{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JMVO3B7OQRRV366NRHZQJPSUQB","short_pith_number":"pith:JMVO3B7O","canonical_record":{"source":{"id":"2411.09219","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-14T06:31:20Z","cross_cats_sorted":[],"title_canon_sha256":"db84d2be585c7ce6bf835423edf6276e214e55964b284db43c51d000bf68f2f0","abstract_canon_sha256":"f3c7624a82c0353b83f38c471d89e19c88b082c2a30880ef698c157a5a7f46a7"},"schema_version":"1.0"},"canonical_sha256":"4b2aed87ee84635dfbcd89f304be548060931646219d8872200f27a86895d631","source":{"kind":"arxiv","id":"2411.09219","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JMVO3B7OQRRV366NRHZQJPSUQB","target":"record","payload":{"canonical_record":{"source":{"id":"2411.09219","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-14T06:31:20Z","cross_cats_sorted":[],"title_canon_sha256":"db84d2be585c7ce6bf835423edf6276e214e55964b284db43c51d000bf68f2f0","abstract_canon_sha256":"f3c7624a82c0353b83f38c471d89e19c88b082c2a30880ef698c157a5a7f46a7"},"schema_version":"1.0"},"canonical_sha256":"4b2aed87ee84635dfbcd89f304be548060931646219d8872200f27a86895d631","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:22.720090Z","signature_b64":"T4fesQls+YNKkDREj+r0uX95QLH9aSD/m7/cNKGUlHsy0i6+p1Dntem6071JDssTyvS0Pwd+0yBtNPd2rQgfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b2aed87ee84635dfbcd89f304be548060931646219d8872200f27a86895d631","last_reissued_at":"2026-07-05T09:35:22.719603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:22.719603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.09219","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":"2026-07-05T09:35:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ppwO2HMYZ+7jesOXClvqe7Z/Odpeb9oURB227KU+MzDc2RUQVQxjeTl1Cjep4dnERZLamZB8NnEVYfMNiAzNCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:18:22.220659Z"},"content_sha256":"f2f6c18549fd6ca519cc2e19272846869680e7c9746dd3c275f6d2c4db8fb54f","schema_version":"1.0","event_id":"sha256:f2f6c18549fd6ca519cc2e19272846869680e7c9746dd3c275f6d2c4db8fb54f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JMVO3B7OQRRV366NRHZQJPSUQB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Xu, Minjing Dong, Yuheng Shi","submitted_at":"2024-11-14T06:31:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09219","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/2411.09219/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":"2026-07-05T09:35:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lKjoTVHVq34thV4Sccdl72Ew1gWQZTd5LJKhIUlgC5PZYbSmTf2SQ2wrg0GhHP7aAFBUMSp6iasSfq1DmVCYCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:18:22.221170Z"},"content_sha256":"0c588a017b69e9de4e49f18f140a4f4965e693486764c83b94bb2be29e1c7030","schema_version":"1.0","event_id":"sha256:0c588a017b69e9de4e49f18f140a4f4965e693486764c83b94bb2be29e1c7030"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JMVO3B7OQRRV366NRHZQJPSUQB/bundle.json","state_url":"https://pith.science/pith/JMVO3B7OQRRV366NRHZQJPSUQB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JMVO3B7OQRRV366NRHZQJPSUQB/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":"2026-08-05T12:18:22Z","links":{"resolver":"https://pith.science/pith/JMVO3B7OQRRV366NRHZQJPSUQB","bundle":"https://pith.science/pith/JMVO3B7OQRRV366NRHZQJPSUQB/bundle.json","state":"https://pith.science/pith/JMVO3B7OQRRV366NRHZQJPSUQB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JMVO3B7OQRRV366NRHZQJPSUQB/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IFOh6v/a5b1SQ+D7oGavQJqCmd5lnhTMABLLBmkgrEcnARao+kJiNsnSSR1Bk3d7MxchB34yI8aUFZsQjajdDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T12:18:22.225121Z","bundle_sha256":"39f3ea27708c61f99cc15ec19f759c0d668bec75b9d0ff9c9df4c5057f94e001"}}