{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:HU22R435ASPHBS4MJ3Q55RE3YB","short_pith_number":"pith:HU22R435","canonical_record":{"source":{"id":"1708.00919","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-02T20:18:10Z","cross_cats_sorted":[],"title_canon_sha256":"1231a04aff64722a4b759ce1cf4892977d35e9516d378c2633fc541c5970654b","abstract_canon_sha256":"dd4bdded7ff5049d776db3382d84228ac79d6367ca743c583e402b70c3835482"},"schema_version":"1.0"},"canonical_sha256":"3d35a8f37d049e70cb8c4ee1dec49bc043bbd8efd2f525727e1c75a347ceadb4","source":{"kind":"arxiv","id":"1708.00919","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.00919","created_at":"2026-05-17T23:58:54Z"},{"alias_kind":"arxiv_version","alias_value":"1708.00919v3","created_at":"2026-05-17T23:58:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.00919","created_at":"2026-05-17T23:58:54Z"},{"alias_kind":"pith_short_12","alias_value":"HU22R435ASPH","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"HU22R435ASPHBS4M","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"HU22R435","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:HU22R435ASPHBS4MJ3Q55RE3YB","target":"record","payload":{"canonical_record":{"source":{"id":"1708.00919","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-02T20:18:10Z","cross_cats_sorted":[],"title_canon_sha256":"1231a04aff64722a4b759ce1cf4892977d35e9516d378c2633fc541c5970654b","abstract_canon_sha256":"dd4bdded7ff5049d776db3382d84228ac79d6367ca743c583e402b70c3835482"},"schema_version":"1.0"},"canonical_sha256":"3d35a8f37d049e70cb8c4ee1dec49bc043bbd8efd2f525727e1c75a347ceadb4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:54.699002Z","signature_b64":"C6z/VNacueGR1cydKn+MaVD/lpacbDrkzo0PEICOrnBp06hcQIXhSrnrSL0nxDUu0WrzUqHo3ksCLPJiOnuWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d35a8f37d049e70cb8c4ee1dec49bc043bbd8efd2f525727e1c75a347ceadb4","last_reissued_at":"2026-05-17T23:58:54.698613Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:54.698613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.00919","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":"2026-05-17T23:58:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1CFQt98w9qBm+gDQAsTj+Jz7MKChI4bKzTeObNJ0MJbHUDpuW2p8FuPf/arDdWU6b6gqSR2Fxek/BFxiUpRIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T11:39:35.632410Z"},"content_sha256":"a70ef9fbc5336780a8f1bac120fc90427da14afab7370042e4425153109955ac","schema_version":"1.0","event_id":"sha256:a70ef9fbc5336780a8f1bac120fc90427da14afab7370042e4425153109955ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:HU22R435ASPHBS4MJ3Q55RE3YB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Spherical Convolution for Fast Features from 360{\\deg} Imagery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kristen Grauman, Yu-Chuan Su","submitted_at":"2017-08-02T20:18:10Z","abstract_excerpt":"While 360{\\deg} cameras offer tremendous new possibilities in vision, graphics, and augmented reality, the spherical images they produce make core feature extraction non-trivial. Convolutional neural networks (CNNs) trained on images from perspective cameras yield \"flat\" filters, yet 360{\\deg} images cannot be projected to a single plane without significant distortion. A naive solution that repeatedly projects the viewing sphere to all tangent planes is accurate, but much too computationally intensive for real problems. We propose to learn a spherical convolutional network that translates a pl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.00919","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":""},"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":"2026-05-17T23:58:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pR7J4n4VQJDpKrKIqQpn7fE/yCQTLqwVV3FhMPx8mwFoO3aZdU94MfhPH9+WAItGM/v7AuCdMs8dLzvaf/UmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T11:39:35.632949Z"},"content_sha256":"7f93a13313a92a9e9f1bce948d55d53e9a0a16f16e9578bcc6d23f3edcde09d3","schema_version":"1.0","event_id":"sha256:7f93a13313a92a9e9f1bce948d55d53e9a0a16f16e9578bcc6d23f3edcde09d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HU22R435ASPHBS4MJ3Q55RE3YB/bundle.json","state_