{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:EOS2AJMIQNB4QY77C7D4DFCDJK","short_pith_number":"pith:EOS2AJMI","canonical_record":{"source":{"id":"1603.04871","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-15T20:10:48Z","cross_cats_sorted":[],"title_canon_sha256":"acd12eacf68a1741bf7add6f3d5e15203c0a6d4836a6c4656861ffd771f29b0e","abstract_canon_sha256":"d1ecad3b7a84ec056d01614ab57b1f84003e95555a73686315194a7866210b90"},"schema_version":"1.0"},"canonical_sha256":"23a5a025888343c863ff17c7c194434aba653db52224162fcdf2486541755ae3","source":{"kind":"arxiv","id":"1603.04871","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.04871","created_at":"2026-05-18T01:18:59Z"},{"alias_kind":"arxiv_version","alias_value":"1603.04871v1","created_at":"2026-05-18T01:18:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.04871","created_at":"2026-05-18T01:18:59Z"},{"alias_kind":"pith_short_12","alias_value":"EOS2AJMIQNB4","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"EOS2AJMIQNB4QY77","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"EOS2AJMI","created_at":"2026-05-18T12:30:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:EOS2AJMIQNB4QY77C7D4DFCDJK","target":"record","payload":{"canonical_record":{"source":{"id":"1603.04871","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-15T20:10:48Z","cross_cats_sorted":[],"title_canon_sha256":"acd12eacf68a1741bf7add6f3d5e15203c0a6d4836a6c4656861ffd771f29b0e","abstract_canon_sha256":"d1ecad3b7a84ec056d01614ab57b1f84003e95555a73686315194a7866210b90"},"schema_version":"1.0"},"canonical_sha256":"23a5a025888343c863ff17c7c194434aba653db52224162fcdf2486541755ae3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:18:59.786804Z","signature_b64":"nNIQCAOGzOViOFRtRDGbj15OvkLop/GRxtf+WOGEV6yHvwRo46vezQz/6KNXeCoYY+0WwKnQoQJ0ukNmTwaPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23a5a025888343c863ff17c7c194434aba653db52224162fcdf2486541755ae3","last_reissued_at":"2026-05-18T01:18:59.786405Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:18:59.786405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1603.04871","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":"2026-05-18T01:18:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KJAX41trTLcXc2i0oCHKulmZteDjJKYwd+YLWXfmt192o5QWjUQcz125SC5rAkxdwUWvNRAjbtFkt4D3lV38BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:41:32.733454Z"},"content_sha256":"cf96d6936ad5d5b22b402416cdad4519513781e101d732e293962d5e4508dc5f","schema_version":"1.0","event_id":"sha256:cf96d6936ad5d5b22b402416cdad4519513781e101d732e293962d5e4508dc5f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:EOS2AJMIQNB4QY77C7D4DFCDJK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Combining the Best of Convolutional Layers and Recurrent Layers: A Hybrid Network for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Zhang, Thomas Breuel, Yangqing Jia, Yizhou Yu, Zhicheng Yan","submitted_at":"2016-03-15T20:10:48Z","abstract_excerpt":"State-of-the-art results of semantic segmentation are established by Fully Convolutional neural Networks (FCNs). FCNs rely on cascaded convolutional and pooling layers to gradually enlarge the receptive fields of neurons, resulting in an indirect way of modeling the distant contextual dependence. In this work, we advocate the use of spatially recurrent layers (i.e. ReNet layers) which directly capture global contexts and lead to improved feature representations. We demonstrate the effectiveness of ReNet layers by building a Naive deep ReNet (N-ReNet), which achieves competitive performance on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.04871","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":"2026-05-18T01:18:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qp6k+KsslZd1XeksgJKSDz/ZZAAy2vbpu0FAaPbQpiPgPpvQJaH3YgjJly7xVr6C8gznmLbV/F0+AbFB34jUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:41:32.734084Z"},"content_sha256":"a2369fe2e756562719f725c73c6618e9798240cc87f26ba9357a56b468b2a2b6","schema_version":"1.0","event_id":"sha256:a2369fe2e756562719f725c73c6618e9798240cc87f26ba9357a56b468b2a2b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EOS2AJMIQNB4QY77C7D4DFCDJK/bundle.json","state_url":"https://pith.science/pith/