{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HT5A2TWB67OIIQ275WFLC7ZNA2","short_pith_number":"pith:HT5A2TWB","canonical_record":{"source":{"id":"1805.12254","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-30T22:53:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"87bf8573bfcd97e2955849308572cde563ec8c53dfebbc2121b392af29dcb67d","abstract_canon_sha256":"75f6f298ac934332a1d99f2dd995e3051c16c9d37d33ef5e36acf3d7cea87b4b"},"schema_version":"1.0"},"canonical_sha256":"3cfa0d4ec1f7dc84435fed8ab17f2d06b1a0f6cbdba6c0f53255dff3c6466fde","source":{"kind":"arxiv","id":"1805.12254","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.12254","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"arxiv_version","alias_value":"1805.12254v2","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.12254","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"pith_short_12","alias_value":"HT5A2TWB67OI","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HT5A2TWB67OIIQ27","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HT5A2TWB","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HT5A2TWB67OIIQ275WFLC7ZNA2","target":"record","payload":{"canonical_record":{"source":{"id":"1805.12254","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-30T22:53:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"87bf8573bfcd97e2955849308572cde563ec8c53dfebbc2121b392af29dcb67d","abstract_canon_sha256":"75f6f298ac934332a1d99f2dd995e3051c16c9d37d33ef5e36acf3d7cea87b4b"},"schema_version":"1.0"},"canonical_sha256":"3cfa0d4ec1f7dc84435fed8ab17f2d06b1a0f6cbdba6c0f53255dff3c6466fde","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:03.186150Z","signature_b64":"ijSwZlpg16CoUsaeVYF5WDnQQleBNoMwzP0+51GoV+vXXjco0ZLDYYkU8jtOagi6vS0vMQLOWI3UpW46g74CCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cfa0d4ec1f7dc84435fed8ab17f2d06b1a0f6cbdba6c0f53255dff3c6466fde","last_reissued_at":"2026-05-17T23:47:03.185460Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:03.185460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.12254","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7w8l361HUUWKEODeW9DckOmGZ0e/8XKwsndHK95Nkefg9fYhYb2XI5Hn3WMeOLZKJXYrALb9D5UVduZZwg3+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T21:08:21.754655Z"},"content_sha256":"780f1f939b17e434ea53758fe001377f411eb6a3a244406e1e038955035190d0","schema_version":"1.0","event_id":"sha256:780f1f939b17e434ea53758fe001377f411eb6a3a244406e1e038955035190d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HT5A2TWB67OIIQ275WFLC7ZNA2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-level 3D CNN for Learning Multi-scale Spatial Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Adarsh Krishnamurthy, Aditya Balu, Sambit Ghadai, Soumik Sarkar, Xian Lee","submitted_at":"2018-05-30T22:53:28Z","abstract_excerpt":"3D object recognition accuracy can be improved by learning the multi-scale spatial features from 3D spatial geometric representations of objects such as point clouds, 3D models, surfaces, and RGB-D data. Current deep learning approaches learn such features either using structured data representations (voxel grids and octrees) or from unstructured representations (graphs and point clouds). Learning features from such structured representations is limited by the restriction on resolution and tree depth while unstructured representations creates a challenge due to non-uniformity among data sample"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.12254","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S1sjdEyHpt1eYPrug5Ej/hEp/VZ9lVYvospIoweZ9NCqWe8/IoPmKcWQJ5/qVb0+2PgRZrr2NoMMMFoHnsiqDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T21:08:21.755093Z"},"content_sha256":"4dd1b1dc287115708900c89ad49c42f8bdc9114670301de2f8517c519a5e455b","schema_version":"1.0","event_id":"sha256:4dd1b1dc287115708900c89ad49c42f8bdc9114670301de2f8517c519a5e455b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HT5A2TWB67OIIQ275WFLC7ZNA2/bundle.json","state_url":"https://pith.science/pith/HT5A2TWB67OIIQ275WFLC7ZNA2