{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:6N5GZTNKLRKCQHN7RIVK7E66YK","short_pith_number":"pith:6N5GZTNK","canonical_record":{"source":{"id":"1605.07681","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-24T23:00:52Z","cross_cats_sorted":[],"title_canon_sha256":"23143552166dc766471df96c95674ec0526b4646179f1dc1f2f21aee3984bb2e","abstract_canon_sha256":"7fdb27858aa04170a67be81daace0354f5181b8e154a0638070d786d73cbc6d1"},"schema_version":"1.0"},"canonical_sha256":"f37a6ccdaa5c54281dbf8a2aaf93dec2a51ad92e4e0ab1dfae99b7953719b1e2","source":{"kind":"arxiv","id":"1605.07681","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.07681","created_at":"2026-05-18T00:44:58Z"},{"alias_kind":"arxiv_version","alias_value":"1605.07681v3","created_at":"2026-05-18T00:44:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.07681","created_at":"2026-05-18T00:44:58Z"},{"alias_kind":"pith_short_12","alias_value":"6N5GZTNKLRKC","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"6N5GZTNKLRKCQHN7","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"6N5GZTNK","created_at":"2026-05-18T12:30:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:6N5GZTNKLRKCQHN7RIVK7E66YK","target":"record","payload":{"canonical_record":{"source":{"id":"1605.07681","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-24T23:00:52Z","cross_cats_sorted":[],"title_canon_sha256":"23143552166dc766471df96c95674ec0526b4646179f1dc1f2f21aee3984bb2e","abstract_canon_sha256":"7fdb27858aa04170a67be81daace0354f5181b8e154a0638070d786d73cbc6d1"},"schema_version":"1.0"},"canonical_sha256":"f37a6ccdaa5c54281dbf8a2aaf93dec2a51ad92e4e0ab1dfae99b7953719b1e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:58.029161Z","signature_b64":"NShvgs+dye+U4RM9tf9pjC66ItX9PdZTUWpVWCXLo3NN5eytVYEyw0RXHmC6r5v718USpQAlbyF6fExhSyL1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f37a6ccdaa5c54281dbf8a2aaf93dec2a51ad92e4e0ab1dfae99b7953719b1e2","last_reissued_at":"2026-05-18T00:44:58.028607Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:58.028607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.07681","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:44:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Dfajs4Q8QeWjngaGD6xVcEDPJbz5nGtjArTFYoLI8Q435QzG2YKU4FfxCEBcRlW0cwfdJ6eVca00FEE7IQLBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:42:19.058576Z"},"content_sha256":"378585aa244487ca5eca92d41685a9951e4692d3a7073537904ccacb210b9b99","schema_version":"1.0","event_id":"sha256:378585aa244487ca5eca92d41685a9951e4692d3a7073537904ccacb210b9b99"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:6N5GZTNKLRKCQHN7RIVK7E66YK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convolutional Random Walk Networks for Semantic Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gedas Bertasius, Jianbo Shi, Lorenzo Torresani, Stella X. Yu","submitted_at":"2016-05-24T23:00:52Z","abstract_excerpt":"Most current semantic segmentation methods rely on fully convolutional networks (FCNs). However, their use of large receptive fields and many pooling layers cause low spatial resolution inside the deep layers. This leads to predictions with poor localization around the boundaries. Prior work has attempted to address this issue by post-processing predictions with CRFs or MRFs. But such models often fail to capture semantic relationships between objects, which causes spatially disjoint predictions. To overcome these problems, recent methods integrated CRFs or MRFs into an FCN framework. The down"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.07681","kind":"arxiv","version":3},"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":"2026-05-18T00:44:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4DuQBiZm8PrU7evqeOaKJZvVyVJ2LzvUOwSXd5aqvSMTNjkd639xbBot2EeTX4UdXiOWXlZR7C83voaASlv1BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:42:19.059220Z"},"content_sha256":"aaaf7338e283bcfb1dcd0a8dbdc923eb9d06978513e03a6a2a42f46c7b957abc","schema_version":"1.0","event_id":"sha256:aaaf7338e283bcfb1dcd0a8dbdc923eb9d06978513e03a6a2a42f46c7b957abc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6N5GZTNKLRKCQHN7RIVK7E66YK/bundle.json","state_url":"https://pith.science/pith/6N