{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MNMZZRK55CRKC5YKXVEWG4ZKXM","short_pith_number":"pith:MNMZZRK5","canonical_record":{"source":{"id":"1805.04554","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-11T18:52:45Z","cross_cats_sorted":[],"title_canon_sha256":"7cab4a76134e95c1f29ef642c3fa7a8893c40a5ad01ca1341940e3947681fd7b","abstract_canon_sha256":"0a5144b75fd8a145736e92f99534681cc9d7dcdaf425276105a3f8302bf9fc23"},"schema_version":"1.0"},"canonical_sha256":"63599cc55de8a2a1770abd4963732abb261fcb9e89e623bc06b22aff67fcbc93","source":{"kind":"arxiv","id":"1805.04554","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.04554","created_at":"2026-05-18T00:01:38Z"},{"alias_kind":"arxiv_version","alias_value":"1805.04554v4","created_at":"2026-05-18T00:01:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.04554","created_at":"2026-05-18T00:01:38Z"},{"alias_kind":"pith_short_12","alias_value":"MNMZZRK55CRK","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MNMZZRK55CRKC5YK","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MNMZZRK5","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MNMZZRK55CRKC5YKXVEWG4ZKXM","target":"record","payload":{"canonical_record":{"source":{"id":"1805.04554","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-11T18:52:45Z","cross_cats_sorted":[],"title_canon_sha256":"7cab4a76134e95c1f29ef642c3fa7a8893c40a5ad01ca1341940e3947681fd7b","abstract_canon_sha256":"0a5144b75fd8a145736e92f99534681cc9d7dcdaf425276105a3f8302bf9fc23"},"schema_version":"1.0"},"canonical_sha256":"63599cc55de8a2a1770abd4963732abb261fcb9e89e623bc06b22aff67fcbc93","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:38.393378Z","signature_b64":"lmKZ/MDFA8unztEedIRa7CLeltVz1vwONeI6C+uJC+QZNobGdPijYCaQR00YxZoe1P0cnAwIa4R873g+CBPJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63599cc55de8a2a1770abd4963732abb261fcb9e89e623bc06b22aff67fcbc93","last_reissued_at":"2026-05-18T00:01:38.392780Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:38.392780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.04554","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:01:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"He7jWvHsmtdyQobjYeD/UEgCg4DU906cLvCOs8P1/TPlnIecygSKqt5/H2CvU0seE4OpaJB0Z7NOfsKzUfkKDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T09:38:55.330410Z"},"content_sha256":"9523012a221c350012e77325dd319824b0fc25359b289b4c7db92ef564ccd5d3","schema_version":"1.0","event_id":"sha256:9523012a221c350012e77325dd319824b0fc25359b289b4c7db92ef564ccd5d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MNMZZRK55CRKC5YKXVEWG4ZKXM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christopher Zach, Rudra P K Poudel, Stephan Liwicki, Ujwal Bonde","submitted_at":"2018-05-11T18:52:45Z","abstract_excerpt":"Modern deep learning architectures produce highly accurate results on many challenging semantic segmentation datasets. State-of-the-art methods are, however, not directly transferable to real-time applications or embedded devices, since naive adaptation of such systems to reduce computational cost (speed, memory and energy) causes a significant drop in accuracy. We propose ContextNet, a new deep neural network architecture which builds on factorized convolution, network compression and pyramid representation to produce competitive semantic segmentation in real-time with low memory requirement."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.04554","kind":"arxiv","version":4},"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":"2026-05-18T00:01:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dQ1U5WyWJNHvqGA+TAvaPCkmFJNnCVv6JnEZBqcfEUAmxUgoQrDxVZNPryDVdqqZABANum9PLW426IwJ0t39AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T09:38:55.330808Z"},"content_sha256":"506f462b1a2817919498aabb20f8f57108c8e76ae8418bc58df94790e0196d81","schema_version":"1.0","event_id":"sha256:506f462b1a2817919498aabb20f8f57108c8e76ae8418bc58df94790e0196d81"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MNMZZRK55CRKC5YKXVEWG4ZKXM/bundle.json","state_url":"https://pith.science/pith/MNMZZRK55CRKC5YKXVEWG4ZKXM