{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UDKB6CQZOJDX3JKKTVANWIN4RM","short_pith_number":"pith:UDKB6CQZ","schema_version":"1.0","canonical_sha256":"a0d41f0a1972477da54a9d40db21bc8b1dc27cc0c05e9d5cddab585a078705aa","source":{"kind":"arxiv","id":"2605.24243","version":1},"attestation_state":"computed","paper":{"title":"GIBLy: Improving 3D Semantic Segmentation through an Architecture-Agnostic Lightweight Geometric Inductive Bias Layer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alessandra Micheletti, Cl\\`audia Soares, Diogo Lavado","submitted_at":"2026-05-22T21:42:05Z","abstract_excerpt":"In 3D scene understanding, deep learning models rely on large models and extensive training to capture basic geometric structures that are present in the 3D data. However, existing methods lack explicit mechanisms to incorporate geometric information, such as learnable primitive shapes, often necessitating large models and more training data which in turn increases cost and can limit generalization. We introduce GIBLy, a lightweight geometric inductive bias layer that integrates learnable geometric priors into 3D segmentation pipelines. GIBLy enhances existing architectures -- whether MLP-base"},"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":"2605.24243","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T21:42:05Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9592afd58313d040c62cd6242e91cc2734bee407c567a455fef98992fbb463f4","abstract_canon_sha256":"7f941ce061bb2c37c82edc11a164ae1ee1287255caebd39e653da71a9cbc83b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:54.435969Z","signature_b64":"l8NnLYwAlkUS4LipbZEpEqIgR0kDO15kH3w7hQxTShLL6SJO3T+Awb4ihG5W8LD9mXT7kmnQt4oxhi8tC6msDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0d41f0a1972477da54a9d40db21bc8b1dc27cc0c05e9d5cddab585a078705aa","last_reissued_at":"2026-05-26T01:02:54.435192Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:54.435192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GIBLy: Improving 3D Semantic Segmentation through an Architecture-Agnostic Lightweight Geometric Inductive Bias Layer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alessandra Micheletti, Cl\\`audia Soares, Diogo Lavado","submitted_at":"2026-05-22T21:42:05Z","abstract_excerpt":"In 3D scene understanding, deep learning models rely on large models and extensive training to capture basic geometric structures that are present in the 3D data. However, existing methods lack explicit mechanisms to incorporate geometric information, such as learnable primitive shapes, often necessitating large models and more training data which in turn increases cost and can limit generalization. We introduce GIBLy, a lightweight geometric inductive bias layer that integrates learnable geometric priors into 3D segmentation pipelines. GIBLy enhances existing architectures -- whether MLP-base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24243","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/2605.24243/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":"2605.24243","created_at":"2026-05-26T01:02:54.435344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24243v1","created_at":"2026-05-26T01:02:54.435344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24243","created_at":"2026-05-26T01:02:54.435344+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDKB6CQZOJDX","created_at":"2026-05-26T01:02:54.435344+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDKB6CQZOJDX3JKK","created_at":"2026-05-26T01:02:54.435344+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDKB6CQZ","created_at":"2026-05-26T01:02:54.435344+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/UDKB6CQZOJDX3JKKTVANWIN4RM","json":"https://pith.science/pith/UDKB6CQZOJDX3JKKTVANWIN4RM.json","graph_json":"https://pith.science/api/pith-number/UDKB6CQZOJDX3JKKTVANWIN4RM/graph.json","events_json":"https://pith.science/api/pith-number/UDKB6CQZOJDX3JKKTVANWIN4RM/events.json","paper":"https://pith.science/paper/UDKB6CQZ"},"agent_actions":{"view_html":"https://pith.science/pith/UDKB6CQZOJDX3JKKTVANWIN4RM","download_json":"https://pith.science/pith/UDKB6CQZOJDX3JKKTVANWIN4RM.json","view_paper":"https://pith.science/paper/UDKB6CQZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24243&json=true","fetch_graph":"https://pith.science/api/pith-number/UDKB6CQZOJDX3JKKTVANWIN4RM/graph.json","fetch_events":"https://pith.science/api/pith-number/UDKB6CQZOJDX3JKKTVANWIN4RM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDKB6CQZOJDX3JKKTVANWIN4RM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDKB6CQZOJDX3JKKTVANWIN4RM/action/storage_attestation","attest_author":"https://pith.science/pith/UDKB6CQZOJDX3JKKTVANWIN4RM/action/author_attestation","sign_citation":"https://pith.science/pith/UDKB6CQZOJDX3JKKTVANWIN4RM/action/citation_signature","submit_replication":"https://pith.science/pith/UDKB6CQZOJDX3JKKTVANWIN4RM/action/replication_record"}},"created_at":"2026-05-26T01:02:54.435344+00:00","updated_at":"2026-05-26T01:02:54.435344+00:00"}