5GZTNKLRKCQHN7RIVK7E66YK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6N5GZTNKLRKCQHN7RIVK7E66YK/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":"2026-05-30T14:42:19Z","links":{"resolver":"https://pith.science/pith/6N5GZTNKLRKCQHN7RIVK7E66YK","bundle":"https://pith.science/pith/6N5GZTNKLRKCQHN7RIVK7E66YK/bundle.json","state":"https://pith.science/pith/6N5GZTNKLRKCQHN7RIVK7E66YK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6N5GZTNKLRKCQHN7RIVK7E66YK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:6N5GZTNKLRKCQHN7RIVK7E66YK","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":"7fdb27858aa04170a67be81daace0354f5181b8e154a0638070d786d73cbc6d1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-24T23:00:52Z","title_canon_sha256":"23143552166dc766471df96c95674ec0526b4646179f1dc1f2f21aee3984bb2e"},"schema_version":"1.0","source":{"id":"1605.07681","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.07681","created_at":"2026-05-18T00:44:58Z"},{"alias_kind":"arxiv_version","alias_value":"1605.07681v3","created_at":"2026-05-18T00:44:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.07681","created_at":"2026-05-18T00:44:58Z"},{"alias_kind":"pith_short_12","alias_value":"6N5GZTNKLRKC","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"6N5GZTNKLRKCQHN7","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"6N5GZTNK","created_at":"2026-05-18T12:30:01Z"}],"graph_snapshots":[{"event_id":"sha256:aaaf7338e283bcfb1dcd0a8dbdc923eb9d06978513e03a6a2a42f46c7b957abc","target":"graph","created_at":"2026-05-18T00:44:58Z","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":"Most current semantic segmentation methods rely on fully convolutional networks (FCNs). However, their use of large receptive fields and many pooling layers cause low spatial resolution inside the deep layers. This leads to predictions with poor localization around the boundaries. Prior work has attempted to address this issue by post-processing predictions with CRFs or MRFs. But such models often fail to capture semantic relationships between objects, which causes spatially disjoint predictions. To overcome these problems, recent methods integrated CRFs or MRFs into an FCN framework. The down","authors_text":"Gedas Bertasius, Jianbo Shi, Lorenzo Torresani, Stella X. Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-24T23:00:52Z","title":"Convolutional Random Walk Networks for Semantic Image Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.07681","kind":"arxiv","version":3},"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":"sha256:378585aa244487ca5eca92d41685a9951e4692d3a7073537904ccacb210b9b99","target":"record","created_at":"2026-05-18T00:44:58Z","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":"7fdb27858aa04170a67be81daace0354f5181b8e154a0638070d786d73cbc6d1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-24T23:00:52Z","title_canon_sha256":"23143552166dc766471df96c95674ec0526b4646179f1dc1f2f21aee3984bb2e"},"schema_version":"1.0","source":{"id":"1605.07681","kind":"arxiv","version":3}},"canonical_sha256":"f37a6ccdaa5c54281dbf8a2aaf93dec2a51ad92e4e0ab1dfae99b7953719b1e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f37a6ccdaa5c54281dbf8a2aaf93dec2a51ad92e4e0ab1dfae99b7953719b1e2","first_computed_at":"2026-05-18T00:44:58.028607Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:44:58.028607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NShvgs+dye+U4RM9tf9pjC66ItX9PdZTUWpVWCXLo3NN5eytVYEyw0RXHmC6r5v718USpQAlbyF6fExhSyL1Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:44:58.029161Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.07681","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:378585aa244487ca5eca92d41685a9951e4692d3a7073537904ccacb210b9b99","sha256:aaaf7338e283bcfb1dcd0a8dbdc923eb9d06978513e03a6a2a42f46c7b957abc"],"state_sha256":"57e75cad1ecb125f43fdbb0bd3d85a91d81cca53845abadd230fa0153cb5229b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qefUeO327/82ZG/ErsreuO6nf4XWIX2Hj3DkeW7D01sys6174Yot4wvtiIGOeWCBV23seb80roAVcmPJ+y5ACg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T14:42:19.062626Z","bundle_sha256":"bbb6a346a2b6b9ede9a962c562d2a39f36e177b4eac0a4c7d65b2a39e6198344"}}