{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4NLU3J4KEBR4B4IFCW36RT7OGZ","short_pith_number":"pith:4NLU3J4K","canonical_record":{"source":{"id":"2506.20469","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2025-06-25T14:18:17Z","cross_cats_sorted":[],"title_canon_sha256":"53610ff6dda45450bb7a903e95544c1bd86cca411572ab1fdade3975d3bb5a6e","abstract_canon_sha256":"c25e3db1c82dbeb6cfb848422179c635c91e05945cb95bf231664dcdcdd01212"},"schema_version":"1.0"},"canonical_sha256":"e3574da78a2063c0f10515b7e8cfee36496c3194c8abd355bf94cc84b4172961","source":{"kind":"arxiv","id":"2506.20469","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20469","created_at":"2026-07-05T11:27:06Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20469v1","created_at":"2026-07-05T11:27:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20469","created_at":"2026-07-05T11:27:06Z"},{"alias_kind":"pith_short_12","alias_value":"4NLU3J4KEBR4","created_at":"2026-07-05T11:27:06Z"},{"alias_kind":"pith_short_16","alias_value":"4NLU3J4KEBR4B4IF","created_at":"2026-07-05T11:27:06Z"},{"alias_kind":"pith_short_8","alias_value":"4NLU3J4K","created_at":"2026-07-05T11:27:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4NLU3J4KEBR4B4IFCW36RT7OGZ","target":"record","payload":{"canonical_record":{"source":{"id":"2506.20469","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2025-06-25T14:18:17Z","cross_cats_sorted":[],"title_canon_sha256":"53610ff6dda45450bb7a903e95544c1bd86cca411572ab1fdade3975d3bb5a6e","abstract_canon_sha256":"c25e3db1c82dbeb6cfb848422179c635c91e05945cb95bf231664dcdcdd01212"},"schema_version":"1.0"},"canonical_sha256":"e3574da78a2063c0f10515b7e8cfee36496c3194c8abd355bf94cc84b4172961","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:06.273290Z","signature_b64":"pQ+8F6TDyAm5cnmPM7r5vbELyyZjgy1ruMEHw2ff7svChxs1N1r35MgwAnlaXDuZ1VSrjqhBlp4nPMwLkxxcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3574da78a2063c0f10515b7e8cfee36496c3194c8abd355bf94cc84b4172961","last_reissued_at":"2026-07-05T11:27:06.272874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:06.272874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.20469","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":"2026-07-05T11:27:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eDS1OzZ/NRwyv6bWaKT01xJJEjXlLaLNw0l8gMDalDfvtLRvShnfGyq0lhnVmeruoR37iksGmH2p2LfOksOuAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:21:31.854212Z"},"content_sha256":"fa33f5fb02491664d0d54759dcf15ecabc9cf2bde2340837079478cf2a784a30","schema_version":"1.0","event_id":"sha256:fa33f5fb02491664d0d54759dcf15ecabc9cf2bde2340837079478cf2a784a30"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4NLU3J4KEBR4B4IFCW36RT7OGZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Surrogate-Assisted Evolution for Efficient Multi-branch Connection Design in Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Daniel Garc\\'ia N\\'u\\~nez, Edgar Galv\\'an, Fergal Stapleton, Yanan Sun","submitted_at":"2025-06-25T14:18:17Z","abstract_excerpt":"State-of-the-art Deep Neural Networks (DNNs) often incorporate multi-branch connections, enabling multi-scale feature extraction and enhancing the capture of diverse features. This design improves network capacity and generalisation to unseen data. However, training such DNNs can be computationally expensive. The challenge is further exacerbated by the complexity of identifying optimal network architectures. To address this, we leverage Evolutionary Algorithms (EAs) to automatically discover high-performing architectures, a process commonly known as neuroevolution. We introduce a novel approac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20469","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.20469/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T11:27:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8I9oQL4d67KmZkzIHjiG3blh1pS1e7z+DdnP8an/MQMYMD6KVbAO68l+bV1Cw7WcZj757iEjzNCJYoqzJ/ixCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:21:31.855164Z"},"content_sha256":"4d1f3d2851883a76feb0630023b0099fe1f0e3c93f80b16fcf9a45a1ad734b8d","schema_version":"1.0","event_id":"sha256:4d1f3d2851883a76feb0630023b0099fe1f0e3c93f80b16fcf9a45a1ad734b8d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4NLU3J4KEBR4B4IFCW36RT7OGZ/bundle.json","state_url":"https://pith.