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MNMZZRK55CRKC5YKXVEWG4ZKXM/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":"2026-05-27T09:38:55Z","links":{"resolver":"https://pith.science/pith/MNMZZRK55CRKC5YKXVEWG4ZKXM","bundle":"https://pith.science/pith/MNMZZRK55CRKC5YKXVEWG4ZKXM/bundle.json","state":"https://pith.science/pith/MNMZZRK55CRKC5YKXVEWG4ZKXM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MNMZZRK55CRKC5YKXVEWG4ZKXM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MNMZZRK55CRKC5YKXVEWG4ZKXM","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":"0a5144b75fd8a145736e92f99534681cc9d7dcdaf425276105a3f8302bf9fc23","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-11T18:52:45Z","title_canon_sha256":"7cab4a76134e95c1f29ef642c3fa7a8893c40a5ad01ca1341940e3947681fd7b"},"schema_version":"1.0","source":{"id":"1805.04554","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.04554","created_at":"2026-05-18T00:01:38Z"},{"alias_kind":"arxiv_version","alias_value":"1805.04554v4","created_at":"2026-05-18T00:01:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.04554","created_at":"2026-05-18T00:01:38Z"},{"alias_kind":"pith_short_12","alias_value":"MNMZZRK55CRK","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MNMZZRK55CRKC5YK","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MNMZZRK5","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:506f462b1a2817919498aabb20f8f57108c8e76ae8418bc58df94790e0196d81","target":"graph","created_at":"2026-05-18T00:01:38Z","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":"Modern deep learning architectures produce highly accurate results on many challenging semantic segmentation datasets. State-of-the-art methods are, however, not directly transferable to real-time applications or embedded devices, since naive adaptation of such systems to reduce computational cost (speed, memory and energy) causes a significant drop in accuracy. We propose ContextNet, a new deep neural network architecture which builds on factorized convolution, network compression and pyramid representation to produce competitive semantic segmentation in real-time with low memory requirement.","authors_text":"Christopher Zach, Rudra P K Poudel, Stephan Liwicki, Ujwal Bonde","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-11T18:52:45Z","title":"ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.04554","kind":"arxiv","version":4},"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":"sha256:9523012a221c350012e77325dd319824b0fc25359b289b4c7db92ef564ccd5d3","target":"record","created_at":"2026-05-18T00:01:38Z","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":"0a5144b75fd8a145736e92f99534681cc9d7dcdaf425276105a3f8302bf9fc23","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-11T18:52:45Z","title_canon_sha256":"7cab4a76134e95c1f29ef642c3fa7a8893c40a5ad01ca1341940e3947681fd7b"},"schema_version":"1.0","source":{"id":"1805.04554","kind":"arxiv","version":4}},"canonical_sha256":"63599cc55de8a2a1770abd4963732abb261fcb9e89e623bc06b22aff67fcbc93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63599cc55de8a2a1770abd4963732abb261fcb9e89e623bc06b22aff67fcbc93","first_computed_at":"2026-05-18T00:01:38.392780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:38.392780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lmKZ/MDFA8unztEedIRa7CLeltVz1vwONeI6C+uJC+QZNobGdPijYCaQR00YxZoe1P0cnAwIa4R873g+CBPJAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:38.393378Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.04554","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9523012a221c350012e77325dd319824b0fc25359b289b4c7db92ef564ccd5d3","sha256:506f462b1a2817919498aabb20f8f57108c8e76ae8418bc58df94790e0196d81"],"state_sha256":"8311dd22307cb6065c1d813e42166150511fcf38107878dff8925e65b4cecb3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zV+z4Lzj2Lz69OtZN+FzMg80QPrryjAI1ZWHODbqga7hkv0NtTQjBbjgYOReinNop8oR+c/SwcYGZL5WE7mvDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T09:38:55.333835Z","bundle_sha256":"1d33f401e9fbeefe17bf3c20cc05c8cf64d51707da6915887f0e49e3f7e8d9c3"}}