{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:IBNH6NVZ5BUITBSCZZAKV5HBDX","short_pith_number":"pith:IBNH6NVZ","canonical_record":{"source":{"id":"1811.05249","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-13T12:24:23Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4933f55af4514127e6775313211dc42f31280cefaceaf2dbc4f72bf6d1289e4c","abstract_canon_sha256":"7690b1b05141f187b45493e4c6eee7e4ed1a9bca6930bf3aa3759c357f2340b3"},"schema_version":"1.0"},"canonical_sha256":"405a7f36b9e868898642ce40aaf4e11dca69fe7fbe043323d137c95f03315450","source":{"kind":"arxiv","id":"1811.05249","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.05249","created_at":"2026-05-18T00:00:46Z"},{"alias_kind":"arxiv_version","alias_value":"1811.05249v1","created_at":"2026-05-18T00:00:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.05249","created_at":"2026-05-18T00:00:46Z"},{"alias_kind":"pith_short_12","alias_value":"IBNH6NVZ5BUI","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"IBNH6NVZ5BUITBSC","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"IBNH6NVZ","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:IBNH6NVZ5BUITBSCZZAKV5HBDX","target":"record","payload":{"canonical_record":{"source":{"id":"1811.05249","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-13T12:24:23Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4933f55af4514127e6775313211dc42f31280cefaceaf2dbc4f72bf6d1289e4c","abstract_canon_sha256":"7690b1b05141f187b45493e4c6eee7e4ed1a9bca6930bf3aa3759c357f2340b3"},"schema_version":"1.0"},"canonical_sha256":"405a7f36b9e868898642ce40aaf4e11dca69fe7fbe043323d137c95f03315450","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:46.522990Z","signature_b64":"PLHjsnjYMHAdeIdY1LJCMZgXPEZnuHlKWa2WgJyv6rUehqPC8eADzXSgFy50vbJI5Wwl3D2HSfTFDPL6HxsZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"405a7f36b9e868898642ce40aaf4e11dca69fe7fbe043323d137c95f03315450","last_reissued_at":"2026-05-18T00:00:46.522406Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:46.522406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.05249","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":"2026-05-18T00:00:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UOzIMRPQBuSx+9efA+g6zTKPBHwSykqUtKa2TVMLxQaTdAiHIl14DBAtKIiqg835PxhsuK4wGeLW/bPIJyitDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T12:27:47.041142Z"},"content_sha256":"1fa94ccd220593235d2438708c45b3d7d7809376396e32ea7f2edfb437f27060","schema_version":"1.0","event_id":"sha256:1fa94ccd220593235d2438708c45b3d7d7809376396e32ea7f2edfb437f27060"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:IBNH6NVZ5BUITBSCZZAKV5HBDX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modular Networks: Learning to Decompose Neural Computation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Barber, Julius Kunze, Louis Kirsch","submitted_at":"2018-11-13T12:24:23Z","abstract_excerpt":"Scaling model capacity has been vital in the success of deep learning. For a typical network, necessary compute resources and training time grow dramatically with model size. Conditional computation is a promising way to increase the number of parameters with a relatively small increase in resources. We propose a training algorithm that flexibly chooses neural modules based on the data to be processed. Both the decomposition and modules are learned end-to-end. In contrast to existing approaches, training does not rely on regularization to enforce diversity in module use. We apply modular netwo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.05249","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":"2026-05-18T00:00:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bCQpz0hsqP9vFxV/WhKWsEK0Pehw+z9/O8Y1cpuNQkJ7CmXkftJ4JgxBTgnU3I22UNbpoVok2JY4LuCI41J3Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T12:27:47.041527Z"},"content_sha256":"fd12dd745d6bcc4244f9b52c1a150816b1dc23e542c99acc7bc21d1fbd549f92","schema_version":"1.0","event_id":"sha256:fd12dd745d6bcc4244f9b52c1a150816b1dc23e542c99acc7bc21d1fbd549f92"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IBNH6NVZ5BUITBSCZZAKV5HBDX/bundle.json","state_url":"https://pith.science/