{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SLNNXORWFBWO3POBQLKBNS7XY4","short_pith_number":"pith:SLNNXORW","canonical_record":{"source":{"id":"1907.08292","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-16T10:21:15Z","cross_cats_sorted":["cs.AI","math.CT"],"title_canon_sha256":"d6fc497ad2066479df67b93198fb6990d1fefb013ff596610fb26561c5ba4389","abstract_canon_sha256":"d731a2dbe2488c14caa7a1c74f5df1d52a57832475a1b484fc24178416a93e38"},"schema_version":"1.0"},"canonical_sha256":"92dadbba36286cedbdc182d416cbf7c71124319d04fe31071e042dc654b2c70c","source":{"kind":"arxiv","id":"1907.08292","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.08292","created_at":"2026-05-17T23:40:10Z"},{"alias_kind":"arxiv_version","alias_value":"1907.08292v1","created_at":"2026-05-17T23:40:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.08292","created_at":"2026-05-17T23:40:10Z"},{"alias_kind":"pith_short_12","alias_value":"SLNNXORWFBWO","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SLNNXORWFBWO3POB","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SLNNXORW","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SLNNXORWFBWO3POBQLKBNS7XY4","target":"record","payload":{"canonical_record":{"source":{"id":"1907.08292","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-16T10:21:15Z","cross_cats_sorted":["cs.AI","math.CT"],"title_canon_sha256":"d6fc497ad2066479df67b93198fb6990d1fefb013ff596610fb26561c5ba4389","abstract_canon_sha256":"d731a2dbe2488c14caa7a1c74f5df1d52a57832475a1b484fc24178416a93e38"},"schema_version":"1.0"},"canonical_sha256":"92dadbba36286cedbdc182d416cbf7c71124319d04fe31071e042dc654b2c70c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:10.322239Z","signature_b64":"Cm7HeSMpW5RVu5AYD/2UrVX7IQ8nHGUWP+J+bwwklGvHFTf00THQW1T78MtpmcZs4HtXYqSWwFQ2+/xcB2DvAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92dadbba36286cedbdc182d416cbf7c71124319d04fe31071e042dc654b2c70c","last_reissued_at":"2026-05-17T23:40:10.321829Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:10.321829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.08292","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:40:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PNSy1vleob2Z9Py51gTpTmuy6LpwMcBPYvhSN4I1DVlJcahGXnFCv+Oacy8ZMXpHmmSdm5s2prf9PKD9c/9kCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T17:23:14.185213Z"},"content_sha256":"3e439a7ed8c82c90152fedb78bdf5ec134be57019e0dda6cd36c850802a3a920","schema_version":"1.0","event_id":"sha256:3e439a7ed8c82c90152fedb78bdf5ec134be57019e0dda6cd36c850802a3a920"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SLNNXORWFBWO3POBQLKBNS7XY4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compositional Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.CT"],"primary_cat":"cs.LG","authors_text":"Bruno Gavranovi\\'c","submitted_at":"2019-07-16T10:21:15Z","abstract_excerpt":"Neural networks have become an increasingly popular tool for solving many real-world problems. They are a general framework for differentiable optimization which includes many other machine learning approaches as special cases. In this thesis we build a category-theoretic formalism around a class of neural networks exemplified by CycleGAN. CycleGAN is a collection of neural networks, closed under composition, whose inductive bias is increased by enforcing composition invariants, i.e. cycle-consistencies. Inspired by Functorial Data Migration, we specify the interconnection of these networks us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.08292","kind":"arxiv","version":1},"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":"2026-05-17T23:40:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z1BF+vTx4tkw0DIKviV692JHFU6y/CRufLzYf0DM81mtG0vbtCiC7IpFDxQDMWzue9063h+uyJMTZhK6KlG8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T17:23:14.185570Z"},"content_sha256":"b20df8a8cd3af98b03229ed9c93cb9578dfc6ea657bdea7a07874d538c78e1ee","schema_version":"1.0","event_id":"sha256:b20df8a8cd3af98b03229ed9c93cb9578dfc6ea657bdea7a07874d538c78e1ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SLNNXORWFBWO3POBQLKBNS7XY4/bundle.json","state_url":"https://pith.science/pith/SLNNXORWFBWO3POBQLKBNS7XY4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SLNNXORWFBWO3POBQLKBNS7XY4/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":"2026-06-28T17:23:14Z","links":{"resolver":"https://pith.science/pith/SLNNXORWFBWO3POBQLKBNS7XY4","bundle":"https://pith.science/pith/SLNNXORWFBWO3POBQLKBNS7XY4/bundle.json","state":"https://pith.science/pith/SLNNXORWFBWO3POBQLKBNS7XY4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SLNNXORWFBWO3POBQLKBNS7XY4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SLNNXORWFBWO3POBQLKBNS7XY4","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":"d731a2dbe2488c14caa7a1c74f5df1d52a57832475a1b484fc24178416a93e38","cross_cats_sorted":["cs.AI","math.CT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-16T10:21:15Z","title_canon_sha256":"d6fc497ad2066479df67b93198fb6990d1fefb013ff596610fb26561c5ba4389"},"schema_version":"1.0","source":{"id":"1907.08292","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.08292","created_at":"2026-05-17T23:40:10Z"},{"alias_kind":"arxiv_version","alias_value":"1907.08292v1","created_at":"2026-05-17T23:40:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.08292","created_at":"2026-05-17T23:40:10Z"},{"alias_kind":"pith_short_12","alias_value":"SLNNXORWFBWO","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SLNNXORWFBWO3POB","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SLNNXORW","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:b20df8a8cd3af98b03229ed9c93cb9578dfc6ea657bdea7a07874d538c78e1ee","target":"graph","created_at":"2026-05-17T23:40:10Z","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":"Neural networks have become an increasingly popular tool for solving many real-world problems. They are a general framework for differentiable optimization which includes many other machine learning approaches as special cases. In this thesis we build a category-theoretic formalism around a class of neural networks exemplified by CycleGAN. CycleGAN is a collection of neural networks, closed under composition, whose inductive bias is increased by enforcing composition invariants, i.e. cycle-consistencies. Inspired by Functorial Data Migration, we specify the interconnection of these networks us","authors_text":"Bruno Gavranovi\\'c","cross_cats":["cs.AI","math.CT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-16T10:21:15Z","title":"Compositional Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.08292","kind":"arxiv","version":1},"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":"sha256:3e439a7ed8c82c90152fedb78bdf5ec134be57019e0dda6cd36c850802a3a920","target":"record","created_at":"2026-05-17T23:40:10Z","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":"d731a2dbe2488c14caa7a1c74f5df1d52a57832475a1b484fc24178416a93e38","cross_cats_sorted":["cs.AI","math.CT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-16T10:21:15Z","title_canon_sha256":"d6fc497ad2066479df67b93198fb6990d1fefb013ff596610fb26561c5ba4389"},"schema_version":"1.0","source":{"id":"1907.08292","kind":"arxiv","version":1}},"canonical_sha256":"92dadbba36286cedbdc182d416cbf7c71124319d04fe31071e042dc654b2c70c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92dadbba36286cedbdc182d416cbf7c71124319d04fe31071e042dc654b2c70c","first_computed_at":"2026-05-17T23:40:10.321829Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:10.321829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cm7HeSMpW5RVu5AYD/2UrVX7IQ8nHGUWP+J+bwwklGvHFTf00THQW1T78MtpmcZs4HtXYqSWwFQ2+/xcB2DvAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:10.322239Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.08292","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e439a7ed8c82c90152fedb78bdf5ec134be57019e0dda6cd36c850802a3a920","sha256:b20df8a8cd3af98b03229ed9c93cb9578dfc6ea657bdea7a07874d538c78e1ee"],"state_sha256":"d2ac145d1bd309ebfec13058ecb7c9d9c4f0499a1f2d2c1949fcaec44169b151"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e9iTmdMgUM2hZky3lKNPcpM5KiQ+l1XuWGG8vQPj6/6eeCqPizsF9w3+Dt28pxfvThEeWZuDa3vrSVzlzNP0Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T17:23:14.187459Z","bundle_sha256":"0056e2832f080b6a7d39675bbea04c0f8982b8d9f76d653e9a10abc825130566"}}