EOS2AJMIQNB4QY77C7D4DFCDJK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EOS2AJMIQNB4QY77C7D4DFCDJK/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":"2026-05-27T22:41:32Z","links":{"resolver":"https://pith.science/pith/EOS2AJMIQNB4QY77C7D4DFCDJK","bundle":"https://pith.science/pith/EOS2AJMIQNB4QY77C7D4DFCDJK/bundle.json","state":"https://pith.science/pith/EOS2AJMIQNB4QY77C7D4DFCDJK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EOS2AJMIQNB4QY77C7D4DFCDJK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:EOS2AJMIQNB4QY77C7D4DFCDJK","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":"d1ecad3b7a84ec056d01614ab57b1f84003e95555a73686315194a7866210b90","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-15T20:10:48Z","title_canon_sha256":"acd12eacf68a1741bf7add6f3d5e15203c0a6d4836a6c4656861ffd771f29b0e"},"schema_version":"1.0","source":{"id":"1603.04871","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.04871","created_at":"2026-05-18T01:18:59Z"},{"alias_kind":"arxiv_version","alias_value":"1603.04871v1","created_at":"2026-05-18T01:18:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.04871","created_at":"2026-05-18T01:18:59Z"},{"alias_kind":"pith_short_12","alias_value":"EOS2AJMIQNB4","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"EOS2AJMIQNB4QY77","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"EOS2AJMI","created_at":"2026-05-18T12:30:12Z"}],"graph_snapshots":[{"event_id":"sha256:a2369fe2e756562719f725c73c6618e9798240cc87f26ba9357a56b468b2a2b6","target":"graph","created_at":"2026-05-18T01:18:59Z","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":"State-of-the-art results of semantic segmentation are established by Fully Convolutional neural Networks (FCNs). FCNs rely on cascaded convolutional and pooling layers to gradually enlarge the receptive fields of neurons, resulting in an indirect way of modeling the distant contextual dependence. In this work, we advocate the use of spatially recurrent layers (i.e. ReNet layers) which directly capture global contexts and lead to improved feature representations. We demonstrate the effectiveness of ReNet layers by building a Naive deep ReNet (N-ReNet), which achieves competitive performance on ","authors_text":"Hao Zhang, Thomas Breuel, Yangqing Jia, Yizhou Yu, Zhicheng Yan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-15T20:10:48Z","title":"Combining the Best of Convolutional Layers and Recurrent Layers: A Hybrid Network for Semantic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.04871","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:cf96d6936ad5d5b22b402416cdad4519513781e101d732e293962d5e4508dc5f","target":"record","created_at":"2026-05-18T01:18:59Z","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":"d1ecad3b7a84ec056d01614ab57b1f84003e95555a73686315194a7866210b90","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-15T20:10:48Z","title_canon_sha256":"acd12eacf68a1741bf7add6f3d5e15203c0a6d4836a6c4656861ffd771f29b0e"},"schema_version":"1.0","source":{"id":"1603.04871","kind":"arxiv","version":1}},"canonical_sha256":"23a5a025888343c863ff17c7c194434aba653db52224162fcdf2486541755ae3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23a5a025888343c863ff17c7c194434aba653db52224162fcdf2486541755ae3","first_computed_at":"2026-05-18T01:18:59.786405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:18:59.786405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nNIQCAOGzOViOFRtRDGbj15OvkLop/GRxtf+WOGEV6yHvwRo46vezQz/6KNXeCoYY+0WwKnQoQJ0ukNmTwaPAg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:18:59.786804Z","signed_message":"canonical_sha256_bytes"},"source_id":"1603.04871","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf96d6936ad5d5b22b402416cdad4519513781e101d732e293962d5e4508dc5f","sha256:a2369fe2e756562719f725c73c6618e9798240cc87f26ba9357a56b468b2a2b6"],"state_sha256":"b8307b59b50b3fe4586684e628e0f26b9fa8f9ca37727dd437fcf0c653c75a64"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I3F4Kq2++EiYUkEbGXpvt04FtSlPlJN6v5iVIqHu/D8aHPoQyf+VTqgbvnvPxaoeRrdLvo9b74y11spfz1lJBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T22:41:32.737475Z","bundle_sha256":"f731c5078dddb9980db09b29bcb79b55624d91fa0355e1f18ebf1fb3bccf5451"}}