{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JXILNYDPMT7SLCUSYNDRJL2SP6","short_pith_number":"pith:JXILNYDP","canonical_record":{"source":{"id":"2408.04883","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-09T06:17:00Z","cross_cats_sorted":[],"title_canon_sha256":"255a4ba763eca6b76167817d1c34334f0fb0feb1d4168d89ee244fb339582e59","abstract_canon_sha256":"6604def60554392150e51bf3ca6a4bd2dce1456480985c57f76dbd53539dffa4"},"schema_version":"1.0"},"canonical_sha256":"4dd0b6e06f64ff258a92c34714af527fa02a2e734a6a75e1ea9e999f0297f461","source":{"kind":"arxiv","id":"2408.04883","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04883","created_at":"2026-07-05T08:53:45Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04883v1","created_at":"2026-07-05T08:53:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04883","created_at":"2026-07-05T08:53:45Z"},{"alias_kind":"pith_short_12","alias_value":"JXILNYDPMT7S","created_at":"2026-07-05T08:53:45Z"},{"alias_kind":"pith_short_16","alias_value":"JXILNYDPMT7SLCUS","created_at":"2026-07-05T08:53:45Z"},{"alias_kind":"pith_short_8","alias_value":"JXILNYDP","created_at":"2026-07-05T08:53:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JXILNYDPMT7SLCUSYNDRJL2SP6","target":"record","payload":{"canonical_record":{"source":{"id":"2408.04883","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-09T06:17:00Z","cross_cats_sorted":[],"title_canon_sha256":"255a4ba763eca6b76167817d1c34334f0fb0feb1d4168d89ee244fb339582e59","abstract_canon_sha256":"6604def60554392150e51bf3ca6a4bd2dce1456480985c57f76dbd53539dffa4"},"schema_version":"1.0"},"canonical_sha256":"4dd0b6e06f64ff258a92c34714af527fa02a2e734a6a75e1ea9e999f0297f461","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:45.391590Z","signature_b64":"O3fgfFbEq69spM0D3MUbSktZmNtkT704wktU7UkDlVLerB7rrZ7t9d2X6KCzczoyV+SyV71/tovxGWTtBD+ACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4dd0b6e06f64ff258a92c34714af527fa02a2e734a6a75e1ea9e999f0297f461","last_reissued_at":"2026-07-05T08:53:45.391107Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:45.391107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.04883","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":"2026-07-05T08:53:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"geQmj5c81O2v/mzYeuW1HWCd/Zw3dwDYAYnq93fk4zXr+Pg7OBI191zkqaCynMsHHmSaGaqWQMIiGmwpeTIjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:40:45.159204Z"},"content_sha256":"ed3f8a2306f7cfae26f3fa5da6cfb885bb27923c302e590378a448fae59d53db","schema_version":"1.0","event_id":"sha256:ed3f8a2306f7cfae26f3fa5da6cfb885bb27923c302e590378a448fae59d53db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JXILNYDPMT7SLCUSYNDRJL2SP6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaofeng Chen, Litong Feng, Mengcheng Lan, Wayne Zhang, Xinjiang Wang, Yiping Ke","submitted_at":"2024-08-09T06:17:00Z","abstract_excerpt":"Open-vocabulary semantic segmentation requires models to effectively integrate visual representations with open-vocabulary semantic labels. While Contrastive Language-Image Pre-training (CLIP) models shine in recognizing visual concepts from text, they often struggle with segment coherence due to their limited localization ability. In contrast, Vision Foundation Models (VFMs) excel at acquiring spatially consistent local visual representations, yet they fall short in semantic understanding. This paper introduces ProxyCLIP, an innovative framework designed to harmonize the strengths of both CLI"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04883","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/2408.04883/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":"2026-07-05T08:53:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6r17rdNOna/XVHgosZE7eDBTFTxo4kYSSAwyq3yzIrlF8gV8B2gyBxR0Bhmw352CBynHQzPrwmKOZjepSg/fBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:40:45.160284Z"},"content_sha256":"3976665e11557c816f87e9c502495dc106003a89559ec45ab5f1072ff64b05d8","schema_version":"1.0","event_id":"sha256:3976665e11557c816f87e9c502495dc106003a89559ec45ab5f1072ff64b05d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JXILNYDPMT7SLCUSYNDRJL2SP6/bundle.json","state_url":"https://pith.science/pith/JXILNYDPMT