{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:WEGIL6WGALF4H7JCJYOHAEKXMZ","short_pith_number":"pith:WEGIL6WG","canonical_record":{"source":{"id":"1909.06043","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-13T05:45:25Z","cross_cats_sorted":[],"title_canon_sha256":"84d80ef635934eaf69cb51d28b08b00d47bd38b5278180ab1110446fbc267534","abstract_canon_sha256":"9efd9fe32a61133ea7d27f261895bb465b558aa2bfdcfa9bd9b5f3041e8ed754"},"schema_version":"1.0"},"canonical_sha256":"b10c85fac602cbc3fd224e1c7011576657724bad500dcdeb07b54eed31bbf10a","source":{"kind":"arxiv","id":"1909.06043","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.06043","created_at":"2026-07-05T00:47:59Z"},{"alias_kind":"arxiv_version","alias_value":"1909.06043v3","created_at":"2026-07-05T00:47:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.06043","created_at":"2026-07-05T00:47:59Z"},{"alias_kind":"pith_short_12","alias_value":"WEGIL6WGALF4","created_at":"2026-07-05T00:47:59Z"},{"alias_kind":"pith_short_16","alias_value":"WEGIL6WGALF4H7JC","created_at":"2026-07-05T00:47:59Z"},{"alias_kind":"pith_short_8","alias_value":"WEGIL6WG","created_at":"2026-07-05T00:47:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:WEGIL6WGALF4H7JCJYOHAEKXMZ","target":"record","payload":{"canonical_record":{"source":{"id":"1909.06043","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-13T05:45:25Z","cross_cats_sorted":[],"title_canon_sha256":"84d80ef635934eaf69cb51d28b08b00d47bd38b5278180ab1110446fbc267534","abstract_canon_sha256":"9efd9fe32a61133ea7d27f261895bb465b558aa2bfdcfa9bd9b5f3041e8ed754"},"schema_version":"1.0"},"canonical_sha256":"b10c85fac602cbc3fd224e1c7011576657724bad500dcdeb07b54eed31bbf10a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:47:59.077690Z","signature_b64":"FAa5dRAB7lxNf0Pow82DxlXrJpNuaDtEelQ3CmeHSr/fYQLhAeaEeAZu3t2Gar9NQ7AR10/na7/mhBGWLazPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b10c85fac602cbc3fd224e1c7011576657724bad500dcdeb07b54eed31bbf10a","last_reissued_at":"2026-07-05T00:47:59.077304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:47:59.077304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.06043","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:47:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L0CjegV7maL4gvMHeThVU1aQC6W7hpbJLVyJBJjAsdqb+cG+buo7mHRgPa6ZxCDyOfOLmXepRmwPUse48ODWAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:30:31.975718Z"},"content_sha256":"cb1111d62a0435eadd08b2ca13f2c5359ea18164f718134bda73c32616a87439","schema_version":"1.0","event_id":"sha256:cb1111d62a0435eadd08b2ca13f2c5359ea18164f718134bda73c32616a87439"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:WEGIL6WGALF4H7JCJYOHAEKXMZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alvaro Parra, Bo Chen, Jiewei Cao, Nan Li, Tat-Jun Chin","submitted_at":"2019-09-13T05:45:25Z","abstract_excerpt":"Deep networks excel in learning patterns from large amounts of data. On the other hand, many geometric vision tasks are specified as optimization problems. To seamlessly combine deep learning and geometric vision, it is vital to perform learning and geometric optimization end-to-end. Towards this aim, we present BPnP, a novel network module that backpropagates gradients through a Perspective-n-Points (PnP) solver to guide parameter updates of a neural network. Based on implicit differentiation, we show that the gradients of a \"self-contained\" PnP solver can be derived accurately and efficientl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.06043","kind":"arxiv","version":3},"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/1909.06043/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:47:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Th3c+Y4zGwW1VtjD+8DUpUgkXEApibaD7st/0Rles3dkSTT82g7O5QT9oFDM5vJ/TVmKjOwB+0LBIUoGI4H7Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:30:31.976214Z"},"content_sha256":"05abd0e9b969de1faf689cffe7d1c2b9d8859710d652c76624d261cd5e928dd1","schema_version":"1.0","event_id":"sha256:05abd0e9b969de1faf689cffe7d1c2b9d8859710d652c76624d261cd5e928dd1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WEGIL6WGALF4H7JCJYOHAEKXMZ/bundle.json","state_url":"https://pith.science/pith/WEGIL6WGALF4H7JCJYOHAEKXMZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WEGIL6WGALF4H7JCJYOHAEKXMZ/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":"2026-08-06T08:30:31Z","links":{"resolver":"https://pith.science/pith/WEGIL6WGALF4H7JCJYOHAEKXMZ","bundle":"https://pith.science/pith/WEGIL6WGALF4H7JCJYOHAEKXMZ/bundle.json","state":"https://pith.science/pith/WEGIL6WGALF4H7JCJYOHAEKXMZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WEGIL6WGALF4H7JCJYOHAEKXMZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WEGIL6WGALF4H7JCJYOHAEKXMZ","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":"9efd9fe32a61133ea7d27f261895bb465b558aa2bfdcfa9bd9b5f3041e8ed754","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-13T05:45:25Z","title_canon_sha256":"84d80ef635934eaf69cb51d28b08b00d47bd38b5278180ab1110446fbc267534"},"schema_version":"1.0","source":{"id":"1909.06043","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.06043","created_at":"2026-07-05T00:47:59Z"},{"alias_kind":"arxiv_version","alias_value":"1909.06043v3","created_at":"2026-07-05T00:47:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.06043","created_at":"2026-07-05T00:47:59Z"},{"alias_kind":"pith_short_12","alias_value":"WEGIL6WGALF4","created_at":"2026-07-05T00:47:59Z"},{"alias_kind":"pith_short_16","alias_value":"WEGIL6WGALF4H7JC","created_at":"2026-07-05T00:47:59Z"},{"alias_kind":"pith_short_8","alias_value":"WEGIL6WG","created_at":"2026-07-05T00:47:59Z"}],"graph_snapshots":[{"event_id":"sha256:05abd0e9b969de1faf689cffe7d1c2b9d8859710d652c76624d261cd5e928dd1","target":"graph","created_at":"2026-07-05T00:47:59Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1909.06043/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep networks excel in learning patterns from large amounts of data. On the other hand, many geometric vision tasks are specified as optimization problems. To seamlessly combine deep learning and geometric vision, it is vital to perform learning and geometric optimization end-to-end. Towards this aim, we present BPnP, a novel network module that backpropagates gradients through a Perspective-n-Points (PnP) solver to guide parameter updates of a neural network. Based on implicit differentiation, we show that the gradients of a \"self-contained\" PnP solver can be derived accurately and efficientl","authors_text":"Alvaro Parra, Bo Chen, Jiewei Cao, Nan Li, Tat-Jun Chin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-13T05:45:25Z","title":"End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.06043","kind":"arxiv","version":3},"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:cb1111d62a0435eadd08b2ca13f2c5359ea18164f718134bda73c32616a87439","target":"record","created_at":"2026-07-05T00:47:59Z","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":"9efd9fe32a61133ea7d27f261895bb465b558aa2bfdcfa9bd9b5f3041e8ed754","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-13T05:45:25Z","title_canon_sha256":"84d80ef635934eaf69cb51d28b08b00d47bd38b5278180ab1110446fbc267534"},"schema_version":"1.0","source":{"id":"1909.06043","kind":"arxiv","version":3}},"canonical_sha256":"b10c85fac602cbc3fd224e1c7011576657724bad500dcdeb07b54eed31bbf10a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b10c85fac602cbc3fd224e1c7011576657724bad500dcdeb07b54eed31bbf10a","first_computed_at":"2026-07-05T00:47:59.077304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:47:59.077304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FAa5dRAB7lxNf0Pow82DxlXrJpNuaDtEelQ3CmeHSr/fYQLhAeaEeAZu3t2Gar9NQ7AR10/na7/mhBGWLazPBw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:47:59.077690Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.06043","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb1111d62a0435eadd08b2ca13f2c5359ea18164f718134bda73c32616a87439","sha256:05abd0e9b969de1faf689cffe7d1c2b9d8859710d652c76624d261cd5e928dd1"],"state_sha256":"23fda9afacf9860917945d0c0472a3593f21ee41f6e8876ec5f654ad603dd080"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xLSopi2QrXRBvj84X0UoBx9zn/i+ECCtT+dLC5XW52hXkRWfLH7PUQpETzLq/r3aTU3ppEWPk8idN1Aw4vR2BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:30:31.981052Z","bundle_sha256":"9474598d9a5a2f55eac7bdff94b162579cba296d3fc72c31d4705c28c1a63381"}}