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HT5A2TWB67OIIQ275WFLC7ZNA2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T21:08:21Z","links":{"resolver":"https://pith.science/pith/HT5A2TWB67OIIQ275WFLC7ZNA2","bundle":"https://pith.science/pith/HT5A2TWB67OIIQ275WFLC7ZNA2/bundle.json","state":"https://pith.science/pith/HT5A2TWB67OIIQ275WFLC7ZNA2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HT5A2TWB67OIIQ275WFLC7ZNA2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HT5A2TWB67OIIQ275WFLC7ZNA2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"75f6f298ac934332a1d99f2dd995e3051c16c9d37d33ef5e36acf3d7cea87b4b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-30T22:53:28Z","title_canon_sha256":"87bf8573bfcd97e2955849308572cde563ec8c53dfebbc2121b392af29dcb67d"},"schema_version":"1.0","source":{"id":"1805.12254","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.12254","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"arxiv_version","alias_value":"1805.12254v2","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.12254","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"pith_short_12","alias_value":"HT5A2TWB67OI","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HT5A2TWB67OIIQ27","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HT5A2TWB","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:4dd1b1dc287115708900c89ad49c42f8bdc9114670301de2f8517c519a5e455b","target":"graph","created_at":"2026-05-17T23:47:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"3D object recognition accuracy can be improved by learning the multi-scale spatial features from 3D spatial geometric representations of objects such as point clouds, 3D models, surfaces, and RGB-D data. Current deep learning approaches learn such features either using structured data representations (voxel grids and octrees) or from unstructured representations (graphs and point clouds). Learning features from such structured representations is limited by the restriction on resolution and tree depth while unstructured representations creates a challenge due to non-uniformity among data sample","authors_text":"Adarsh Krishnamurthy, Aditya Balu, Sambit Ghadai, Soumik Sarkar, Xian Lee","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-30T22:53:28Z","title":"Multi-level 3D CNN for Learning Multi-scale Spatial Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.12254","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:780f1f939b17e434ea53758fe001377f411eb6a3a244406e1e038955035190d0","target":"record","created_at":"2026-05-17T23:47:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"75f6f298ac934332a1d99f2dd995e3051c16c9d37d33ef5e36acf3d7cea87b4b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-30T22:53:28Z","title_canon_sha256":"87bf8573bfcd97e2955849308572cde563ec8c53dfebbc2121b392af29dcb67d"},"schema_version":"1.0","source":{"id":"1805.12254","kind":"arxiv","version":2}},"canonical_sha256":"3cfa0d4ec1f7dc84435fed8ab17f2d06b1a0f6cbdba6c0f53255dff3c6466fde","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3cfa0d4ec1f7dc84435fed8ab17f2d06b1a0f6cbdba6c0f53255dff3c6466fde","first_computed_at":"2026-05-17T23:47:03.185460Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:03.185460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ijSwZlpg16CoUsaeVYF5WDnQQleBNoMwzP0+51GoV+vXXjco0ZLDYYkU8jtOagi6vS0vMQLOWI3UpW46g74CCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:03.186150Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.12254","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:780f1f939b17e434ea53758fe001377f411eb6a3a244406e1e038955035190d0","sha256:4dd1b1dc287115708900c89ad49c42f8bdc9114670301de2f8517c519a5e455b"],"state_sha256":"54d5f9401ecf237ee04ed3ff1f9cc271c7964cf35b587c70eb062dd70b46256a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Ih9aLWn7A7UhS0r8BAdziZAI5u3oZ4jMO+eJ/p7QxwfpncyINr+Lo68iPng4brRnz0Q+LXCnn+Z0YhvyQDzAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T21:08:21.758886Z","bundle_sha256":"301933b9f51ad1da4a06b6121c5ad17e9e607a601ead5d1bc6b101cce5834869"}}