url":"https://pith.science/pith/HU22R435ASPHBS4MJ3Q55RE3YB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HU22R435ASPHBS4MJ3Q55RE3YB/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":"2026-05-27T11:39:35Z","links":{"resolver":"https://pith.science/pith/HU22R435ASPHBS4MJ3Q55RE3YB","bundle":"https://pith.science/pith/HU22R435ASPHBS4MJ3Q55RE3YB/bundle.json","state":"https://pith.science/pith/HU22R435ASPHBS4MJ3Q55RE3YB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HU22R435ASPHBS4MJ3Q55RE3YB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:HU22R435ASPHBS4MJ3Q55RE3YB","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":"dd4bdded7ff5049d776db3382d84228ac79d6367ca743c583e402b70c3835482","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-02T20:18:10Z","title_canon_sha256":"1231a04aff64722a4b759ce1cf4892977d35e9516d378c2633fc541c5970654b"},"schema_version":"1.0","source":{"id":"1708.00919","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.00919","created_at":"2026-05-17T23:58:54Z"},{"alias_kind":"arxiv_version","alias_value":"1708.00919v3","created_at":"2026-05-17T23:58:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.00919","created_at":"2026-05-17T23:58:54Z"},{"alias_kind":"pith_short_12","alias_value":"HU22R435ASPH","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"HU22R435ASPHBS4M","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"HU22R435","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:7f93a13313a92a9e9f1bce948d55d53e9a0a16f16e9578bcc6d23f3edcde09d3","target":"graph","created_at":"2026-05-17T23:58:54Z","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":"While 360{\\deg} cameras offer tremendous new possibilities in vision, graphics, and augmented reality, the spherical images they produce make core feature extraction non-trivial. Convolutional neural networks (CNNs) trained on images from perspective cameras yield \"flat\" filters, yet 360{\\deg} images cannot be projected to a single plane without significant distortion. A naive solution that repeatedly projects the viewing sphere to all tangent planes is accurate, but much too computationally intensive for real problems. We propose to learn a spherical convolutional network that translates a pl","authors_text":"Kristen Grauman, Yu-Chuan Su","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-02T20:18:10Z","title":"Learning Spherical Convolution for Fast Features from 360{\\deg} Imagery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.00919","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:a70ef9fbc5336780a8f1bac120fc90427da14afab7370042e4425153109955ac","target":"record","created_at":"2026-05-17T23:58:54Z","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":"dd4bdded7ff5049d776db3382d84228ac79d6367ca743c583e402b70c3835482","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-02T20:18:10Z","title_canon_sha256":"1231a04aff64722a4b759ce1cf4892977d35e9516d378c2633fc541c5970654b"},"schema_version":"1.0","source":{"id":"1708.00919","kind":"arxiv","version":3}},"canonical_sha256":"3d35a8f37d049e70cb8c4ee1dec49bc043bbd8efd2f525727e1c75a347ceadb4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d35a8f37d049e70cb8c4ee1dec49bc043bbd8efd2f525727e1c75a347ceadb4","first_computed_at":"2026-05-17T23:58:54.698613Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:54.698613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C6z/VNacueGR1cydKn+MaVD/lpacbDrkzo0PEICOrnBp06hcQIXhSrnrSL0nxDUu0WrzUqHo3ksCLPJiOnuWAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:54.699002Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.00919","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a70ef9fbc5336780a8f1bac120fc90427da14afab7370042e4425153109955ac","sha256:7f93a13313a92a9e9f1bce948d55d53e9a0a16f16e9578bcc6d23f3edcde09d3"],"state_sha256":"a97c999c3029ca1b13cdebaa79c09989421b935f5f41ab917cf3c868a159259e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HOvHl7PUj2+648kOS+kLOEUpT5we2bAuj4HbClOzfhAt0C0KTbhC81HtZPx27CpGdFeTt6pofOrUzcpWCP5RDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T11:39:35.636156Z","bundle_sha256":"624a2a4846eea1f8eec408ad667202e101fbb73d7a7970e2f59939239e7f227d"}}