{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:22I4N3AKU5GMTIJAMNDYX4L77T","short_pith_number":"pith:22I4N3AK","schema_version":"1.0","canonical_sha256":"d691c6ec0aa74cc9a12063478bf17ffcc574f88c49cc9bead05ddb964e8824f8","source":{"kind":"arxiv","id":"2411.03405","version":1},"attestation_state":"computed","paper":{"title":"Fine-Grained Spatial and Verbal Losses for 3D Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christos Sakaridis, Luc Van Gool, Ozan Unal, Sombit Dey","submitted_at":"2024-11-05T18:39:25Z","abstract_excerpt":"3D visual grounding consists of identifying the instance in a 3D scene which is referred by an accompanying language description. While several architectures have been proposed within the commonly employed grounding-by-selection framework, the utilized losses are comparatively under-explored. In particular, most methods rely on a basic supervised cross-entropy loss on the predicted distribution over candidate instances, which fails to model both spatial relations between instances and the internal fine-grained word-level structure of the verbal referral. Sparse attempts to additionally supervi"},"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":"2411.03405","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-05T18:39:25Z","cross_cats_sorted":[],"title_canon_sha256":"7125bacc52af6957b0b292684c106644c3cec5c42fc167d8214c9417aecd1803","abstract_canon_sha256":"ba8ae51a1f8fb3a186f9b986c1661a71c3cb1fc42d5d64212aa102079f55f33b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:32.447295Z","signature_b64":"noi+cVKQkbMYgmOCsx+8oPCm8XHgNbrepf99+bMMwEOydyZJdj0LhFw/YBPZLYV21IVgfQSrV3l91WHFktL8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d691c6ec0aa74cc9a12063478bf17ffcc574f88c49cc9bead05ddb964e8824f8","last_reissued_at":"2026-07-05T09:31:32.446890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:32.446890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-Grained Spatial and Verbal Losses for 3D Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christos Sakaridis, Luc Van Gool, Ozan Unal, Sombit Dey","submitted_at":"2024-11-05T18:39:25Z","abstract_excerpt":"3D visual grounding consists of identifying the instance in a 3D scene which is referred by an accompanying language description. While several architectures have been proposed within the commonly employed grounding-by-selection framework, the utilized losses are comparatively under-explored. In particular, most methods rely on a basic supervised cross-entropy loss on the predicted distribution over candidate instances, which fails to model both spatial relations between instances and the internal fine-grained word-level structure of the verbal referral. Sparse attempts to additionally supervi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03405","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/2411.03405/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":"2411.03405","created_at":"2026-07-05T09:31:32.446954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.03405v1","created_at":"2026-07-05T09:31:32.446954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03405","created_at":"2026-07-05T09:31:32.446954+00:00"},{"alias_kind":"pith_short_12","alias_value":"22I4N3AKU5GM","created_at":"2026-07-05T09:31:32.446954+00:00"},{"alias_kind":"pith_short_16","alias_value":"22I4N3AKU5GMTIJA","created_at":"2026-07-05T09:31:32.446954+00:00"},{"alias_kind":"pith_short_8","alias_value":"22I4N3AK","created_at":"2026-07-05T09:31:32.446954+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/22I4N3AKU5GMTIJAMNDYX4L77T","json":"https://pith.science/pith/22I4N3AKU5GMTIJAMNDYX4L77T.json","graph_json":"https://pith.science/api/pith-number/22I4N3AKU5GMTIJAMNDYX4L77T/graph.json","events_json":"https://pith.science/api/pith-number/22I4N3AKU5GMTIJAMNDYX4L77T/events.json","paper":"https://pith.science/paper/22I4N3AK"},"agent_actions":{"view_html":"https://pith.science/pith/22I4N3AKU5GMTIJAMNDYX4L77T","download_json":"https://pith.science/pith/22I4N3AKU5GMTIJAMNDYX4L77T.json","view_paper":"https://pith.science/paper/22I4N3AK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.03405&json=true","fetch_graph":"https://pith.science/api/pith-number/22I4N3AKU5GMTIJAMNDYX4L77T/graph.json","fetch_events":"https://pith.science/api/pith-number/22I4N3AKU5GMTIJAMNDYX4L77T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/22I4N3AKU5GMTIJAMNDYX4L77T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/22I4N3AKU5GMTIJAMNDYX4L77T/action/storage_attestation","attest_author":"https://pith.science/pith/22I4N3AKU5GMTIJAMNDYX4L77T/action/author_attestation","sign_citation":"https://pith.science/pith/22I4N3AKU5GMTIJAMNDYX4L77T/action/citation_signature","submit_replication":"https://pith.science/pith/22I4N3AKU5GMTIJAMNDYX4L77T/action/replication_record"}},"created_at":"2026-07-05T09:31:32.446954+00:00","updated_at":"2026-07-05T09:31:32.446954+00:00"}