{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:RFZ3KYG3GM3ZQ7A5MX6Y2B2VM2","short_pith_number":"pith:RFZ3KYG3","canonical_record":{"source":{"id":"1509.05360","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-09-17T18:30:10Z","cross_cats_sorted":[],"title_canon_sha256":"6f273b229810a4a357b904d4299b2f3f84a02370308a8f1a8f254768d15227fd","abstract_canon_sha256":"6102e3b67f84e01b479c65ccbec699848a2352dcec130ec85bcbb3f634d597ae"},"schema_version":"1.0"},"canonical_sha256":"8973b560db3337987c1d65fd8d075566b02f307404bfa2096201091d91890649","source":{"kind":"arxiv","id":"1509.05360","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1509.05360","created_at":"2026-05-18T01:29:53Z"},{"alias_kind":"arxiv_version","alias_value":"1509.05360v2","created_at":"2026-05-18T01:29:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.05360","created_at":"2026-05-18T01:29:53Z"},{"alias_kind":"pith_short_12","alias_value":"RFZ3KYG3GM3Z","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"RFZ3KYG3GM3ZQ7A5","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"RFZ3KYG3","created_at":"2026-05-18T12:29:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:RFZ3KYG3GM3ZQ7A5MX6Y2B2VM2","target":"record","payload":{"canonical_record":{"source":{"id":"1509.05360","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-09-17T18:30:10Z","cross_cats_sorted":[],"title_canon_sha256":"6f273b229810a4a357b904d4299b2f3f84a02370308a8f1a8f254768d15227fd","abstract_canon_sha256":"6102e3b67f84e01b479c65ccbec699848a2352dcec130ec85bcbb3f634d597ae"},"schema_version":"1.0"},"canonical_sha256":"8973b560db3337987c1d65fd8d075566b02f307404bfa2096201091d91890649","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:29:53.661543Z","signature_b64":"1iaAcguqErvaGpTyTE1lLysV3t2OLlo3i2mU65QKJ+7HvRVsTv+YzPkSGXX1dyGj45m/U8KjUuaNKbJsb0MKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8973b560db3337987c1d65fd8d075566b02f307404bfa2096201091d91890649","last_reissued_at":"2026-05-18T01:29:53.661020Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:29:53.661020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1509.05360","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":"2026-05-18T01:29:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AHDloB75PVHjkjfQayOxeWE0eAQ007aW6MEGUKlAUAx1eNGDXe7defWHHsMXx/BGzrgFInofXW9haL9ZDAG8CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T22:29:10.688510Z"},"content_sha256":"dcc962b6b8ec713a6ff09d768dd16e8b86acc50b0bbc8438b340bacfcc434cc6","schema_version":"1.0","event_id":"sha256:dcc962b6b8ec713a6ff09d768dd16e8b86acc50b0bbc8438b340bacfcc434cc6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:RFZ3KYG3GM3ZQ7A5MX6Y2B2VM2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Geometry-aware Deep Transform","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guillermo Sapiro, Jiaji Huang, Qiang Qiu, Robert Calderbank","submitted_at":"2015-09-17T18:30:10Z","abstract_excerpt":"Many recent efforts have been devoted to designing sophisticated deep learning structures, obtaining revolutionary results on benchmark datasets. The success of these deep learning methods mostly relies on an enormous volume of labeled training samples to learn a huge number of parameters in a network; therefore, understanding the generalization ability of a learned deep network cannot be overlooked, especially when restricted to a small training set, which is the case for many applications. In this paper, we propose a novel deep learning objective formulation that unifies both the classificat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.05360","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":"2026-05-18T01:29:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TmSGA9a+1ta+hdZY+Pv1GYgPww1kfm4FTXNXAjwBb5vzS1QYXCDgIsjZVsf2ZVJE5V5LCvz75nAYr/hmrcSKCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T22:29:10.689148Z"},"content_sha256":"5a7daa72152955f5b2e9ae28ce61ef29bf6e3fd7cd56afea5945ea7ea763ce43","schema_version":"1.0","event_id":"sha256:5a7daa72152955f5b2e9ae28ce61ef29bf6e3fd7cd56afea5945ea7ea763ce43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RFZ3KYG3GM3ZQ7A5MX6Y2B2VM2/bundle.json","state_url":"https://pith.science/pith/RFZ3KYG3GM3ZQ7A5MX6Y2B2VM2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RFZ3KYG3GM3ZQ7A5MX6Y2B2VM2/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":"2026-05-28T22:29:10Z","links":{"resolver":"https://pith.science/pith/RFZ3KYG3GM3ZQ7A5MX6Y2B2VM2","bundle":"https://pith.science/pith/RFZ3KYG3GM3ZQ7A5MX6Y2B2VM2/bundle.json","state":"https://pith.science/pith/RFZ3KYG3GM3ZQ7A5MX6Y2B2VM2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RFZ3KYG3GM3ZQ7A5MX6Y2B2VM2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:RFZ3KYG3GM3ZQ7A5MX6Y2B2VM2","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":"6102e3b67f84e01b479c65ccbec699848a2352dcec130ec85bcbb3f634d597ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-09-17T18:30:10Z","title_canon_sha256":"6f273b229810a4a357b904d4299b2f3f84a02370308a8f1a8f254768d15227fd"},"schema_version":"1.0","source":{"id":"1509.05360","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1509.05360","created_at":"2026-05-18T01:29:53Z"},{"alias_kind":"arxiv_version","alias_value":"1509.05360v2","created_at":"2026-05-18T01:29:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.05360","created_at":"2026-05-18T01:29:53Z"},{"alias_kind":"pith_short_12","alias_value":"RFZ3KYG3GM3Z","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"RFZ3KYG3GM3ZQ7A5","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"RFZ3KYG3","created_at":"2026-05-18T12:29:39Z"}],"graph_snapshots":[{"event_id":"sha256:5a7daa72152955f5b2e9ae28ce61ef29bf6e3fd7cd56afea5945ea7ea763ce43","target":"graph","created_at":"2026-05-18T01:29:53Z","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 recent efforts have been devoted to designing sophisticated deep learning structures, obtaining revolutionary results on benchmark datasets. The success of these deep learning methods mostly relies on an enormous volume of labeled training samples to learn a huge number of parameters in a network; therefore, understanding the generalization ability of a learned deep network cannot be overlooked, especially when restricted to a small training set, which is the case for many applications. In this paper, we propose a novel deep learning objective formulation that unifies both the classificat","authors_text":"Guillermo Sapiro, Jiaji Huang, Qiang Qiu, Robert Calderbank","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-09-17T18:30:10Z","title":"Geometry-aware Deep Transform"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.05360","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:dcc962b6b8ec713a6ff09d768dd16e8b86acc50b0bbc8438b340bacfcc434cc6","target":"record","created_at":"2026-05-18T01:29:53Z","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":"6102e3b67f84e01b479c65ccbec699848a2352dcec130ec85bcbb3f634d597ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-09-17T18:30:10Z","title_canon_sha256":"6f273b229810a4a357b904d4299b2f3f84a02370308a8f1a8f254768d15227fd"},"schema_version":"1.0","source":{"id":"1509.05360","kind":"arxiv","version":2}},"canonical_sha256":"8973b560db3337987c1d65fd8d075566b02f307404bfa2096201091d91890649","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8973b560db3337987c1d65fd8d075566b02f307404bfa2096201091d91890649","first_computed_at":"2026-05-18T01:29:53.661020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:29:53.661020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1iaAcguqErvaGpTyTE1lLysV3t2OLlo3i2mU65QKJ+7HvRVsTv+YzPkSGXX1dyGj45m/U8KjUuaNKbJsb0MKCg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:29:53.661543Z","signed_message":"canonical_sha256_bytes"},"source_id":"1509.05360","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcc962b6b8ec713a6ff09d768dd16e8b86acc50b0bbc8438b340bacfcc434cc6","sha256:5a7daa72152955f5b2e9ae28ce61ef29bf6e3fd7cd56afea5945ea7ea763ce43"],"state_sha256":"3f0dcf124055676f1ce793be7a54c497472aba1149a37c05023999548caec377"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a3nDopqNDuViEQbR1vcE8tonBqczMsfv6Eysg4HIEob7F5TME3Pqlk2L402OF4qn2TbPSJlQI3u8GefXYPVVBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T22:29:10.692151Z","bundle_sha256":"9c46b19252a0fcf896638fd6e393da0d3f2f24b24bfb944a45120741015ddfbb"}}