{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DYO4BMYRMMG4TIFP75F7LLL3IA","short_pith_number":"pith:DYO4BMYR","canonical_record":{"source":{"id":"1805.06558","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-17T00:18:08Z","cross_cats_sorted":[],"title_canon_sha256":"34c45ab9136058cce05a05ea41065322caffe5bea0734a70d2d23610bc38a6e7","abstract_canon_sha256":"62959806a497ca9c1a0f6e7f6c4690f86d19883a29f18ad24fcdf487763fa9bc"},"schema_version":"1.0"},"canonical_sha256":"1e1dc0b311630dc9a0afff4bf5ad7b4020969073f7c3baf747f1187ef58409e4","source":{"kind":"arxiv","id":"1805.06558","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.06558","created_at":"2026-05-18T00:15:44Z"},{"alias_kind":"arxiv_version","alias_value":"1805.06558v1","created_at":"2026-05-18T00:15:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.06558","created_at":"2026-05-18T00:15:44Z"},{"alias_kind":"pith_short_12","alias_value":"DYO4BMYRMMG4","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DYO4BMYRMMG4TIFP","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DYO4BMYR","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DYO4BMYRMMG4TIFP75F7LLL3IA","target":"record","payload":{"canonical_record":{"source":{"id":"1805.06558","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-17T00:18:08Z","cross_cats_sorted":[],"title_canon_sha256":"34c45ab9136058cce05a05ea41065322caffe5bea0734a70d2d23610bc38a6e7","abstract_canon_sha256":"62959806a497ca9c1a0f6e7f6c4690f86d19883a29f18ad24fcdf487763fa9bc"},"schema_version":"1.0"},"canonical_sha256":"1e1dc0b311630dc9a0afff4bf5ad7b4020969073f7c3baf747f1187ef58409e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:44.065305Z","signature_b64":"XdskJpYIB26K26PH+CeO2Lwsf07l6jtZbjmefRQ9fkLlC/EZWp4B0/RX0XB67+Ds7RFwmJnOJ0WYYNXwQbXJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e1dc0b311630dc9a0afff4bf5ad7b4020969073f7c3baf747f1187ef58409e4","last_reissued_at":"2026-05-18T00:15:44.064790Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:44.064790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.06558","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qCLzDGPMuOhhYZDsYo5CIRbT8XZbV2rfMZjTt6P3T8R26QB3efY6eY9/EpcXwICZqE48gM8Ea9CdN/qQW3M1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:13:13.909994Z"},"content_sha256":"9c87290a1f1c611dd262eef30ed8070b2bd1d84bb1486f2bdbd686ecb1aeec83","schema_version":"1.0","event_id":"sha256:9c87290a1f1c611dd262eef30ed8070b2bd1d84bb1486f2bdbd686ecb1aeec83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DYO4BMYRMMG4TIFP75F7LLL3IA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recurrent Neural Network for Learning DenseDepth and Ego-Motion from Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jan-Michael Frahm, Rui Wang, Stephen M. Pizer","submitted_at":"2018-05-17T00:18:08Z","abstract_excerpt":"Learning-based, single-view depth estimation often generalizes poorly to unseen datasets. While learning-based, two-frame depth estimation solves this problem to some extent by learning to match features across frames, it performs poorly at large depth where the uncertainty is high. There exists few learning-based, multi-view depth estimation methods. In this paper, we present a learning-based, multi-view dense depth map and ego-motion estimation method that uses Recurrent Neural Networks (RNN). Our model is designed for 3D reconstruction from video where the input frames are temporally correl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.06558","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":""},"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":"2026-05-18T00:15:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1CQCL7eh/jqY3vsehCKa51xLZmg1qDuINEfKfQfDENRS8FSQsqkdBeq6LcCtDluY38R3JZ6shwdv2UlD4UkeBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:13:13.910834Z"},"content_sha256":"2fda1afbd7046c8584db0458632d73ba62e30b281f0ada37f952f7e54600ffae","schema_version":"1.0","event_id":"sha256:2fda1afbd7046c8584db0458632d73ba62e30b281f0ada37f952f7e54600ffae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DYO4BMYRMMG4TIFP75F7LLL3IA/bundle.json","state_url":"https://pith.science/pith/DYO4BMYRMMG4TIFP75F7LLL3IA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DYO4BMYRMMG4TIFP75F7LLL3IA/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":"2026-05-31T18:13:13Z","links":{"resolver":"https://pith.science/pith/DYO4BMYRMMG4TIFP75F7LLL3IA","bundle":"https://pith.science/pith/DYO4BMYRMMG4TIFP75F7LLL3IA/bundle.json","state":"https://pith.science/pith/DYO4BMYRMMG4TIFP75F7LLL3IA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DYO4BMYRMMG4TIFP75F7LLL3IA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DYO4BMYRMMG4TIFP75F7LLL3IA","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":"62959806a497ca9c1a0f6e7f6c4690f86d19883a29f18ad24fcdf487763fa9bc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-17T00:18:08Z","title_canon_sha256":"34c45ab9136058cce05a05ea41065322caffe5bea0734a70d2d23610bc38a6e7"},"schema_version":"1.0","source":{"id":"1805.06558","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.06558","created_at":"2026-05-18T00:15:44Z"},{"alias_kind":"arxiv_version","alias_value":"1805.06558v1","created_at":"2026-05-18T00:15:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.06558","created_at":"2026-05-18T00:15:44Z"},{"alias_kind":"pith_short_12","alias_value":"DYO4BMYRMMG4","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DYO4BMYRMMG4TIFP","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DYO4BMYR","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:2fda1afbd7046c8584db0458632d73ba62e30b281f0ada37f952f7e54600ffae","target":"graph","created_at":"2026-05-18T00:15:44Z","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":"Learning-based, single-view depth estimation often generalizes poorly to unseen datasets. While learning-based, two-frame depth estimation solves this problem to some extent by learning to match features across frames, it performs poorly at large depth where the uncertainty is high. There exists few learning-based, multi-view depth estimation methods. In this paper, we present a learning-based, multi-view dense depth map and ego-motion estimation method that uses Recurrent Neural Networks (RNN). Our model is designed for 3D reconstruction from video where the input frames are temporally correl","authors_text":"Jan-Michael Frahm, Rui Wang, Stephen M. Pizer","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-17T00:18:08Z","title":"Recurrent Neural Network for Learning DenseDepth and Ego-Motion from Video"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.06558","kind":"arxiv","version":1},"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":"sha256:9c87290a1f1c611dd262eef30ed8070b2bd1d84bb1486f2bdbd686ecb1aeec83","target":"record","created_at":"2026-05-18T00:15:44Z","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":"62959806a497ca9c1a0f6e7f6c4690f86d19883a29f18ad24fcdf487763fa9bc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-17T00:18:08Z","title_canon_sha256":"34c45ab9136058cce05a05ea41065322caffe5bea0734a70d2d23610bc38a6e7"},"schema_version":"1.0","source":{"id":"1805.06558","kind":"arxiv","version":1}},"canonical_sha256":"1e1dc0b311630dc9a0afff4bf5ad7b4020969073f7c3baf747f1187ef58409e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e1dc0b311630dc9a0afff4bf5ad7b4020969073f7c3baf747f1187ef58409e4","first_computed_at":"2026-05-18T00:15:44.064790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:44.064790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XdskJpYIB26K26PH+CeO2Lwsf07l6jtZbjmefRQ9fkLlC/EZWp4B0/RX0XB67+Ds7RFwmJnOJ0WYYNXwQbXJDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:44.065305Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.06558","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c87290a1f1c611dd262eef30ed8070b2bd1d84bb1486f2bdbd686ecb1aeec83","sha256:2fda1afbd7046c8584db0458632d73ba62e30b281f0ada37f952f7e54600ffae"],"state_sha256":"ada8adf668782aa1638607fbc768f8fc712b6ca7dec9b30921e35ee90606dc15"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8awxw9bSKS7QxbsTA776pRELvN8wejKyF0VJV4sgnGUS2Q2RbxabrdcPzvfzVlkOJm0wExjZKG664hFTv8DfBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T18:13:13.915153Z","bundle_sha256":"e59710ed76293bfa95b5b650f90a32c88023c7cc313a818b53b9b773e0acf7a7"}}