{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:SKSTM56NCWUDVN7WWBKZCAOMR5","short_pith_number":"pith:SKSTM56N","canonical_record":{"source":{"id":"1807.02917","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-09T02:31:44Z","cross_cats_sorted":[],"title_canon_sha256":"6f6590e0a9dc160420a3e9e127222f533a9f9152e5af3d0720dc2144ea3a8180","abstract_canon_sha256":"4b00271600702fcfe6701bab2802595b4ab94714475950a14ed7b914ccd2ff34"},"schema_version":"1.0"},"canonical_sha256":"92a53677cd15a83ab7f6b0559101cc8f7b179fa74c7265b7dbfb710ea7bac922","source":{"kind":"arxiv","id":"1807.02917","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.02917","created_at":"2026-05-18T00:11:13Z"},{"alias_kind":"arxiv_version","alias_value":"1807.02917v1","created_at":"2026-05-18T00:11:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.02917","created_at":"2026-05-18T00:11:13Z"},{"alias_kind":"pith_short_12","alias_value":"SKSTM56NCWUD","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SKSTM56NCWUDVN7W","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SKSTM56N","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:SKSTM56NCWUDVN7WWBKZCAOMR5","target":"record","payload":{"canonical_record":{"source":{"id":"1807.02917","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-09T02:31:44Z","cross_cats_sorted":[],"title_canon_sha256":"6f6590e0a9dc160420a3e9e127222f533a9f9152e5af3d0720dc2144ea3a8180","abstract_canon_sha256":"4b00271600702fcfe6701bab2802595b4ab94714475950a14ed7b914ccd2ff34"},"schema_version":"1.0"},"canonical_sha256":"92a53677cd15a83ab7f6b0559101cc8f7b179fa74c7265b7dbfb710ea7bac922","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:13.378151Z","signature_b64":"n/LRcNsYt5i3TbBWWPR8Y8loMXCM+TommcEy2mpZGznhh6wdDXaF5Y+ojoWr9qIhkKP5YRNOj85aIOk98JO2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92a53677cd15a83ab7f6b0559101cc8f7b179fa74c7265b7dbfb710ea7bac922","last_reissued_at":"2026-05-18T00:11:13.377379Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:13.377379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.02917","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":"2026-05-18T00:11:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KC0qqAeFfUR4Juvs0aLr22uQZn9kTM1EXV+4fkozY07S8iESB+qfyeyaa6FSA9oToZfpf6VZpi0PdE1yoAx7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T10:30:28.372094Z"},"content_sha256":"4bb065014e022e51f691b9f0dc7a837421ac6f7577cfe5b62cfb53a84e9126ab","schema_version":"1.0","event_id":"sha256:4bb065014e022e51f691b9f0dc7a837421ac6f7577cfe5b62cfb53a84e9126ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:SKSTM56NCWUDVN7WWBKZCAOMR5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attention to Refine through Multi-Scales for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gang Peng, Shiqi Yang","submitted_at":"2018-07-09T02:31:44Z","abstract_excerpt":"This paper proposes a novel attention model for semantic segmentation, which aggregates multi-scale and context features to refine prediction. Specifically, the skeleton convolutional neural network framework takes in multiple different scales inputs, by which means the CNN can get representations in different scales. The proposed attention model will handle the features from different scale streams respectively and integrate them. Then location attention branch of the model learns to softly weight the multi-scale features at each pixel location. Moreover, we add an recalibrating branch, paral"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.02917","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":"2026-05-18T00:11:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T2doEr0wqKiFjUprdzvm4UGgN9jcoCtJbOYqWSJ174lLCLWXy9MadnEadjusJGNuUUIZEE2c8ME5oBzvQx6RDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T10:30:28.372713Z"},"content_sha256":"e8249a9ce75a546889de54052db2e0f50f91e15a322309434000ff3d78c61b9f","schema_version":"1.0","event_id":"sha256:e8249a9ce75a546889de54052db2e0f50f91e15a322309434000ff3d78c61b9f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SKSTM56NCWUDVN7WWBKZCAOMR5/bundle.json","state_url":"https://pith.science/pith/SKSTM56NCWUDVN7WWBKZCAOMR5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SKSTM56NCWUDVN7WWBKZCAOMR5/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":"2026-05-27T10:30:28Z","links":{"resolver":"https://pith.science/pith/SKSTM56NCWUDVN7WWBKZCAOMR5","bundle":"https://pith.science/pith/SKSTM56NCWUDVN7WWBKZCAOMR5/bundle.json","state":"https://pith.science/pith/SKSTM56NCWUDVN7WWBKZCAOMR5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SKSTM56NCWUDVN7WWBKZCAOMR5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:SKSTM56NCWUDVN7WWBKZCAOMR5","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":"4b00271600702fcfe6701bab2802595b4ab94714475950a14ed7b914ccd2ff34","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-09T02:31:44Z","title_canon_sha256":"6f6590e0a9dc160420a3e9e127222f533a9f9152e5af3d0720dc2144ea3a8180"},"schema_version":"1.0","source":{"id":"1807.02917","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.02917","created_at":"2026-05-18T00:11:13Z"},{"alias_kind":"arxiv_version","alias_value":"1807.02917v1","created_at":"2026-05-18T00:11:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.02917","created_at":"2026-05-18T00:11:13Z"},{"alias_kind":"pith_short_12","alias_value":"SKSTM56NCWUD","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SKSTM56NCWUDVN7W","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SKSTM56N","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:e8249a9ce75a546889de54052db2e0f50f91e15a322309434000ff3d78c61b9f","target":"graph","created_at":"2026-05-18T00:11:13Z","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":"This paper proposes a novel attention model for semantic segmentation, which aggregates multi-scale and context features to refine prediction. Specifically, the skeleton convolutional neural network framework takes in multiple different scales inputs, by which means the CNN can get representations in different scales. The proposed attention model will handle the features from different scale streams respectively and integrate them. Then location attention branch of the model learns to softly weight the multi-scale features at each pixel location. Moreover, we add an recalibrating branch, paral","authors_text":"Gang Peng, Shiqi Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-09T02:31:44Z","title":"Attention to Refine through Multi-Scales for Semantic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.02917","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":"sha256:4bb065014e022e51f691b9f0dc7a837421ac6f7577cfe5b62cfb53a84e9126ab","target":"record","created_at":"2026-05-18T00:11:13Z","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":"4b00271600702fcfe6701bab2802595b4ab94714475950a14ed7b914ccd2ff34","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-09T02:31:44Z","title_canon_sha256":"6f6590e0a9dc160420a3e9e127222f533a9f9152e5af3d0720dc2144ea3a8180"},"schema_version":"1.0","source":{"id":"1807.02917","kind":"arxiv","version":1}},"canonical_sha256":"92a53677cd15a83ab7f6b0559101cc8f7b179fa74c7265b7dbfb710ea7bac922","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92a53677cd15a83ab7f6b0559101cc8f7b179fa74c7265b7dbfb710ea7bac922","first_computed_at":"2026-05-18T00:11:13.377379Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:13.377379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n/LRcNsYt5i3TbBWWPR8Y8loMXCM+TommcEy2mpZGznhh6wdDXaF5Y+ojoWr9qIhkKP5YRNOj85aIOk98JO2DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:13.378151Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.02917","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bb065014e022e51f691b9f0dc7a837421ac6f7577cfe5b62cfb53a84e9126ab","sha256:e8249a9ce75a546889de54052db2e0f50f91e15a322309434000ff3d78c61b9f"],"state_sha256":"8c13098f3d084be7b16f2380ff6c8efb7a7b1523d2cc50021fad1394bc9ba7b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NOV7MqojjiMpRHojqyLOWnExmKxy4RvuhOldY/8SjboKe5Sa7hQ7kgiE//waQO/1JS9cFkJABEd5MtzCNjiqDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T10:30:28.376142Z","bundle_sha256":"b2accce6973abd342c0691875f55b58d7ffd2873d28f28ec36afb1e3b42e3180"}}