pith/IBNH6NVZ5BUITBSCZZAKV5HBDX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IBNH6NVZ5BUITBSCZZAKV5HBDX/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":"2026-06-23T12:27:47Z","links":{"resolver":"https://pith.science/pith/IBNH6NVZ5BUITBSCZZAKV5HBDX","bundle":"https://pith.science/pith/IBNH6NVZ5BUITBSCZZAKV5HBDX/bundle.json","state":"https://pith.science/pith/IBNH6NVZ5BUITBSCZZAKV5HBDX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IBNH6NVZ5BUITBSCZZAKV5HBDX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:IBNH6NVZ5BUITBSCZZAKV5HBDX","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":"7690b1b05141f187b45493e4c6eee7e4ed1a9bca6930bf3aa3759c357f2340b3","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-13T12:24:23Z","title_canon_sha256":"4933f55af4514127e6775313211dc42f31280cefaceaf2dbc4f72bf6d1289e4c"},"schema_version":"1.0","source":{"id":"1811.05249","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.05249","created_at":"2026-05-18T00:00:46Z"},{"alias_kind":"arxiv_version","alias_value":"1811.05249v1","created_at":"2026-05-18T00:00:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.05249","created_at":"2026-05-18T00:00:46Z"},{"alias_kind":"pith_short_12","alias_value":"IBNH6NVZ5BUI","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"IBNH6NVZ5BUITBSC","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"IBNH6NVZ","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:fd12dd745d6bcc4244f9b52c1a150816b1dc23e542c99acc7bc21d1fbd549f92","target":"graph","created_at":"2026-05-18T00:00:46Z","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":"Scaling model capacity has been vital in the success of deep learning. For a typical network, necessary compute resources and training time grow dramatically with model size. Conditional computation is a promising way to increase the number of parameters with a relatively small increase in resources. We propose a training algorithm that flexibly chooses neural modules based on the data to be processed. Both the decomposition and modules are learned end-to-end. In contrast to existing approaches, training does not rely on regularization to enforce diversity in module use. We apply modular netwo","authors_text":"David Barber, Julius Kunze, Louis Kirsch","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-13T12:24:23Z","title":"Modular Networks: Learning to Decompose Neural Computation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.05249","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":"sha256:1fa94ccd220593235d2438708c45b3d7d7809376396e32ea7f2edfb437f27060","target":"record","created_at":"2026-05-18T00:00:46Z","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":"7690b1b05141f187b45493e4c6eee7e4ed1a9bca6930bf3aa3759c357f2340b3","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-13T12:24:23Z","title_canon_sha256":"4933f55af4514127e6775313211dc42f31280cefaceaf2dbc4f72bf6d1289e4c"},"schema_version":"1.0","source":{"id":"1811.05249","kind":"arxiv","version":1}},"canonical_sha256":"405a7f36b9e868898642ce40aaf4e11dca69fe7fbe043323d137c95f03315450","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"405a7f36b9e868898642ce40aaf4e11dca69fe7fbe043323d137c95f03315450","first_computed_at":"2026-05-18T00:00:46.522406Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:46.522406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PLHjsnjYMHAdeIdY1LJCMZgXPEZnuHlKWa2WgJyv6rUehqPC8eADzXSgFy50vbJI5Wwl3D2HSfTFDPL6HxsZCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:46.522990Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.05249","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1fa94ccd220593235d2438708c45b3d7d7809376396e32ea7f2edfb437f27060","sha256:fd12dd745d6bcc4244f9b52c1a150816b1dc23e542c99acc7bc21d1fbd549f92"],"state_sha256":"a97a4eb9972a3bac3b9eaa46aa63a6db47247f86dbf1b8c845ee338909956077"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L2p7ykC4hFhLCf9CqQPykZQCG3HmSt/5B2XnRRYDyrz8CJlPuEhkDe6x4L2m1x6es3ZeNGCZ2QrK6dhLk9MXBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-23T12:27:47.043490Z","bundle_sha256":"f509409fb78b64e57ed118151c8f20ec5690c79cde8a1c08c71cb89ef85e6976"}}