{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EDVUHVILGQI3CSL73XAX5KLZDM","short_pith_number":"pith:EDVUHVIL","schema_version":"1.0","canonical_sha256":"20eb43d50b3411b1497fddc17ea9791b165e778f5b2feb7e0edf3fecdfc06540","source":{"kind":"arxiv","id":"2605.22492","version":1},"attestation_state":"computed","paper":{"title":"Training-Free Fine-Grained Semantic Segmentations in Low Data Regimes: A FungiTastic Baseline","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Francesco Pelosin, Lapo Faggi, Sebastian Cavada","submitted_at":"2026-05-21T13:44:52Z","abstract_excerpt":"Fine-grained semantic segmentation requires both precise localization and discrimination between visually similar classes. In FungiTastic, this problem is further complicated by a long-tailed distribution and strong variation in image acquisition conditions. We propose a training-free two-stage framework that decouples segmentation from classification. SAM3 first produces class-agnostic mushroom masks using macro-taxonomic prompts, and DINOv3 then assigns fine-grained labels through prototype matching in the embedding space. To improve this stage, we apply a simple transformation of the DINOv3"},"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":"2605.22492","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T13:44:52Z","cross_cats_sorted":[],"title_canon_sha256":"d8680216a39b3a046b8692e7a079f226733b235223f10de97332c5a4b4beb194","abstract_canon_sha256":"9d61899d02d0ca638b22a1cbaf38264093e6f5db259beb78173c15c1d89eeb7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:47.388676Z","signature_b64":"tLvkLlgsfiFlONqYCzssmYdJbuPpYuesiduImqH1PO5dT7ibAywiKYHAnry7/WXBi4YAaNAYcSCouC2+/JH+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20eb43d50b3411b1497fddc17ea9791b165e778f5b2feb7e0edf3fecdfc06540","last_reissued_at":"2026-05-22T01:04:47.388023Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:47.388023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training-Free Fine-Grained Semantic Segmentations in Low Data Regimes: A FungiTastic Baseline","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Francesco Pelosin, Lapo Faggi, Sebastian Cavada","submitted_at":"2026-05-21T13:44:52Z","abstract_excerpt":"Fine-grained semantic segmentation requires both precise localization and discrimination between visually similar classes. In FungiTastic, this problem is further complicated by a long-tailed distribution and strong variation in image acquisition conditions. We propose a training-free two-stage framework that decouples segmentation from classification. SAM3 first produces class-agnostic mushroom masks using macro-taxonomic prompts, and DINOv3 then assigns fine-grained labels through prototype matching in the embedding space. To improve this stage, we apply a simple transformation of the DINOv3"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22492","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/2605.22492/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":"2605.22492","created_at":"2026-05-22T01:04:47.388122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22492v1","created_at":"2026-05-22T01:04:47.388122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22492","created_at":"2026-05-22T01:04:47.388122+00:00"},{"alias_kind":"pith_short_12","alias_value":"EDVUHVILGQI3","created_at":"2026-05-22T01:04:47.388122+00:00"},{"alias_kind":"pith_short_16","alias_value":"EDVUHVILGQI3CSL7","created_at":"2026-05-22T01:04:47.388122+00:00"},{"alias_kind":"pith_short_8","alias_value":"EDVUHVIL","created_at":"2026-05-22T01:04:47.388122+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/EDVUHVILGQI3CSL73XAX5KLZDM","json":"https://pith.science/pith/EDVUHVILGQI3CSL73XAX5KLZDM.json","graph_json":"https://pith.science/api/pith-number/EDVUHVILGQI3CSL73XAX5KLZDM/graph.json","events_json":"https://pith.science/api/pith-number/EDVUHVILGQI3CSL73XAX5KLZDM/events.json","paper":"https://pith.science/paper/EDVUHVIL"},"agent_actions":{"view_html":"https://pith.science/pith/EDVUHVILGQI3CSL73XAX5KLZDM","download_json":"https://pith.science/pith/EDVUHVILGQI3CSL73XAX5KLZDM.json","view_paper":"https://pith.science/paper/EDVUHVIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22492&json=true","fetch_graph":"https://pith.science/api/pith-number/EDVUHVILGQI3CSL73XAX5KLZDM/graph.json","fetch_events":"https://pith.science/api/pith-number/EDVUHVILGQI3CSL73XAX5KLZDM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EDVUHVILGQI3CSL73XAX5KLZDM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EDVUHVILGQI3CSL73XAX5KLZDM/action/storage_attestation","attest_author":"https://pith.science/pith/EDVUHVILGQI3CSL73XAX5KLZDM/action/author_attestation","sign_citation":"https://pith.science/pith/EDVUHVILGQI3CSL73XAX5KLZDM/action/citation_signature","submit_replication":"https://pith.science/pith/EDVUHVILGQI3CSL73XAX5KLZDM/action/replication_record"}},"created_at":"2026-05-22T01:04:47.388122+00:00","updated_at":"2026-05-22T01:04:47.388122+00:00"}