{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:KUSU4XMSDS2G4YTOOOGBTD4OFV","short_pith_number":"pith:KUSU4XMS","canonical_record":{"source":{"id":"1901.02511","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-08T20:45:49Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"f88113d4be3b0991f8a6f8632bdcf41e4d688e146f42c76533d9b9721e50c2aa","abstract_canon_sha256":"8778be6b83a3434fffd92b2e8020a790d597b6942ef329e8ba056eeb3279bdcf"},"schema_version":"1.0"},"canonical_sha256":"55254e5d921cb46e626e738c198f8e2d54e1d0e820eee609a728365428a1f8ce","source":{"kind":"arxiv","id":"1901.02511","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.02511","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"arxiv_version","alias_value":"1901.02511v1","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02511","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"pith_short_12","alias_value":"KUSU4XMSDS2G","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KUSU4XMSDS2G4YTO","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KUSU4XMS","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:KUSU4XMSDS2G4YTOOOGBTD4OFV","target":"record","payload":{"canonical_record":{"source":{"id":"1901.02511","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-08T20:45:49Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"f88113d4be3b0991f8a6f8632bdcf41e4d688e146f42c76533d9b9721e50c2aa","abstract_canon_sha256":"8778be6b83a3434fffd92b2e8020a790d597b6942ef329e8ba056eeb3279bdcf"},"schema_version":"1.0"},"canonical_sha256":"55254e5d921cb46e626e738c198f8e2d54e1d0e820eee609a728365428a1f8ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:40.750645Z","signature_b64":"/k4OITJqWuG5iwab5N2Vu2+UmzxRwnNm1VH1euLP2G9x2Hlb7fvkStY7loMK56SCQWYdNwTQrgAHO2UUwY+6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55254e5d921cb46e626e738c198f8e2d54e1d0e820eee609a728365428a1f8ce","last_reissued_at":"2026-05-17T23:50:40.750087Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:40.750087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.02511","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":"2026-05-17T23:50:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hbDJgyHmDoQjMIQ1VCuPGu88A2llpTbS5fkKPwCvQe/Gp3cEjkuQz03FKygRkbjU9mKoutkGP3keRtFmMG8nCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:52:29.993131Z"},"content_sha256":"1f30b08cf4e77afa2a1d53110e89f6607e164dd7940c6712463c4d00c93e1b69","schema_version":"1.0","event_id":"sha256:1f30b08cf4e77afa2a1d53110e89f6607e164dd7940c6712463c4d00c93e1b69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:KUSU4XMSDS2G4YTOOOGBTD4OFV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-stream CNN based Video Semantic Segmentation for Automated Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Ganesh Sistu, Senthil Yogamani, Sumanth Chennupati","submitted_at":"2019-01-08T20:45:49Z","abstract_excerpt":"Majority of semantic segmentation algorithms operate on a single frame even in the case of videos. In this work, the goal is to exploit temporal information within the algorithm model for leveraging motion cues and temporal consistency. We propose two simple high-level architectures based on Recurrent FCN (RFCN) and Multi-Stream FCN (MSFCN) networks. In case of RFCN, a recurrent network namely LSTM is inserted between the encoder and decoder. MSFCN combines the encoders of different frames into a fused encoder via 1x1 channel-wise convolution. We use a ResNet50 network as the baseline encoder "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02511","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":"2026-05-17T23:50:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kzBGB7aPGmb/QYALfRmqn3J6ZpgsjVpDevyInxTa71J2x1eyT7o1dT+jv7teHyWU6my7SE9OsSo7/uSoL1f1Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:52:29.993608Z"},"content_sha256":"835e382e2570c52f90d76b5d3ac8fe38765dc1b67fcdcf7e098dba2b1e65ed82","schema_version":"1.0","event_id":"sha256:835e382e2570c52f90d76b5d3ac8fe38765dc1b67fcdcf7e098dba2b1e65ed82"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KUSU4XMSDS2G4YTOOOGBTD4OFV/bundle.json","state_url":"https://pith.science