{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:4XD6OHVUSQVO5MLL6NVKXQZARX","short_pith_number":"pith:4XD6OHVU","canonical_record":{"source":{"id":"1808.00769","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-02T11:59:45Z","cross_cats_sorted":[],"title_canon_sha256":"005e23db597d78889f9490e3574bb9746cfba253b90e2ba0ce6f3177c959ef5a","abstract_canon_sha256":"3e7027eab19463885c5c670cd477bcf25de6003109e823f5f9be2d7b79489868"},"schema_version":"1.0"},"canonical_sha256":"e5c7e71eb4942aeeb16bf36aabc3208dfd4d6e0c56cb29bba8c50eb6342503b5","source":{"kind":"arxiv","id":"1808.00769","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.00769","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"arxiv_version","alias_value":"1808.00769v2","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.00769","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"pith_short_12","alias_value":"4XD6OHVUSQVO","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4XD6OHVUSQVO5MLL","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4XD6OHVU","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:4XD6OHVUSQVO5MLL6NVKXQZARX","target":"record","payload":{"canonical_record":{"source":{"id":"1808.00769","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-02T11:59:45Z","cross_cats_sorted":[],"title_canon_sha256":"005e23db597d78889f9490e3574bb9746cfba253b90e2ba0ce6f3177c959ef5a","abstract_canon_sha256":"3e7027eab19463885c5c670cd477bcf25de6003109e823f5f9be2d7b79489868"},"schema_version":"1.0"},"canonical_sha256":"e5c7e71eb4942aeeb16bf36aabc3208dfd4d6e0c56cb29bba8c50eb6342503b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:45.780436Z","signature_b64":"btGEng2WErlS5tJBX24Ypy+A3L35ee3F4qN5iED6Ep9cBbWKxXugOUlV0eCD26e6dRAWk2ADOSXjBreCop81DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5c7e71eb4942aeeb16bf36aabc3208dfd4d6e0c56cb29bba8c50eb6342503b5","last_reissued_at":"2026-05-18T00:06:45.779845Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:45.779845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.00769","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":"2026-05-18T00:06:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eQEBwoX4Dtm2q16SldI9aQv6hluVXyax3N5UjE52Q6NFjAfX5e+V2bGzYLQdbzyD0oSmqKeXb7gL5NeqyS0NAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T23:16:23.989967Z"},"content_sha256":"3474d114cd12dc41353b0fe28db44d1cc4e90ec27380bfeaa3d2b07c22dcfc01","schema_version":"1.0","event_id":"sha256:3474d114cd12dc41353b0fe28db44d1cc4e90ec27380bfeaa3d2b07c22dcfc01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:4XD6OHVUSQVO5MLL6NVKXQZARX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Emilie Wirbel, Fawzi Nashashibi, Maximilian Jaritz, Raoul de Charette, Xavier Perrotton","submitted_at":"2018-08-02T11:59:45Z","abstract_excerpt":"Convolutional neural networks are designed for dense data, but vision data is often sparse (stereo depth, point clouds, pen stroke, etc.). We present a method to handle sparse depth data with optional dense RGB, and accomplish depth completion and semantic segmentation changing only the last layer. Our proposal efficiently learns sparse features without the need of an additional validity mask. We show how to ensure network robustness to varying input sparsities. Our method even works with densities as low as 0.8% (8 layer lidar), and outperforms all published state-of-the-art on the Kitti dept"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.00769","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":"2026-05-18T00:06:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M6wxouSlRmWh+XquQIlcbQwqyiuWUXifnVvresYlHQXO4zjfY+cTN0E7LIv1vEeGDqKSbpZuXHcu3YtsMVdXAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T23:16:23.990747Z"},"content_sha256":"21f120f0df51b10470088fe31c43e5fc70292ed2a48b8c6adedab3b3e5917649","schema_version":"1.0","event_id":"sha256:21f120f0df51b10470088fe31c43e5fc70292ed2a48b8c6adedab3b3e5917649"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4XD6OHVUSQVO5MLL6NVKXQZARX/bundle.json","state_url":"https://pith.science/pith/4XD6OHVUSQVO5MLL6NVKXQZARX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4XD6OHVUSQVO5MLL6NVKXQZARX/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":"2026-05-30T23:16:23Z","links":{"resolver":"https://pith.science/pith/4XD6OHVUSQVO5MLL6NVKXQZARX","bundle":"https://pith.science/pith/4XD6OHVUSQVO5MLL6NVKXQZARX/bundle.json","state":"https://pith.science/pith/4XD6OHVUSQVO5MLL6NVKXQZARX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4XD6OHVUSQVO5MLL6NVKXQZARX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4XD6OHVUSQVO5MLL6NVKXQZARX","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":"3e7027eab19463885c5c670cd477bcf25de6003109e823f5f9be2d7b79489868","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-02T11:59:45Z","title_canon_sha256":"005e23db597d78889f9490e3574bb9746cfba253b90e2ba0ce6f3177c959ef5a"},"schema_version":"1.0","source":{"id":"1808.00769","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.00769","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"arxiv_version","alias_value":"1808.00769v2","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.00769","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"pith_short_12","alias_value":"4XD6OHVUSQVO","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4XD6OHVUSQVO5MLL","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4XD6OHVU","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:21f120f0df51b10470088fe31c43e5fc70292ed2a48b8c6adedab3b3e5917649","target":"graph","created_at":"2026-05-18T00:06:45Z","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":"Convolutional neural networks are designed for dense data, but vision data is often sparse (stereo depth, point clouds, pen stroke, etc.). We present a method to handle sparse depth data with optional dense RGB, and accomplish depth completion and semantic segmentation changing only the last layer. Our proposal efficiently learns sparse features without the need of an additional validity mask. We show how to ensure network robustness to varying input sparsities. Our method even works with densities as low as 0.8% (8 layer lidar), and outperforms all published state-of-the-art on the Kitti dept","authors_text":"Emilie Wirbel, Fawzi Nashashibi, Maximilian Jaritz, Raoul de Charette, Xavier Perrotton","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-02T11:59:45Z","title":"Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.00769","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":"sha256:3474d114cd12dc41353b0fe28db44d1cc4e90ec27380bfeaa3d2b07c22dcfc01","target":"record","created_at":"2026-05-18T00:06:45Z","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":"3e7027eab19463885c5c670cd477bcf25de6003109e823f5f9be2d7b79489868","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-02T11:59:45Z","title_canon_sha256":"005e23db597d78889f9490e3574bb9746cfba253b90e2ba0ce6f3177c959ef5a"},"schema_version":"1.0","source":{"id":"1808.00769","kind":"arxiv","version":2}},"canonical_sha256":"e5c7e71eb4942aeeb16bf36aabc3208dfd4d6e0c56cb29bba8c50eb6342503b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5c7e71eb4942aeeb16bf36aabc3208dfd4d6e0c56cb29bba8c50eb6342503b5","first_computed_at":"2026-05-18T00:06:45.779845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:45.779845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"btGEng2WErlS5tJBX24Ypy+A3L35ee3F4qN5iED6Ep9cBbWKxXugOUlV0eCD26e6dRAWk2ADOSXjBreCop81DA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:45.780436Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.00769","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3474d114cd12dc41353b0fe28db44d1cc4e90ec27380bfeaa3d2b07c22dcfc01","sha256:21f120f0df51b10470088fe31c43e5fc70292ed2a48b8c6adedab3b3e5917649"],"state_sha256":"5e84974d6ce5c6c152f5cbc1cf3d908c04095972e442a2caf033441e196b3aca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+yELkAlPjSC23ygWaGEOh8dWHTmbjjx7mHAMObWMSbUCPcGHjFBc9U5HHWfFEGTeo0kJPbElsNiRG7uTyIpKBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T23:16:23.994533Z","bundle_sha256":"230ee8708e6bcfa01aa949feaa35664779cb69b22d1740717192196ce2c01af5"}}