{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ESHBGX3SKBIN64CZMJ4ZRL7THH","short_pith_number":"pith:ESHBGX3S","schema_version":"1.0","canonical_sha256":"248e135f725050df7059627998aff339d574efd33ab13e8122643366b00127a7","source":{"kind":"arxiv","id":"2505.22209","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Training-free Open-Vocabulary Semantic Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ivan Martinovi\\'c, Naomi Kombol, Sini\\v{s}a \\v{S}egvi\\'c","submitted_at":"2025-05-28T10:37:52Z","abstract_excerpt":"Semantic segmentation is one of the most fundamental tasks in image understanding with a long history of research, and subsequently a myriad of different approaches. Traditional methods strive to train models up from scratch, requiring vast amounts of computational resources and training data. In the advent of moving to open-vocabulary semantic segmentation, which asks models to classify beyond learned categories, large quantities of finely annotated data would be prohibitively expensive. Researchers have instead turned to training-free methods where they leverage existing models made for task"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.22209","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T10:37:52Z","cross_cats_sorted":[],"title_canon_sha256":"3aaaf4667e031cce0cd03b9ebb87eff04bf843d6dac1d71bfb5d304f3d838088","abstract_canon_sha256":"fbeac99f2161b8ec37780105b938fb1310f6f1109112d73adf1ffb47c0ad560c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:11.471420Z","signature_b64":"/wP33EBHFEoNwqIci2lXZIMUa/0ieM6Pd7dCq40pfbk1Q3AAiQebj/DLDjrjla6wgNpKKePGoLgVEtM0kAkxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"248e135f725050df7059627998aff339d574efd33ab13e8122643366b00127a7","last_reissued_at":"2026-07-05T11:11:11.470931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:11.470931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Training-free Open-Vocabulary Semantic Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ivan Martinovi\\'c, Naomi Kombol, Sini\\v{s}a \\v{S}egvi\\'c","submitted_at":"2025-05-28T10:37:52Z","abstract_excerpt":"Semantic segmentation is one of the most fundamental tasks in image understanding with a long history of research, and subsequently a myriad of different approaches. Traditional methods strive to train models up from scratch, requiring vast amounts of computational resources and training data. In the advent of moving to open-vocabulary semantic segmentation, which asks models to classify beyond learned categories, large quantities of finely annotated data would be prohibitively expensive. Researchers have instead turned to training-free methods where they leverage existing models made for task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22209","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/2505.22209/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.22209","created_at":"2026-07-05T11:11:11.470988+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22209v1","created_at":"2026-07-05T11:11:11.470988+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22209","created_at":"2026-07-05T11:11:11.470988+00:00"},{"alias_kind":"pith_short_12","alias_value":"ESHBGX3SKBIN","created_at":"2026-07-05T11:11:11.470988+00:00"},{"alias_kind":"pith_short_16","alias_value":"ESHBGX3SKBIN64CZ","created_at":"2026-07-05T11:11:11.470988+00:00"},{"alias_kind":"pith_short_8","alias_value":"ESHBGX3S","created_at":"2026-07-05T11:11:11.470988+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ESHBGX3SKBIN64CZMJ4ZRL7THH","json":"https://pith.science/pith/ESHBGX3SKBIN64CZMJ4ZRL7THH.json","graph_json":"https://pith.science/api/pith-number/ESHBGX3SKBIN64CZMJ4ZRL7THH/graph.json","events_json":"https://pith.science/api/pith-number/ESHBGX3SKBIN64CZMJ4ZRL7THH/events.json","paper":"https://pith.science/paper/ESHBGX3S"},"agent_actions":{"view_html":"https://pith.science/pith/ESHBGX3SKBIN64CZMJ4ZRL7THH","download_json":"https://pith.science/pith/ESHBGX3SKBIN64CZMJ4ZRL7THH.json","view_paper":"https://pith.science/paper/ESHBGX3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22209&json=true","fetch_graph":"https://pith.science/api/pith-number/ESHBGX3SKBIN64CZMJ4ZRL7THH/graph.json","fetch_events":"https://pith.science/api/pith-number/ESHBGX3SKBIN64CZMJ4ZRL7THH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ESHBGX3SKBIN64CZMJ4ZRL7THH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ESHBGX3SKBIN64CZMJ4ZRL7THH/action/storage_attestation","attest_author":"https://pith.science/pith/ESHBGX3SKBIN64CZMJ4ZRL7THH/action/author_attestation","sign_citation":"https://pith.science/pith/ESHBGX3SKBIN64CZMJ4ZRL7THH/action/citation_signature","submit_replication":"https://pith.science/pith/ESHBGX3SKBIN64CZMJ4ZRL7THH/action/replication_record"}},"created_at":"2026-07-05T11:11:11.470988+00:00","updated_at":"2026-07-05T11:11:11.470988+00:00"}