{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZPC4HDD46NNLQSG7276ZGCFRZE","short_pith_number":"pith:ZPC4HDD4","canonical_record":{"source":{"id":"1803.08071","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-03-21T18:13:54Z","cross_cats_sorted":[],"title_canon_sha256":"e4825168bc65677bc91825e885102bab27574420393e9a5bd53b569b6e0f5884","abstract_canon_sha256":"788350b4cceb67e7b1d457922e01b41e5a7b75d78325ad03465fd62d70fb0237"},"schema_version":"1.0"},"canonical_sha256":"cbc5c38c7cf35ab848dfd7fd9308b1c92d073b2220505f7860959f35a7dd80f9","source":{"kind":"arxiv","id":"1803.08071","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.08071","created_at":"2026-05-18T00:20:13Z"},{"alias_kind":"arxiv_version","alias_value":"1803.08071v2","created_at":"2026-05-18T00:20:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.08071","created_at":"2026-05-18T00:20:13Z"},{"alias_kind":"pith_short_12","alias_value":"ZPC4HDD46NNL","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZPC4HDD46NNLQSG7","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZPC4HDD4","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZPC4HDD46NNLQSG7276ZGCFRZE","target":"record","payload":{"canonical_record":{"source":{"id":"1803.08071","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-03-21T18:13:54Z","cross_cats_sorted":[],"title_canon_sha256":"e4825168bc65677bc91825e885102bab27574420393e9a5bd53b569b6e0f5884","abstract_canon_sha256":"788350b4cceb67e7b1d457922e01b41e5a7b75d78325ad03465fd62d70fb0237"},"schema_version":"1.0"},"canonical_sha256":"cbc5c38c7cf35ab848dfd7fd9308b1c92d073b2220505f7860959f35a7dd80f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:13.279613Z","signature_b64":"qrsOwFrcBNPheV95bmMsgeLFC/WnucTSJg0gGQlnUaWOwhIlNzrxOiPm2biRfTQ381TUvwYue5M4SNKXsLXYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbc5c38c7cf35ab848dfd7fd9308b1c92d073b2220505f7860959f35a7dd80f9","last_reissued_at":"2026-05-18T00:20:13.279117Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:13.279117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.08071","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":"2026-05-18T00:20:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jqikhYr1ouseLxPsUybf06LLKqX5cZg1O+7CXMYaYceD+CoA185LoTHTltQ8n11k892ijRI2EFv3uw7z8pExDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:51:25.758630Z"},"content_sha256":"0cd8983da0137539a9f4287fd1b74fbd085f673fd65b8835df5b4959361203e2","schema_version":"1.0","event_id":"sha256:0cd8983da0137539a9f4287fd1b74fbd085f673fd65b8835df5b4959361203e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZPC4HDD46NNLQSG7276ZGCFRZE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Wang, Kwang Moo Yi, Mathieu Salzmann, Pascal Fua, Yinlin Hu, Zheng Dang","submitted_at":"2018-03-21T18:13:54Z","abstract_excerpt":"Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be solved by finding the eigenvector corresponding to the smallest, or zero, eigenvalue of a matrix representing a linear system. Incorporating this in deep learning frameworks would allow us to explicitly encode known notions of geometry, instead of having the network implicitly learn them from data. However, performing eigendecomposition within a network requires the ability to differentiate this operation. Unfortunately, while theoretically doable, this introd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.08071","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":"2026-05-18T00:20:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iFACyRu82sp5u8zoeL2xF3WUDHyPltP4INiB0Y7r5K2kMxQqYULMD1URcDoeFyrdgsk9u69Lgl64PtBIvvL4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:51:25.759093Z"},"content_sha256":"51ea14beb6ed95d5eae8fd392df082ed622674d2ad4e7ec352e0af04ae0c8283","schema_version":"1.0","event_id":"sha256:51ea14beb6ed95d5eae8fd392df082ed622674d2ad4e7ec352e0af04ae0c8283"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZPC4HDD46NNLQSG7276ZGCFRZE/bundle.json","state_url":"https://pith.science/pith/ZPC4HDD46NNLQSG7276ZGCFRZE