{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MTUAIAS7VWVBRYYJORK6X5UIKJ","short_pith_number":"pith:MTUAIAS7","schema_version":"1.0","canonical_sha256":"64e804025fadaa18e3097455ebf688525b1b719c5c0105bdfde86665326c1cff","source":{"kind":"arxiv","id":"1904.08506","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Hierarchical Down-Sampling for Point Cloud Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingbing Liu, Ehsan Nezhadarya, Ehsan Taghavi, Jun Luo, Ryan Razani","submitted_at":"2019-04-11T23:10:13Z","abstract_excerpt":"While several convolution-like operators have recently been proposed for extracting features out of point clouds, down-sampling an unordered point cloud in a deep neural network has not been rigorously studied. Existing methods down-sample the points regardless of their importance for the output. As a result, some important points in the point cloud may be removed, while less valuable points may be passed to the next layers. In contrast, adaptive down-sampling methods sample the points by taking into account the importance of each point, which varies based on the application, task and training"},"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":"1904.08506","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-11T23:10:13Z","cross_cats_sorted":[],"title_canon_sha256":"94ea3742b8988e2af50c20ad699ad0fd81480213a51ff5d989b608aa219072d7","abstract_canon_sha256":"63ea26cb558a578c4656344580e3d3b6ff12dab5b3efad9ccb5c1b05ae51c764"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:05:34.606958Z","signature_b64":"KuZGvrY4Lb9RXGExQEAnda/Gn1QVc671gcuS1P/DbUE8HOrdHD3CYvKqvfesFXsvhmzRcuPuZX/XNUXUpuLRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64e804025fadaa18e3097455ebf688525b1b719c5c0105bdfde86665326c1cff","last_reissued_at":"2026-07-05T01:05:34.606518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:05:34.606518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Hierarchical Down-Sampling for Point Cloud Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingbing Liu, Ehsan Nezhadarya, Ehsan Taghavi, Jun Luo, Ryan Razani","submitted_at":"2019-04-11T23:10:13Z","abstract_excerpt":"While several convolution-like operators have recently been proposed for extracting features out of point clouds, down-sampling an unordered point cloud in a deep neural network has not been rigorously studied. Existing methods down-sample the points regardless of their importance for the output. As a result, some important points in the point cloud may be removed, while less valuable points may be passed to the next layers. In contrast, adaptive down-sampling methods sample the points by taking into account the importance of each point, which varies based on the application, task and training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.08506","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/1904.08506/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":"1904.08506","created_at":"2026-07-05T01:05:34.606575+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.08506v2","created_at":"2026-07-05T01:05:34.606575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.08506","created_at":"2026-07-05T01:05:34.606575+00:00"},{"alias_kind":"pith_short_12","alias_value":"MTUAIAS7VWVB","created_at":"2026-07-05T01:05:34.606575+00:00"},{"alias_kind":"pith_short_16","alias_value":"MTUAIAS7VWVBRYYJ","created_at":"2026-07-05T01:05:34.606575+00:00"},{"alias_kind":"pith_short_8","alias_value":"MTUAIAS7","created_at":"2026-07-05T01:05:34.606575+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/MTUAIAS7VWVBRYYJORK6X5UIKJ","json":"https://pith.science/pith/MTUAIAS7VWVBRYYJORK6X5UIKJ.json","graph_json":"https://pith.science/api/pith-number/MTUAIAS7VWVBRYYJORK6X5UIKJ/graph.json","events_json":"https://pith.science/api/pith-number/MTUAIAS7VWVBRYYJORK6X5UIKJ/events.json","paper":"https://pith.science/paper/MTUAIAS7"},"agent_actions":{"view_html":"https://pith.science/pith/MTUAIAS7VWVBRYYJORK6X5UIKJ","download_json":"https://pith.science/pith/MTUAIAS7VWVBRYYJORK6X5UIKJ.json","view_paper":"https://pith.science/paper/MTUAIAS7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.08506&json=true","fetch_graph":"https://pith.science/api/pith-number/MTUAIAS7VWVBRYYJORK6X5UIKJ/graph.json","fetch_events":"https://pith.science/api/pith-number/MTUAIAS7VWVBRYYJORK6X5UIKJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MTUAIAS7VWVBRYYJORK6X5UIKJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MTUAIAS7VWVBRYYJORK6X5UIKJ/action/storage_attestation","attest_author":"https://pith.science/pith/MTUAIAS7VWVBRYYJORK6X5UIKJ/action/author_attestation","sign_citation":"https://pith.science/pith/MTUAIAS7VWVBRYYJORK6X5UIKJ/action/citation_signature","submit_replication":"https://pith.science/pith/MTUAIAS7VWVBRYYJORK6X5UIKJ/action/replication_record"}},"created_at":"2026-07-05T01:05:34.606575+00:00","updated_at":"2026-07-05T01:05:34.606575+00:00"}