{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:KXI7GGMSX7JJXWRZMQQ54GL7UQ","short_pith_number":"pith:KXI7GGMS","canonical_record":{"source":{"id":"1901.07647","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-22T23:37:43Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"f8366625f57775e0befe6925e8ff641bcf5ed849838a3e93c290f05400113cd7","abstract_canon_sha256":"f50e3a29ca4b096196a1f353b4c8900f706e64fdeb22018787ed71f40a2b2fd0"},"schema_version":"1.0"},"canonical_sha256":"55d1f31992bfd29bda396421de197fa42c68b26bed1242fa8c33d242ba302434","source":{"kind":"arxiv","id":"1901.07647","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.07647","created_at":"2026-05-17T23:46:53Z"},{"alias_kind":"arxiv_version","alias_value":"1901.07647v2","created_at":"2026-05-17T23:46:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07647","created_at":"2026-05-17T23:46:53Z"},{"alias_kind":"pith_short_12","alias_value":"KXI7GGMSX7JJ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KXI7GGMSX7JJXWRZ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KXI7GGMS","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:KXI7GGMSX7JJXWRZMQQ54GL7UQ","target":"record","payload":{"canonical_record":{"source":{"id":"1901.07647","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-22T23:37:43Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"f8366625f57775e0befe6925e8ff641bcf5ed849838a3e93c290f05400113cd7","abstract_canon_sha256":"f50e3a29ca4b096196a1f353b4c8900f706e64fdeb22018787ed71f40a2b2fd0"},"schema_version":"1.0"},"canonical_sha256":"55d1f31992bfd29bda396421de197fa42c68b26bed1242fa8c33d242ba302434","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:53.010047Z","signature_b64":"xStA49LUrilh4j4fTl22cL8jLUSSAbBLhFU7RYuRB8RjM3VVQ+ptL5DDYy37Tdr1mbE2vwIkvzp91OuxtEuXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55d1f31992bfd29bda396421de197fa42c68b26bed1242fa8c33d242ba302434","last_reissued_at":"2026-05-17T23:46:53.009547Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:53.009547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.07647","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":"2026-05-17T23:46:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C5SoSy05I6luDntBwHEY3cKeGwaqWIkUivq5xcXGtHMYRwIgkINCODnZ1OBmkqBWi864sT/XYQzn1uLHOm7QCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T11:57:03.514748Z"},"content_sha256":"175bd99d130850a605d4af4cead152ca7a7d4139208625221a29e1034ba18618","schema_version":"1.0","event_id":"sha256:175bd99d130850a605d4af4cead152ca7a7d4139208625221a29e1034ba18618"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:KXI7GGMSX7JJXWRZMQQ54GL7UQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Geometry of Encoder-Decoder CNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jong Chul Ye, Woon Kyoung Sung","submitted_at":"2019-01-22T23:37:43Z","abstract_excerpt":"Encoder-decoder networks using convolutional neural network (CNN) architecture have been extensively used in deep learning literatures thanks to its excellent performance for various inverse problems. However, it is still difficult to obtain coherent geometric view why such an architecture gives the desired performance. Inspired by recent theoretical understanding on generalizability, expressivity and optimization landscape of neural networks, as well as the theory of convolutional framelets, here we provide a unified theoretical framework that leads to a better understanding of geometry of en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.07647","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":"2026-05-17T23:46:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2QBU14lr3u/0eZGHvaQ0PS/tqaJq/zRBTo67kDspyDZj8QqJjm6rZVGQahSNi2OAiGG4gB0Q7sKvw5kiB3MBAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T11:57:03.515146Z"},"content_sha256":"248a55a0762e3f1f7d1cb3d18f1c516c92892e5105113186465adab862e0fa0b","schema_version":"1.0","event_id":"sha256:248a55a0762e3f1f7d1cb3d18f1c516c92892e5105113186465adab862e0fa0b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KXI7GGMSX7JJXWRZMQQ54GL7UQ/bundle.json","state_url":"https://pith.science/pith/KXI7GGMSX7JJXWRZMQQ54GL7UQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KXI7GGMSX7JJXWRZMQQ54GL7UQ/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":"2026-06-06T11:57:03Z","links":{"resolver":"https://pith.science/pith/KXI7GGMSX7JJXWRZMQQ54GL7UQ","bundle":"https://pith.science/pith/KXI7GGMSX7JJXWRZMQQ54GL7UQ/bundle.json","state":"https://pith.science/pith/KXI7GGMSX7JJXWRZMQQ54GL7UQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KXI7GGMSX7JJXWRZMQQ54GL7UQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KXI7GGMSX7JJXWRZMQQ54GL7UQ","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":"f50e3a29ca4b096196a1f353b4c8900f706e64fdeb22018787ed71f40a2b2fd0","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-22T23:37:43Z","title_canon_sha256":"f8366625f57775e0befe6925e8ff641bcf5ed849838a3e93c290f05400113cd7"},"schema_version":"1.0","source":{"id":"1901.07647","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.07647","created_at":"2026-05-17T23:46:53Z"},{"alias_kind":"arxiv_version","alias_value":"1901.07647v2","created_at":"2026-05-17T23:46:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07647","created_at":"2026-05-17T23:46:53Z"},{"alias_kind":"pith_short_12","alias_value":"KXI7GGMSX7JJ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KXI7GGMSX7JJXWRZ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KXI7GGMS","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:248a55a0762e3f1f7d1cb3d18f1c516c92892e5105113186465adab862e0fa0b","target":"graph","created_at":"2026-05-17T23:46:53Z","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":"Encoder-decoder networks using convolutional neural network (CNN) architecture have been extensively used in deep learning literatures thanks to its excellent performance for various inverse problems. However, it is still difficult to obtain coherent geometric view why such an architecture gives the desired performance. Inspired by recent theoretical understanding on generalizability, expressivity and optimization landscape of neural networks, as well as the theory of convolutional framelets, here we provide a unified theoretical framework that leads to a better understanding of geometry of en","authors_text":"Jong Chul Ye, Woon Kyoung Sung","cross_cats":["cs.AI","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-22T23:37:43Z","title":"Understanding Geometry of Encoder-Decoder CNNs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.07647","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":"sha256:175bd99d130850a605d4af4cead152ca7a7d4139208625221a29e1034ba18618","target":"record","created_at":"2026-05-17T23:46:53Z","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":"f50e3a29ca4b096196a1f353b4c8900f706e64fdeb22018787ed71f40a2b2fd0","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-22T23:37:43Z","title_canon_sha256":"f8366625f57775e0befe6925e8ff641bcf5ed849838a3e93c290f05400113cd7"},"schema_version":"1.0","source":{"id":"1901.07647","kind":"arxiv","version":2}},"canonical_sha256":"55d1f31992bfd29bda396421de197fa42c68b26bed1242fa8c33d242ba302434","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55d1f31992bfd29bda396421de197fa42c68b26bed1242fa8c33d242ba302434","first_computed_at":"2026-05-17T23:46:53.009547Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:53.009547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xStA49LUrilh4j4fTl22cL8jLUSSAbBLhFU7RYuRB8RjM3VVQ+ptL5DDYy37Tdr1mbE2vwIkvzp91OuxtEuXAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:53.010047Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.07647","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:175bd99d130850a605d4af4cead152ca7a7d4139208625221a29e1034ba18618","sha256:248a55a0762e3f1f7d1cb3d18f1c516c92892e5105113186465adab862e0fa0b"],"state_sha256":"184d113f6bbbc33303754121e6b3384d25f06b3d78717cfebec0eff31b127283"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CFUUr4+2S/VlLM+rBipBd3yeHNPdXR511khjXWTkUSoVy9n7fjeQeI2+YMFnerHkxkuA/voEY7CBgKtMdfN1Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T11:57:03.517934Z","bundle_sha256":"de1fd940830a3262302a7cf35ab655177ecc401aadd111cbcfe8bbf3e9f5eee5"}}