{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:BLIYWSIPO5L3FFSZMHSNP7UG7X","short_pith_number":"pith:BLIYWSIP","canonical_record":{"source":{"id":"1804.02201","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-06T10:55:16Z","cross_cats_sorted":[],"title_canon_sha256":"0271cd8636f81ee2a884223cc7244bdf3ac88d57bff9475d4be2ac31c2b66a8d","abstract_canon_sha256":"da0152f3beee24f8148267a9348da1abd13ea230199279d213069be09f656e2f"},"schema_version":"1.0"},"canonical_sha256":"0ad18b490f7757b2965961e4d7fe86fdfc04786d30a4f257b7e694e2c2a9b323","source":{"kind":"arxiv","id":"1804.02201","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.02201","created_at":"2026-05-18T00:19:05Z"},{"alias_kind":"arxiv_version","alias_value":"1804.02201v1","created_at":"2026-05-18T00:19:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02201","created_at":"2026-05-18T00:19:05Z"},{"alias_kind":"pith_short_12","alias_value":"BLIYWSIPO5L3","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"BLIYWSIPO5L3FFSZ","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"BLIYWSIP","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:BLIYWSIPO5L3FFSZMHSNP7UG7X","target":"record","payload":{"canonical_record":{"source":{"id":"1804.02201","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-06T10:55:16Z","cross_cats_sorted":[],"title_canon_sha256":"0271cd8636f81ee2a884223cc7244bdf3ac88d57bff9475d4be2ac31c2b66a8d","abstract_canon_sha256":"da0152f3beee24f8148267a9348da1abd13ea230199279d213069be09f656e2f"},"schema_version":"1.0"},"canonical_sha256":"0ad18b490f7757b2965961e4d7fe86fdfc04786d30a4f257b7e694e2c2a9b323","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:05.569056Z","signature_b64":"o1Ha0my4X5xicTMvoWyU1HxG4Aat9w9INSaLnaRYYvv4cERB68lYFIVn39f5SKV37yBm2dz8cimSURr72MQPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ad18b490f7757b2965961e4d7fe86fdfc04786d30a4f257b7e694e2c2a9b323","last_reissued_at":"2026-05-18T00:19:05.568442Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:05.568442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.02201","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":"2026-05-18T00:19:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NeGBEB7O6TSNX/0+idWyOdRUgB57CKS50IOUoEw/AVGb+9OrvXN/9CQ8PBEHzbC8Bxo4LZXp58hL468fzDFzAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T18:45:22.099611Z"},"content_sha256":"8fb83ed45f3bd23b043420224d1cd0dcbdee95fba96e8d42b300fa1ed28e0a9e","schema_version":"1.0","event_id":"sha256:8fb83ed45f3bd23b043420224d1cd0dcbdee95fba96e8d42b300fa1ed28e0a9e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:BLIYWSIPO5L3FFSZMHSNP7UG7X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ensemble Manifold Segmentation for Model Distillation and Semi-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dengxin Dai, Luc Van Gool, Till Kroeger, Wen Li","submitted_at":"2018-04-06T10:55:16Z","abstract_excerpt":"Manifold theory has been the central concept of many learning methods. However, learning modern CNNs with manifold structures has not raised due attention, mainly because of the inconvenience of imposing manifold structures onto the architecture of the CNNs. In this paper we present ManifoldNet, a novel method to encourage learning of manifold-aware representations. Our approach segments the input manifold into a set of fragments. By assigning the corresponding segmentation id as a pseudo label to every sample, we convert the problem of preserving the local manifold structure into a point-wise"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02201","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":"2026-05-18T00:19:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VhiYOc4aK05t1KX6iQ8Y97kkXTZtOZ5xthulpx5j1G01L74B+e6FoyD+cNLj9F2k1Ewv98d3VFsl07aavdVoCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T18:45:22.100456Z"},"content_sha256":"ff829b5a0719376a977439d66bf7f0b5990cd2246a75bc6e9651fd171a14df39","schema_version":"1.0","event_id":"sha256:ff829b5a0719376a977439d66bf7f0b5990cd2246a75bc6e9651fd171a14df39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BLIYWSIPO5L3FFSZMHSNP7UG7X/bundle.json","state_url":"https://pith.science