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZPC4HDD46NNLQSG7276ZGCFRZE/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":"2026-05-26T06:51:25Z","links":{"resolver":"https://pith.science/pith/ZPC4HDD46NNLQSG7276ZGCFRZE","bundle":"https://pith.science/pith/ZPC4HDD46NNLQSG7276ZGCFRZE/bundle.json","state":"https://pith.science/pith/ZPC4HDD46NNLQSG7276ZGCFRZE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZPC4HDD46NNLQSG7276ZGCFRZE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZPC4HDD46NNLQSG7276ZGCFRZE","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":"788350b4cceb67e7b1d457922e01b41e5a7b75d78325ad03465fd62d70fb0237","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-03-21T18:13:54Z","title_canon_sha256":"e4825168bc65677bc91825e885102bab27574420393e9a5bd53b569b6e0f5884"},"schema_version":"1.0","source":{"id":"1803.08071","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.08071","created_at":"2026-05-18T00:20:13Z"},{"alias_kind":"arxiv_version","alias_value":"1803.08071v2","created_at":"2026-05-18T00:20:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.08071","created_at":"2026-05-18T00:20:13Z"},{"alias_kind":"pith_short_12","alias_value":"ZPC4HDD46NNL","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZPC4HDD46NNLQSG7","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZPC4HDD4","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:51ea14beb6ed95d5eae8fd392df082ed622674d2ad4e7ec352e0af04ae0c8283","target":"graph","created_at":"2026-05-18T00:20:13Z","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":"Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be solved by finding the eigenvector corresponding to the smallest, or zero, eigenvalue of a matrix representing a linear system. Incorporating this in deep learning frameworks would allow us to explicitly encode known notions of geometry, instead of having the network implicitly learn them from data. However, performing eigendecomposition within a network requires the ability to differentiate this operation. Unfortunately, while theoretically doable, this introd","authors_text":"Fei Wang, Kwang Moo Yi, Mathieu Salzmann, Pascal Fua, Yinlin Hu, Zheng Dang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-03-21T18:13:54Z","title":"Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.08071","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":"sha256:0cd8983da0137539a9f4287fd1b74fbd085f673fd65b8835df5b4959361203e2","target":"record","created_at":"2026-05-18T00:20:13Z","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":"788350b4cceb67e7b1d457922e01b41e5a7b75d78325ad03465fd62d70fb0237","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-03-21T18:13:54Z","title_canon_sha256":"e4825168bc65677bc91825e885102bab27574420393e9a5bd53b569b6e0f5884"},"schema_version":"1.0","source":{"id":"1803.08071","kind":"arxiv","version":2}},"canonical_sha256":"cbc5c38c7cf35ab848dfd7fd9308b1c92d073b2220505f7860959f35a7dd80f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbc5c38c7cf35ab848dfd7fd9308b1c92d073b2220505f7860959f35a7dd80f9","first_computed_at":"2026-05-18T00:20:13.279117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:13.279117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qrsOwFrcBNPheV95bmMsgeLFC/WnucTSJg0gGQlnUaWOwhIlNzrxOiPm2biRfTQ381TUvwYue5M4SNKXsLXYCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:13.279613Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.08071","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cd8983da0137539a9f4287fd1b74fbd085f673fd65b8835df5b4959361203e2","sha256:51ea14beb6ed95d5eae8fd392df082ed622674d2ad4e7ec352e0af04ae0c8283"],"state_sha256":"cd68ae914860576cb1a6597e935572b6d34072a519c30c02067886a7eb1bc2cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6QEOnOor8eQ1m61A94ZgrrJAeOlXa6tNNxNeZXqAA7gu9NzGapDQ09iLYWma72Xsjdrt1NxcyINIhZ7R55lkCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T06:51:25.762678Z","bundle_sha256":"244ddf0e696802233adc1cdef0f07b7bbe60615f67724cf31edf4ab023b66513"}}