/pith/KUSU4XMSDS2G4YTOOOGBTD4OFV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KUSU4XMSDS2G4YTOOOGBTD4OFV/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":"2026-05-25T19:52:29Z","links":{"resolver":"https://pith.science/pith/KUSU4XMSDS2G4YTOOOGBTD4OFV","bundle":"https://pith.science/pith/KUSU4XMSDS2G4YTOOOGBTD4OFV/bundle.json","state":"https://pith.science/pith/KUSU4XMSDS2G4YTOOOGBTD4OFV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KUSU4XMSDS2G4YTOOOGBTD4OFV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KUSU4XMSDS2G4YTOOOGBTD4OFV","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":"8778be6b83a3434fffd92b2e8020a790d597b6942ef329e8ba056eeb3279bdcf","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-08T20:45:49Z","title_canon_sha256":"f88113d4be3b0991f8a6f8632bdcf41e4d688e146f42c76533d9b9721e50c2aa"},"schema_version":"1.0","source":{"id":"1901.02511","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.02511","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"arxiv_version","alias_value":"1901.02511v1","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02511","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"pith_short_12","alias_value":"KUSU4XMSDS2G","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KUSU4XMSDS2G4YTO","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KUSU4XMS","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:835e382e2570c52f90d76b5d3ac8fe38765dc1b67fcdcf7e098dba2b1e65ed82","target":"graph","created_at":"2026-05-17T23:50:40Z","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":"Majority of semantic segmentation algorithms operate on a single frame even in the case of videos. In this work, the goal is to exploit temporal information within the algorithm model for leveraging motion cues and temporal consistency. We propose two simple high-level architectures based on Recurrent FCN (RFCN) and Multi-Stream FCN (MSFCN) networks. In case of RFCN, a recurrent network namely LSTM is inserted between the encoder and decoder. MSFCN combines the encoders of different frames into a fused encoder via 1x1 channel-wise convolution. We use a ResNet50 network as the baseline encoder ","authors_text":"Ganesh Sistu, Senthil Yogamani, Sumanth Chennupati","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-08T20:45:49Z","title":"Multi-stream CNN based Video Semantic Segmentation for Automated Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02511","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":"sha256:1f30b08cf4e77afa2a1d53110e89f6607e164dd7940c6712463c4d00c93e1b69","target":"record","created_at":"2026-05-17T23:50:40Z","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":"8778be6b83a3434fffd92b2e8020a790d597b6942ef329e8ba056eeb3279bdcf","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-08T20:45:49Z","title_canon_sha256":"f88113d4be3b0991f8a6f8632bdcf41e4d688e146f42c76533d9b9721e50c2aa"},"schema_version":"1.0","source":{"id":"1901.02511","kind":"arxiv","version":1}},"canonical_sha256":"55254e5d921cb46e626e738c198f8e2d54e1d0e820eee609a728365428a1f8ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55254e5d921cb46e626e738c198f8e2d54e1d0e820eee609a728365428a1f8ce","first_computed_at":"2026-05-17T23:50:40.750087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:40.750087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/k4OITJqWuG5iwab5N2Vu2+UmzxRwnNm1VH1euLP2G9x2Hlb7fvkStY7loMK56SCQWYdNwTQrgAHO2UUwY+6CQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:40.750645Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.02511","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f30b08cf4e77afa2a1d53110e89f6607e164dd7940c6712463c4d00c93e1b69","sha256:835e382e2570c52f90d76b5d3ac8fe38765dc1b67fcdcf7e098dba2b1e65ed82"],"state_sha256":"f7f8872e084d1ad6a07a3e508753cb7e10f24c50901923d00fcdb666fb41ad27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a2ln8KMaImNr2oaVgw1URIv5uYBKYSimE+2bs0mFglfHLdN8kxd9+hVvRQsL4KI/0pFsa/Ad3flFWzd4upGkBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:52:29.997713Z","bundle_sha256":"cf1d0308c6f922cb52df45270043a252fef26214af06746520ac1f1d3b579b57"}}