{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5XQNTUZU3L6KTSHHKUOUNLOKG2","short_pith_number":"pith:5XQNTUZU","schema_version":"1.0","canonical_sha256":"ede0d9d334dafca9c8e7551d46adca36ac2a1dc2d3fe954b1651c9eecd85a30e","source":{"kind":"arxiv","id":"2409.09497","version":2},"attestation_state":"computed","paper":{"title":"Multi-Scale Grouped Prototypes for Interpretable Semantic Segmentation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Devis Tuia, Diego Marcos, Emanuele Dalsasso, Hugo Porta","submitted_at":"2024-09-14T17:52:59Z","abstract_excerpt":"Prototypical part learning is emerging as a promising approach for making semantic segmentation interpretable. The model selects real patches seen during training as prototypes and constructs the dense prediction map based on the similarity between parts of the test image and the prototypes. This improves interpretability since the user can inspect the link between the predicted output and the patterns learned by the model in terms of prototypical information. In this paper, we propose a method for interpretable semantic segmentation that leverages multi-scale image representation for prototyp"},"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":"2409.09497","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-14T17:52:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a1b592ae4835359dca49b4d1c192d69dd3e951ed9b5783fd320e02880cf75719","abstract_canon_sha256":"6bd534452d71d358dbf4f02727ccc86177e29132322f03b46bfd75f811f2baa9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:36.283469Z","signature_b64":"eifUxDSxL5T8Ba3YpN53rBm+YZlQ6qiJhrL9TaD/ZZcb7OLDe/ZGS7t+1Zd1ADTy1nHEYwB9Io0Z7YZ8wpQODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ede0d9d334dafca9c8e7551d46adca36ac2a1dc2d3fe954b1651c9eecd85a30e","last_reissued_at":"2026-07-05T10:54:36.283021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:36.283021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Scale Grouped Prototypes for Interpretable Semantic Segmentation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Devis Tuia, Diego Marcos, Emanuele Dalsasso, Hugo Porta","submitted_at":"2024-09-14T17:52:59Z","abstract_excerpt":"Prototypical part learning is emerging as a promising approach for making semantic segmentation interpretable. The model selects real patches seen during training as prototypes and constructs the dense prediction map based on the similarity between parts of the test image and the prototypes. This improves interpretability since the user can inspect the link between the predicted output and the patterns learned by the model in terms of prototypical information. In this paper, we propose a method for interpretable semantic segmentation that leverages multi-scale image representation for prototyp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09497","kind":"arxiv","version":2},"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/2409.09497/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":"2409.09497","created_at":"2026-07-05T10:54:36.283077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09497v2","created_at":"2026-07-05T10:54:36.283077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09497","created_at":"2026-07-05T10:54:36.283077+00:00"},{"alias_kind":"pith_short_12","alias_value":"5XQNTUZU3L6K","created_at":"2026-07-05T10:54:36.283077+00:00"},{"alias_kind":"pith_short_16","alias_value":"5XQNTUZU3L6KTSHH","created_at":"2026-07-05T10:54:36.283077+00:00"},{"alias_kind":"pith_short_8","alias_value":"5XQNTUZU","created_at":"2026-07-05T10:54:36.283077+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/5XQNTUZU3L6KTSHHKUOUNLOKG2","json":"https://pith.science/pith/5XQNTUZU3L6KTSHHKUOUNLOKG2.json","graph_json":"https://pith.science/api/pith-number/5XQNTUZU3L6KTSHHKUOUNLOKG2/graph.json","events_json":"https://pith.science/api/pith-number/5XQNTUZU3L6KTSHHKUOUNLOKG2/events.json","paper":"https://pith.science/paper/5XQNTUZU"},"agent_actions":{"view_html":"https://pith.science/pith/5XQNTUZU3L6KTSHHKUOUNLOKG2","download_json":"https://pith.science/pith/5XQNTUZU3L6KTSHHKUOUNLOKG2.json","view_paper":"https://pith.science/paper/5XQNTUZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09497&json=true","fetch_graph":"https://pith.science/api/pith-number/5XQNTUZU3L6KTSHHKUOUNLOKG2/graph.json","fetch_events":"https://pith.science/api/pith-number/5XQNTUZU3L6KTSHHKUOUNLOKG2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5XQNTUZU3L6KTSHHKUOUNLOKG2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5XQNTUZU3L6KTSHHKUOUNLOKG2/action/storage_attestation","attest_author":"https://pith.science/pith/5XQNTUZU3L6KTSHHKUOUNLOKG2/action/author_attestation","sign_citation":"https://pith.science/pith/5XQNTUZU3L6KTSHHKUOUNLOKG2/action/citation_signature","submit_replication":"https://pith.science/pith/5XQNTUZU3L6KTSHHKUOUNLOKG2/action/replication_record"}},"created_at":"2026-07-05T10:54:36.283077+00:00","updated_at":"2026-07-05T10:54:36.283077+00:00"}