{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:WKCLKJXEESAV2XYKGWL2S4AMD5","short_pith_number":"pith:WKCLKJXE","canonical_record":{"source":{"id":"2008.08261","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-19T04:53:31Z","cross_cats_sorted":[],"title_canon_sha256":"97a291279831cb19b1bd7c2a7d00bc0396103b9758b333042cb1387e9c35c364","abstract_canon_sha256":"8fd948f04ee3cc79a70e3601f8180a596e7fe00c52c9f0cc7763ca032fdfc580"},"schema_version":"1.0"},"canonical_sha256":"b284b526e424815d5f0a3597a9700c1f618a1b66ffae54111c2ac8a10dbeb3a7","source":{"kind":"arxiv","id":"2008.08261","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.08261","created_at":"2026-07-05T01:28:24Z"},{"alias_kind":"arxiv_version","alias_value":"2008.08261v1","created_at":"2026-07-05T01:28:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.08261","created_at":"2026-07-05T01:28:24Z"},{"alias_kind":"pith_short_12","alias_value":"WKCLKJXEESAV","created_at":"2026-07-05T01:28:24Z"},{"alias_kind":"pith_short_16","alias_value":"WKCLKJXEESAV2XYK","created_at":"2026-07-05T01:28:24Z"},{"alias_kind":"pith_short_8","alias_value":"WKCLKJXE","created_at":"2026-07-05T01:28:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:WKCLKJXEESAV2XYKGWL2S4AMD5","target":"record","payload":{"canonical_record":{"source":{"id":"2008.08261","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-19T04:53:31Z","cross_cats_sorted":[],"title_canon_sha256":"97a291279831cb19b1bd7c2a7d00bc0396103b9758b333042cb1387e9c35c364","abstract_canon_sha256":"8fd948f04ee3cc79a70e3601f8180a596e7fe00c52c9f0cc7763ca032fdfc580"},"schema_version":"1.0"},"canonical_sha256":"b284b526e424815d5f0a3597a9700c1f618a1b66ffae54111c2ac8a10dbeb3a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:28:24.056340Z","signature_b64":"8SqUomd+R0sM8l3VyfS9L08Q1YcgcRLJY9jfIadcxSbXvagAIUDyGN4FS0p7AjMbxJzU0NZJ2RIsSbAKCVB6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b284b526e424815d5f0a3597a9700c1f618a1b66ffae54111c2ac8a10dbeb3a7","last_reissued_at":"2026-07-05T01:28:24.055985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:28:24.055985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.08261","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":"2026-07-05T01:28:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8W6VCsake0Q37u82XQGSROm7GZKBQ8mueie65TbGsIFUf+wg5XPN9oBE7zqJHiCp0u9PeUsdWDLIY7165YlwAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:24:39.371920Z"},"content_sha256":"44c194958a919c7d214f8129fdb1119e7bbff09b57c4dba7ca4624a53f18afc5","schema_version":"1.0","event_id":"sha256:44c194958a919c7d214f8129fdb1119e7bbff09b57c4dba7ca4624a53f18afc5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:WKCLKJXEESAV2XYKGWL2S4AMD5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Connectivity of Neural Networks from a Topological Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Shao, Junjie Yan, Kun Yuan, Quanquan Li","submitted_at":"2020-08-19T04:53:31Z","abstract_excerpt":"Seeking effective neural networks is a critical and practical field in deep learning. Besides designing the depth, type of convolution, normalization, and nonlinearities, the topological connectivity of neural networks is also important. Previous principles of rule-based modular design simplify the difficulty of building an effective architecture, but constrain the possible topologies in limited spaces. In this paper, we attempt to optimize the connectivity in neural networks. We propose a topological perspective to represent a network into a complete graph for analysis, where nodes carry out "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.08261","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/2008.08261/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":"2026-07-05T01:28:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i5iEOU86LPgyrPh0kslYeHLqRZWVFhhWDdDROyp0qxG9KuCZfVZDoZANDLCofWj9rfylnTaR6YX2qL+j1d8lBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:24:39.372429Z"},"content_sha256":"29b5bcafdf088dee330eee079796b75c8f6f7831210e20e0175d25a9280982a7","schema_version":"1.0","event_id":"sha256:29b5bcafdf088dee330eee079796b75c8f6f7831210e20e0175d25a9280982a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WKCLKJXEESAV2XYKGWL2S4AMD5/bundle.json","state_url":"https://pith.science/pith/WKCLKJXEESAV2XYKGWL2S4AMD5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WKCLKJXEESAV2XYKGWL2S4AMD5/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":"2026-08-04T19:24:39Z","links":{"resolver":"https://pith.science/pith/WKCLKJXEESAV2XYKGWL2S4AMD5","bundle":"https://pith.science/pith/WKCLKJXEESAV2XYKGWL2S4AMD5/bundle.json","state":"https://pith.science/pith/WKCLKJXEESAV2XYKGWL2S4AMD5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WKCLKJXEESAV2XYKGWL2S4AMD5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:WKCLKJXEESAV2XYKGWL2S4AMD5","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":"8fd948f04ee3cc79a70e3601f8180a596e7fe00c52c9f0cc7763ca032fdfc580","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-19T04:53:31Z","title_canon_sha256":"97a291279831cb19b1bd7c2a7d00bc0396103b9758b333042cb1387e9c35c364"},"schema_version":"1.0","source":{"id":"2008.08261","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.08261","created_at":"2026-07-05T01:28:24Z"},{"alias_kind":"arxiv_version","alias_value":"2008.08261v1","created_at":"2026-07-05T01:28:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.08261","created_at":"2026-07-05T01:28:24Z"},{"alias_kind":"pith_short_12","alias_value":"WKCLKJXEESAV","created_at":"2026-07-05T01:28:24Z"},{"alias_kind":"pith_short_16","alias_value":"WKCLKJXEESAV2XYK","created_at":"2026-07-05T01:28:24Z"},{"alias_kind":"pith_short_8","alias_value":"WKCLKJXE","created_at":"2026-07-05T01:28:24Z"}],"graph_snapshots":[{"event_id":"sha256:29b5bcafdf088dee330eee079796b75c8f6f7831210e20e0175d25a9280982a7","target":"graph","created_at":"2026-07-05T01:28:24Z","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/2008.08261/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Seeking effective neural networks is a critical and practical field in deep learning. Besides designing the depth, type of convolution, normalization, and nonlinearities, the topological connectivity of neural networks is also important. Previous principles of rule-based modular design simplify the difficulty of building an effective architecture, but constrain the possible topologies in limited spaces. In this paper, we attempt to optimize the connectivity in neural networks. We propose a topological perspective to represent a network into a complete graph for analysis, where nodes carry out ","authors_text":"Jing Shao, Junjie Yan, Kun Yuan, Quanquan Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-19T04:53:31Z","title":"Learning Connectivity of Neural Networks from a Topological Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.08261","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":"sha256:44c194958a919c7d214f8129fdb1119e7bbff09b57c4dba7ca4624a53f18afc5","target":"record","created_at":"2026-07-05T01:28:24Z","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":"8fd948f04ee3cc79a70e3601f8180a596e7fe00c52c9f0cc7763ca032fdfc580","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-19T04:53:31Z","title_canon_sha256":"97a291279831cb19b1bd7c2a7d00bc0396103b9758b333042cb1387e9c35c364"},"schema_version":"1.0","source":{"id":"2008.08261","kind":"arxiv","version":1}},"canonical_sha256":"b284b526e424815d5f0a3597a9700c1f618a1b66ffae54111c2ac8a10dbeb3a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b284b526e424815d5f0a3597a9700c1f618a1b66ffae54111c2ac8a10dbeb3a7","first_computed_at":"2026-07-05T01:28:24.055985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:28:24.055985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8SqUomd+R0sM8l3VyfS9L08Q1YcgcRLJY9jfIadcxSbXvagAIUDyGN4FS0p7AjMbxJzU0NZJ2RIsSbAKCVB6DA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:28:24.056340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.08261","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44c194958a919c7d214f8129fdb1119e7bbff09b57c4dba7ca4624a53f18afc5","sha256:29b5bcafdf088dee330eee079796b75c8f6f7831210e20e0175d25a9280982a7"],"state_sha256":"8b2070da4061fabe2e14a8a17851373605f58739dd7cd40fe2fc12c21c0b5e0e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aD++dJiVLCOSyECa24a0zXnAtUsFNPVF5WuEm2tGAV0YHba6zkVd47BJktTZx7AR5QLVZU8jxJiVCgD19B8pBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:24:39.391798Z","bundle_sha256":"05ca4c24bddf043e9ae89f557d6b9d10732594d43e7fb4f61998acb2445a1258"}}