7SLCUSYNDRJL2SP6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JXILNYDPMT7SLCUSYNDRJL2SP6/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":"2026-08-06T03:40:45Z","links":{"resolver":"https://pith.science/pith/JXILNYDPMT7SLCUSYNDRJL2SP6","bundle":"https://pith.science/pith/JXILNYDPMT7SLCUSYNDRJL2SP6/bundle.json","state":"https://pith.science/pith/JXILNYDPMT7SLCUSYNDRJL2SP6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JXILNYDPMT7SLCUSYNDRJL2SP6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JXILNYDPMT7SLCUSYNDRJL2SP6","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":"6604def60554392150e51bf3ca6a4bd2dce1456480985c57f76dbd53539dffa4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-09T06:17:00Z","title_canon_sha256":"255a4ba763eca6b76167817d1c34334f0fb0feb1d4168d89ee244fb339582e59"},"schema_version":"1.0","source":{"id":"2408.04883","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04883","created_at":"2026-07-05T08:53:45Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04883v1","created_at":"2026-07-05T08:53:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04883","created_at":"2026-07-05T08:53:45Z"},{"alias_kind":"pith_short_12","alias_value":"JXILNYDPMT7S","created_at":"2026-07-05T08:53:45Z"},{"alias_kind":"pith_short_16","alias_value":"JXILNYDPMT7SLCUS","created_at":"2026-07-05T08:53:45Z"},{"alias_kind":"pith_short_8","alias_value":"JXILNYDP","created_at":"2026-07-05T08:53:45Z"}],"graph_snapshots":[{"event_id":"sha256:3976665e11557c816f87e9c502495dc106003a89559ec45ab5f1072ff64b05d8","target":"graph","created_at":"2026-07-05T08:53:45Z","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/2408.04883/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-vocabulary semantic segmentation requires models to effectively integrate visual representations with open-vocabulary semantic labels. While Contrastive Language-Image Pre-training (CLIP) models shine in recognizing visual concepts from text, they often struggle with segment coherence due to their limited localization ability. In contrast, Vision Foundation Models (VFMs) excel at acquiring spatially consistent local visual representations, yet they fall short in semantic understanding. This paper introduces ProxyCLIP, an innovative framework designed to harmonize the strengths of both CLI","authors_text":"Chaofeng Chen, Litong Feng, Mengcheng Lan, Wayne Zhang, Xinjiang Wang, Yiping Ke","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-09T06:17:00Z","title":"ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04883","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:ed3f8a2306f7cfae26f3fa5da6cfb885bb27923c302e590378a448fae59d53db","target":"record","created_at":"2026-07-05T08:53:45Z","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":"6604def60554392150e51bf3ca6a4bd2dce1456480985c57f76dbd53539dffa4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-09T06:17:00Z","title_canon_sha256":"255a4ba763eca6b76167817d1c34334f0fb0feb1d4168d89ee244fb339582e59"},"schema_version":"1.0","source":{"id":"2408.04883","kind":"arxiv","version":1}},"canonical_sha256":"4dd0b6e06f64ff258a92c34714af527fa02a2e734a6a75e1ea9e999f0297f461","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4dd0b6e06f64ff258a92c34714af527fa02a2e734a6a75e1ea9e999f0297f461","first_computed_at":"2026-07-05T08:53:45.391107Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:45.391107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O3fgfFbEq69spM0D3MUbSktZmNtkT704wktU7UkDlVLerB7rrZ7t9d2X6KCzczoyV+SyV71/tovxGWTtBD+ACw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:45.391590Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.04883","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed3f8a2306f7cfae26f3fa5da6cfb885bb27923c302e590378a448fae59d53db","sha256:3976665e11557c816f87e9c502495dc106003a89559ec45ab5f1072ff64b05d8"],"state_sha256":"ecb4b154efaaead10136650f9c86ab272cf0142371e096d8378fcb6713d6b93c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MRTB+EhRr2XDGjXewG2gtuOhLuIGRQA4wHIC7AIQFWFsw7MwTw+/+NtkDe+QH3L2bYVweVg7rs2fqeyXs2X9Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:40:45.165996Z","bundle_sha256":"b0342529948432b48916b322619783ae6649fb000499d651b78d6117e696caae"}}