{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FFLC5JQQDLBMJK3FYJQ6LLG4A2","short_pith_number":"pith:FFLC5JQQ","schema_version":"1.0","canonical_sha256":"29562ea6101ac2c4ab65c261e5acdc06825809b95d823df8c1c2f93503b06806","source":{"kind":"arxiv","id":"2502.11891","version":1},"attestation_state":"computed","paper":{"title":"From Open-Vocabulary to Vocabulary-Free Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Federico Tombari, Giulia Rizzoli, Klara Reichard, Lukas Hoyer, Nassir Navab, Pietro Zanuttigh, Stefano Gasperini","submitted_at":"2025-02-17T15:17:08Z","abstract_excerpt":"Open-vocabulary semantic segmentation enables models to identify novel object categories beyond their training data. While this flexibility represents a significant advancement, current approaches still rely on manually specified class names as input, creating an inherent bottleneck in real-world applications. This work proposes a Vocabulary-Free Semantic Segmentation pipeline, eliminating the need for predefined class vocabularies. Specifically, we address the chicken-and-egg problem where users need knowledge of all potential objects within a scene to identify them, yet the purpose of segmen"},"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":"2502.11891","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-17T15:17:08Z","cross_cats_sorted":[],"title_canon_sha256":"6bce97adc57f441039db69f0304dd7f5e1cca9691d9c08d3e8f0d30d47f4a0d3","abstract_canon_sha256":"6571621fad99375995be0b4db09a7a78891ec84bdc418155561538871dde1a1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:35.761015Z","signature_b64":"0yGV6cIBSFu5rsS32QvLj1jW/AknUlBpn9Y5whs/Poz/Q/FQxpogeWTT0Ve0DM93MRrnxc47VQsZNQS9vUt/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29562ea6101ac2c4ab65c261e5acdc06825809b95d823df8c1c2f93503b06806","last_reissued_at":"2026-07-05T10:15:35.760524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:35.760524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Open-Vocabulary to Vocabulary-Free Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Federico Tombari, Giulia Rizzoli, Klara Reichard, Lukas Hoyer, Nassir Navab, Pietro Zanuttigh, Stefano Gasperini","submitted_at":"2025-02-17T15:17:08Z","abstract_excerpt":"Open-vocabulary semantic segmentation enables models to identify novel object categories beyond their training data. While this flexibility represents a significant advancement, current approaches still rely on manually specified class names as input, creating an inherent bottleneck in real-world applications. This work proposes a Vocabulary-Free Semantic Segmentation pipeline, eliminating the need for predefined class vocabularies. Specifically, we address the chicken-and-egg problem where users need knowledge of all potential objects within a scene to identify them, yet the purpose of segmen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11891","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/2502.11891/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":"2502.11891","created_at":"2026-07-05T10:15:35.760578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11891v1","created_at":"2026-07-05T10:15:35.760578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11891","created_at":"2026-07-05T10:15:35.760578+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFLC5JQQDLBM","created_at":"2026-07-05T10:15:35.760578+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFLC5JQQDLBMJK3F","created_at":"2026-07-05T10:15:35.760578+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFLC5JQQ","created_at":"2026-07-05T10:15:35.760578+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19569","citing_title":"What You Perceive Is What You Conceive: A Cognition-Inspired Framework for Open Vocabulary Image Segmentation","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FFLC5JQQDLBMJK3FYJQ6LLG4A2","json":"https://pith.science/pith/FFLC5JQQDLBMJK3FYJQ6LLG4A2.json","graph_json":"https://pith.science/api/pith-number/FFLC5JQQDLBMJK3FYJQ6LLG4A2/graph.json","events_json":"https://pith.science/api/pith-number/FFLC5JQQDLBMJK3FYJQ6LLG4A2/events.json","paper":"https://pith.science/paper/FFLC5JQQ"},"agent_actions":{"view_html":"https://pith.science/pith/FFLC5JQQDLBMJK3FYJQ6LLG4A2","download_json":"https://pith.science/pith/FFLC5JQQDLBMJK3FYJQ6LLG4A2.json","view_paper":"https://pith.science/paper/FFLC5JQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11891&json=true","fetch_graph":"https://pith.science/api/pith-number/FFLC5JQQDLBMJK3FYJQ6LLG4A2/graph.json","fetch_events":"https://pith.science/api/pith-number/FFLC5JQQDLBMJK3FYJQ6LLG4A2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFLC5JQQDLBMJK3FYJQ6LLG4A2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFLC5JQQDLBMJK3FYJQ6LLG4A2/action/storage_attestation","attest_author":"https://pith.science/pith/FFLC5JQQDLBMJK3FYJQ6LLG4A2/action/author_attestation","sign_citation":"https://pith.science/pith/FFLC5JQQDLBMJK3FYJQ6LLG4A2/action/citation_signature","submit_replication":"https://pith.science/pith/FFLC5JQQDLBMJK3FYJQ6LLG4A2/action/replication_record"}},"created_at":"2026-07-05T10:15:35.760578+00:00","updated_at":"2026-07-05T10:15:35.760578+00:00"}