantic matching. Nevertheless, given the modality gap between text and vision spaces, the text prototypes employed by these methods have not effectively established a close correspondence with pixel-level vision features. In this work, our theoretical analysis indic","authors_text":"Feilong Tang, Ge Zhang, Jionglong Su, Yingxue Su, Zhe Chen, Zhiyi Zhao, Zhongxing Xu, Zongyuan Ge","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T13:55:11Z","title":"Toward Modality Gap: Vision Prototype Learning for Weakly-supervised Semantic Segmentation with CLIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19650","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:f3df42037b71ea008d53bf8c2f1b9301d6afe4de221d62d5dc7070ab7d2377f4","target":"record","created_at":"2026-07-05T09:54:39Z","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":"420b08a32149f8343ac803ef6c8b7cf842906e8412d57688381f5e4de1ce6cdd","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T13:55:11Z","title_canon_sha256":"a0fc6d9cf252111c77e2ae50b6eda87a90a6cbeb0ed97bd80cd4390bcf7e5544"},"schema_version":"1.0","source":{"id":"2412.19650","kind":"arxiv","version":1}},"canonical_sha256":"246ac540ddedc1af2d52aa1ca6038d4adfd99ac98d7ba9fdae277a2f811095a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"246ac540ddedc1af2d52aa1ca6038d4adfd99ac98d7ba9fdae277a2f811095a9","first_computed_at":"2026-07-05T09:54:39.234339Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:39.234339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GMIh8d7R1NCSgkudWuDmo0OA3vyfhpmJAUimNH4f5kDnb9v9vnmivXsxVm84vDT2l6HvUj/fbSNoPlIH6MIICg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:39.234750Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19650","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3df42037b71ea008d53bf8c2f1b9301d6afe4de221d62d5dc7070ab7d2377f4","sha256:68ad16a883073b3e7c524dbf80f58b8beb43fd2a03e44f0918a4602ee2a7bfba"],"state_sha256":"73c0828d3ad284213f5c751e41d7785af07b235704e0fb3796090d922534d974"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ojQza1vlGkodRG4byCYJaRcaO3p30+/DwqIzPqU+Kqk7WBkdop1zT9HEmvs+L8S0H68rpZKQJTwN3WfMITHyDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T05:03:03.026640Z","bundle_sha256":"ff16339cfeb2543d1d6d4ad00f7c40da400fa4f8539b3301edd02dd7d124a138"}}