{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JIVNDKYICW2VVSVIOVYWF4WMCE","short_pith_number":"pith:JIVNDKYI","schema_version":"1.0","canonical_sha256":"4a2ad1ab0815b55acaa8757162f2cc112359de7af8f1cb0fd046cf00c0a00b23","source":{"kind":"arxiv","id":"2509.08104","version":1},"attestation_state":"computed","paper":{"title":"APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Constantino \\'Alvarez Casado, Miguel Bordallo L\\'opez, Mohammad Sabokrou, Sasan Sharifipour","submitted_at":"2025-09-09T19:31:06Z","abstract_excerpt":"Training deep learning models for point cloud prediction tasks such as shape completion and generation depends critically on loss functions that measure discrepancies between predicted and ground-truth point sets. Commonly used functions such as Chamfer Distance (CD), HyperCD, and InfoCD rely on nearest-neighbor assignments, which often induce many-to-one correspondences, leading to point congestion in dense regions and poor coverage in sparse regions. These losses also involve non-differentiable operations due to index selection, which may affect gradient-based optimization. Earth Mover Dista"},"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":"2509.08104","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-09T19:31:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cb1e16f5cc05cca3cd6b21fbdf2eaaa5e2908c71bf3a4d6337d05656f7ee35c0","abstract_canon_sha256":"83382fab8e8091afe780335de564b543ca13b97dbdde347326da2204213e7a34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:22.465460Z","signature_b64":"l72XQQKgCl922vl0M1oseSjsZ2nE0pibqEfxr/9rvAk6NJat9TaL8HztLezeJ50DM+nT0IyRHRXMmkDXO8BYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a2ad1ab0815b55acaa8757162f2cc112359de7af8f1cb0fd046cf00c0a00b23","last_reissued_at":"2026-07-05T12:08:22.464925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:22.464925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Constantino \\'Alvarez Casado, Miguel Bordallo L\\'opez, Mohammad Sabokrou, Sasan Sharifipour","submitted_at":"2025-09-09T19:31:06Z","abstract_excerpt":"Training deep learning models for point cloud prediction tasks such as shape completion and generation depends critically on loss functions that measure discrepancies between predicted and ground-truth point sets. Commonly used functions such as Chamfer Distance (CD), HyperCD, and InfoCD rely on nearest-neighbor assignments, which often induce many-to-one correspondences, leading to point congestion in dense regions and poor coverage in sparse regions. These losses also involve non-differentiable operations due to index selection, which may affect gradient-based optimization. Earth Mover Dista"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08104","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/2509.08104/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":"2509.08104","created_at":"2026-07-05T12:08:22.464989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08104v1","created_at":"2026-07-05T12:08:22.464989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08104","created_at":"2026-07-05T12:08:22.464989+00:00"},{"alias_kind":"pith_short_12","alias_value":"JIVNDKYICW2V","created_at":"2026-07-05T12:08:22.464989+00:00"},{"alias_kind":"pith_short_16","alias_value":"JIVNDKYICW2VVSVI","created_at":"2026-07-05T12:08:22.464989+00:00"},{"alias_kind":"pith_short_8","alias_value":"JIVNDKYI","created_at":"2026-07-05T12:08:22.464989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16813","citing_title":"QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning","ref_index":215,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JIVNDKYICW2VVSVIOVYWF4WMCE","json":"https://pith.science/pith/JIVNDKYICW2VVSVIOVYWF4WMCE.json","graph_json":"https://pith.science/api/pith-number/JIVNDKYICW2VVSVIOVYWF4WMCE/graph.json","events_json":"https://pith.science/api/pith-number/JIVNDKYICW2VVSVIOVYWF4WMCE/events.json","paper":"https://pith.science/paper/JIVNDKYI"},"agent_actions":{"view_html":"https://pith.science/pith/JIVNDKYICW2VVSVIOVYWF4WMCE","download_json":"https://pith.science/pith/JIVNDKYICW2VVSVIOVYWF4WMCE.json","view_paper":"https://pith.science/paper/JIVNDKYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08104&json=true","fetch_graph":"https://pith.science/api/pith-number/JIVNDKYICW2VVSVIOVYWF4WMCE/graph.json","fetch_events":"https://pith.science/api/pith-number/JIVNDKYICW2VVSVIOVYWF4WMCE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JIVNDKYICW2VVSVIOVYWF4WMCE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JIVNDKYICW2VVSVIOVYWF4WMCE/action/storage_attestation","attest_author":"https://pith.science/pith/JIVNDKYICW2VVSVIOVYWF4WMCE/action/author_attestation","sign_citation":"https://pith.science/pith/JIVNDKYICW2VVSVIOVYWF4WMCE/action/citation_signature","submit_replication":"https://pith.science/pith/JIVNDKYICW2VVSVIOVYWF4WMCE/action/replication_record"}},"created_at":"2026-07-05T12:08:22.464989+00:00","updated_at":"2026-07-05T12:08:22.464989+00:00"}