{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G52JPDTG3FSCJKZXOBZ6O7KGF6","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":"24d4d4aee2707841fe9d004ec6829db116b28c09299503a44b40e8e6923d08a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T01:13:03Z","title_canon_sha256":"dfc5c8431c4c45bf55b5433c294efd821ec9dba08818568d9e5fff0348bdfa05"},"schema_version":"1.0","source":{"id":"2409.19846","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19846","created_at":"2026-07-05T09:13:23Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19846v1","created_at":"2026-07-05T09:13:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19846","created_at":"2026-07-05T09:13:23Z"},{"alias_kind":"pith_short_12","alias_value":"G52JPDTG3FSC","created_at":"2026-07-05T09:13:23Z"},{"alias_kind":"pith_short_16","alias_value":"G52JPDTG3FSCJKZX","created_at":"2026-07-05T09:13:23Z"},{"alias_kind":"pith_short_8","alias_value":"G52JPDTG","created_at":"2026-07-05T09:13:23Z"}],"graph_snapshots":[{"event_id":"sha256:3a39525b495fb0d2e67b9af4eb3cc7e91b09430f7c6195b5939929de6d1a8fa2","target":"graph","created_at":"2026-07-05T09:13:23Z","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/2409.19846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale vision-language models like CLIP have demonstrated impressive open-vocabulary capabilities for image-level tasks, excelling in recognizing what objects are present. However, they struggle with pixel-level recognition tasks like semantic segmentation, which additionally require understanding where the objects are located. In this work, we propose a novel method, PixelCLIP, to adapt the CLIP image encoder for pixel-level understanding by guiding the model on where, which is achieved using unlabeled images and masks generated from vision foundation models such as SAM and DINO. To addr","authors_text":"Anurag Arnab, Chaehyun Kim, Heeseong Shin, Paul Hongsuck Seo, Seokju Cho, Seungryong Kim, Sunghwan Hong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T01:13:03Z","title":"Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19846","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":"sha256:983fa3feb9c447b683c253027239df6bf5c632db240c588f630253a222f6457a","target":"record","created_at":"2026-07-05T09:13:23Z","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":"24d4d4aee2707841fe9d004ec6829db116b28c09299503a44b40e8e6923d08a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T01:13:03Z","title_canon_sha256":"dfc5c8431c4c45bf55b5433c294efd821ec9dba08818568d9e5fff0348bdfa05"},"schema_version":"1.0","source":{"id":"2409.19846","kind":"arxiv","version":1}},"canonical_sha256":"3774978e66d96424ab377073e77d462f9ca3eedb67c659f2f3dd941bb8de74b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3774978e66d96424ab377073e77d462f9ca3eedb67c659f2f3dd941bb8de74b2","first_computed_at":"2026-07-05T09:13:23.691097Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:23.691097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9nqtRX9qomqS3UfzNYbdGi7Iw862+yQoYcrO22WiqQKTB+eSp0FcEawjL3g0VJhsVkXZaA5tQqEccaSNK9JqBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:23.691608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.19846","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:983fa3feb9c447b683c253027239df6bf5c632db240c588f630253a222f6457a","sha256:3a39525b495fb0d2e67b9af4eb3cc7e91b09430f7c6195b5939929de6d1a8fa2"],"state_sha256":"08cae868de75735a216d26a5cbeff56bc06fa278d4542921852cc2799a2aa796"}