science/pith/4NLU3J4KEBR4B4IFCW36RT7OGZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4NLU3J4KEBR4B4IFCW36RT7OGZ/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":"2026-08-11T02:21:31Z","links":{"resolver":"https://pith.science/pith/4NLU3J4KEBR4B4IFCW36RT7OGZ","bundle":"https://pith.science/pith/4NLU3J4KEBR4B4IFCW36RT7OGZ/bundle.json","state":"https://pith.science/pith/4NLU3J4KEBR4B4IFCW36RT7OGZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4NLU3J4KEBR4B4IFCW36RT7OGZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4NLU3J4KEBR4B4IFCW36RT7OGZ","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":"c25e3db1c82dbeb6cfb848422179c635c91e05945cb95bf231664dcdcdd01212","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2025-06-25T14:18:17Z","title_canon_sha256":"53610ff6dda45450bb7a903e95544c1bd86cca411572ab1fdade3975d3bb5a6e"},"schema_version":"1.0","source":{"id":"2506.20469","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20469","created_at":"2026-07-05T11:27:06Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20469v1","created_at":"2026-07-05T11:27:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20469","created_at":"2026-07-05T11:27:06Z"},{"alias_kind":"pith_short_12","alias_value":"4NLU3J4KEBR4","created_at":"2026-07-05T11:27:06Z"},{"alias_kind":"pith_short_16","alias_value":"4NLU3J4KEBR4B4IF","created_at":"2026-07-05T11:27:06Z"},{"alias_kind":"pith_short_8","alias_value":"4NLU3J4K","created_at":"2026-07-05T11:27:06Z"}],"graph_snapshots":[{"event_id":"sha256:4d1f3d2851883a76feb0630023b0099fe1f0e3c93f80b16fcf9a45a1ad734b8d","target":"graph","created_at":"2026-07-05T11:27:06Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.20469/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art Deep Neural Networks (DNNs) often incorporate multi-branch connections, enabling multi-scale feature extraction and enhancing the capture of diverse features. This design improves network capacity and generalisation to unseen data. However, training such DNNs can be computationally expensive. The challenge is further exacerbated by the complexity of identifying optimal network architectures. To address this, we leverage Evolutionary Algorithms (EAs) to automatically discover high-performing architectures, a process commonly known as neuroevolution. We introduce a novel approac","authors_text":"Daniel Garc\\'ia N\\'u\\~nez, Edgar Galv\\'an, Fergal Stapleton, Yanan Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2025-06-25T14:18:17Z","title":"Surrogate-Assisted Evolution for Efficient Multi-branch Connection Design in Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20469","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:fa33f5fb02491664d0d54759dcf15ecabc9cf2bde2340837079478cf2a784a30","target":"record","created_at":"2026-07-05T11:27:06Z","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":"c25e3db1c82dbeb6cfb848422179c635c91e05945cb95bf231664dcdcdd01212","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2025-06-25T14:18:17Z","title_canon_sha256":"53610ff6dda45450bb7a903e95544c1bd86cca411572ab1fdade3975d3bb5a6e"},"schema_version":"1.0","source":{"id":"2506.20469","kind":"arxiv","version":1}},"canonical_sha256":"e3574da78a2063c0f10515b7e8cfee36496c3194c8abd355bf94cc84b4172961","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3574da78a2063c0f10515b7e8cfee36496c3194c8abd355bf94cc84b4172961","first_computed_at":"2026-07-05T11:27:06.272874Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:06.272874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pQ+8F6TDyAm5cnmPM7r5vbELyyZjgy1ruMEHw2ff7svChxs1N1r35MgwAnlaXDuZ1VSrjqhBlp4nPMwLkxxcBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:06.273290Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.20469","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa33f5fb02491664d0d54759dcf15ecabc9cf2bde2340837079478cf2a784a30","sha256:4d1f3d2851883a76feb0630023b0099fe1f0e3c93f80b16fcf9a45a1ad734b8d"],"state_sha256":"71aab33c26915f0494531a9c18e6ecbfa6d5dcb2d74dce284ce35659cec74165"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fbtZ3eaS+0ayDLGw7p14xcaXF/JEkoCTrf6Td3MbHxKcPkQM1GEYLbCLye7n0bHJ+BGCaibiYmjrwF1d5WNpCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T02:21:31.863723Z","bundle_sha256":"924c6f89d5a3e1be735916bd6aaa7df515f56e2bbe52ff0dfa98f953cff3a6be"}}