{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JMVO3B7OQRRV366NRHZQJPSUQB","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":"f3c7624a82c0353b83f38c471d89e19c88b082c2a30880ef698c157a5a7f46a7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-14T06:31:20Z","title_canon_sha256":"db84d2be585c7ce6bf835423edf6276e214e55964b284db43c51d000bf68f2f0"},"schema_version":"1.0","source":{"id":"2411.09219","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.09219","created_at":"2026-07-05T09:35:22Z"},{"alias_kind":"arxiv_version","alias_value":"2411.09219v1","created_at":"2026-07-05T09:35:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09219","created_at":"2026-07-05T09:35:22Z"},{"alias_kind":"pith_short_12","alias_value":"JMVO3B7OQRRV","created_at":"2026-07-05T09:35:22Z"},{"alias_kind":"pith_short_16","alias_value":"JMVO3B7OQRRV366N","created_at":"2026-07-05T09:35:22Z"},{"alias_kind":"pith_short_8","alias_value":"JMVO3B7O","created_at":"2026-07-05T09:35:22Z"}],"graph_snapshots":[{"event_id":"sha256:0c588a017b69e9de4e49f18f140a4f4965e693486764c83b94bb2be29e1c7030","target":"graph","created_at":"2026-07-05T09:35:22Z","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/2411.09219/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Contrastive Language-Image Pre-training (CLIP) has advanced open-vocabulary predictions, its performance on semantic segmentation remains suboptimal. This shortfall primarily stems from its spatial-invariant semantic features and constrained resolution. While previous adaptations addressed spatial invariance semantic by modifying the self-attention in CLIP's image encoder, the issue of limited resolution remains unexplored. Different from previous segment-then-splice methods that segment sub-images via a sliding window and splice the results, we introduce a splice-then-segment paradigm t","authors_text":"Chang Xu, Minjing Dong, Yuheng Shi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-14T06:31:20Z","title":"Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09219","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:f2f6c18549fd6ca519cc2e19272846869680e7c9746dd3c275f6d2c4db8fb54f","target":"record","created_at":"2026-07-05T09:35:22Z","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":"f3c7624a82c0353b83f38c471d89e19c88b082c2a30880ef698c157a5a7f46a7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-14T06:31:20Z","title_canon_sha256":"db84d2be585c7ce6bf835423edf6276e214e55964b284db43c51d000bf68f2f0"},"schema_version":"1.0","source":{"id":"2411.09219","kind":"arxiv","version":1}},"canonical_sha256":"4b2aed87ee84635dfbcd89f304be548060931646219d8872200f27a86895d631","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b2aed87ee84635dfbcd89f304be548060931646219d8872200f27a86895d631","first_computed_at":"2026-07-05T09:35:22.719603Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:22.719603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T4fesQls+YNKkDREj+r0uX95QLH9aSD/m7/cNKGUlHsy0i6+p1Dntem6071JDssTyvS0Pwd+0yBtNPd2rQgfCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:22.720090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.09219","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2f6c18549fd6ca519cc2e19272846869680e7c9746dd3c275f6d2c4db8fb54f","sha256:0c588a017b69e9de4e49f18f140a4f4965e693486764c83b94bb2be29e1c7030"],"state_sha256":"9046a2d1c1d50fe7dc109f3f2c0c32d95ecd0769eb63739f8963c20dae4e2355"}