/pith/BLIYWSIPO5L3FFSZMHSNP7UG7X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BLIYWSIPO5L3FFSZMHSNP7UG7X/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":"2026-05-30T18:45:22Z","links":{"resolver":"https://pith.science/pith/BLIYWSIPO5L3FFSZMHSNP7UG7X","bundle":"https://pith.science/pith/BLIYWSIPO5L3FFSZMHSNP7UG7X/bundle.json","state":"https://pith.science/pith/BLIYWSIPO5L3FFSZMHSNP7UG7X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BLIYWSIPO5L3FFSZMHSNP7UG7X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:BLIYWSIPO5L3FFSZMHSNP7UG7X","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":"da0152f3beee24f8148267a9348da1abd13ea230199279d213069be09f656e2f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-06T10:55:16Z","title_canon_sha256":"0271cd8636f81ee2a884223cc7244bdf3ac88d57bff9475d4be2ac31c2b66a8d"},"schema_version":"1.0","source":{"id":"1804.02201","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.02201","created_at":"2026-05-18T00:19:05Z"},{"alias_kind":"arxiv_version","alias_value":"1804.02201v1","created_at":"2026-05-18T00:19:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02201","created_at":"2026-05-18T00:19:05Z"},{"alias_kind":"pith_short_12","alias_value":"BLIYWSIPO5L3","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"BLIYWSIPO5L3FFSZ","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"BLIYWSIP","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:ff829b5a0719376a977439d66bf7f0b5990cd2246a75bc6e9651fd171a14df39","target":"graph","created_at":"2026-05-18T00:19:05Z","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":"Manifold theory has been the central concept of many learning methods. However, learning modern CNNs with manifold structures has not raised due attention, mainly because of the inconvenience of imposing manifold structures onto the architecture of the CNNs. In this paper we present ManifoldNet, a novel method to encourage learning of manifold-aware representations. Our approach segments the input manifold into a set of fragments. By assigning the corresponding segmentation id as a pseudo label to every sample, we convert the problem of preserving the local manifold structure into a point-wise","authors_text":"Dengxin Dai, Luc Van Gool, Till Kroeger, Wen Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-06T10:55:16Z","title":"Ensemble Manifold Segmentation for Model Distillation and Semi-supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02201","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":"sha256:8fb83ed45f3bd23b043420224d1cd0dcbdee95fba96e8d42b300fa1ed28e0a9e","target":"record","created_at":"2026-05-18T00:19:05Z","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":"da0152f3beee24f8148267a9348da1abd13ea230199279d213069be09f656e2f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-06T10:55:16Z","title_canon_sha256":"0271cd8636f81ee2a884223cc7244bdf3ac88d57bff9475d4be2ac31c2b66a8d"},"schema_version":"1.0","source":{"id":"1804.02201","kind":"arxiv","version":1}},"canonical_sha256":"0ad18b490f7757b2965961e4d7fe86fdfc04786d30a4f257b7e694e2c2a9b323","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ad18b490f7757b2965961e4d7fe86fdfc04786d30a4f257b7e694e2c2a9b323","first_computed_at":"2026-05-18T00:19:05.568442Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:05.568442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o1Ha0my4X5xicTMvoWyU1HxG4Aat9w9INSaLnaRYYvv4cERB68lYFIVn39f5SKV37yBm2dz8cimSURr72MQPBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:05.569056Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.02201","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fb83ed45f3bd23b043420224d1cd0dcbdee95fba96e8d42b300fa1ed28e0a9e","sha256:ff829b5a0719376a977439d66bf7f0b5990cd2246a75bc6e9651fd171a14df39"],"state_sha256":"dd7c9044c028f62b05f279d96f633564d719b6ee105fdb222c6da6d3e13827bb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z6ryng/kySnP9BISsWyNHsyLlb8TtB3NE0+8QzJTZtlqUmiREnY9z1uKhI1lL18HzVCDSlY6NVohypC7rPIyCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T18:45:22.105052Z","bundle_sha256":"7b8eab03f28db15c70719ccbd8432d7cf7cd39e122e54fed7743654eba596706"}}