{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:E7GLASSV4CBSE4VNVBH4XBQB56","short_pith_number":"pith:E7GLASSV","canonical_record":{"source":{"id":"1903.04688","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-12T01:34:39Z","cross_cats_sorted":[],"title_canon_sha256":"d11b68f82a04040f48486fbe5aa8acecc789f8c1d022141e0c0cdd219499910b","abstract_canon_sha256":"1cff11c1a4158e939a66fb7a237d6fdc259d6f24de279900e4c8fa7a4441e452"},"schema_version":"1.0"},"canonical_sha256":"27ccb04a55e0832272ada84fcb8601efb8522d2bfaa3714367a9100f9e5c2741","source":{"kind":"arxiv","id":"1903.04688","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.04688","created_at":"2026-05-17T23:51:28Z"},{"alias_kind":"arxiv_version","alias_value":"1903.04688v1","created_at":"2026-05-17T23:51:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.04688","created_at":"2026-05-17T23:51:28Z"},{"alias_kind":"pith_short_12","alias_value":"E7GLASSV4CBS","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"E7GLASSV4CBSE4VN","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"E7GLASSV","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:E7GLASSV4CBSE4VNVBH4XBQB56","target":"record","payload":{"canonical_record":{"source":{"id":"1903.04688","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-12T01:34:39Z","cross_cats_sorted":[],"title_canon_sha256":"d11b68f82a04040f48486fbe5aa8acecc789f8c1d022141e0c0cdd219499910b","abstract_canon_sha256":"1cff11c1a4158e939a66fb7a237d6fdc259d6f24de279900e4c8fa7a4441e452"},"schema_version":"1.0"},"canonical_sha256":"27ccb04a55e0832272ada84fcb8601efb8522d2bfaa3714367a9100f9e5c2741","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:28.947657Z","signature_b64":"9yFmic098m37TvencvBOX2jdVMoADUf2egun0sk3d5KYrLDEvt6wS6FK8uPuF4mSQHUWGHSAfKCYfGOfBEP7Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27ccb04a55e0832272ada84fcb8601efb8522d2bfaa3714367a9100f9e5c2741","last_reissued_at":"2026-05-17T23:51:28.947195Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:28.947195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.04688","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":"2026-05-17T23:51:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ULj++naBLnC8mT1ohOCBv+50YaQVGew/LgDIU7u4EcK+ItiC5dTFvnjDJqPKt1u6VX+HPGC2kxDSI8FpLkYbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:02:25.289848Z"},"content_sha256":"cb7d867f58a26dbb1ecd2421157527c6be08c731d75036383fa393587e389d85","schema_version":"1.0","event_id":"sha256:cb7d867f58a26dbb1ecd2421157527c6be08c731d75036383fa393587e389d85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:E7GLASSV4CBSE4VNVBH4XBQB56","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Knowledge Adaptation for Efficient Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changming Sun, Chunhua Shen, Dong Gong, Tong He, Youliang Yan, Zhi Tian","submitted_at":"2019-03-12T01:34:39Z","abstract_excerpt":"Both accuracy and efficiency are of significant importance to the task of semantic segmentation. Existing deep FCNs suffer from heavy computations due to a series of high-resolution feature maps for preserving the detailed knowledge in dense estimation. Although reducing the feature map resolution (i.e., applying a large overall stride) via subsampling operations (e.g., pooling and convolution striding) can instantly increase the efficiency, it dramatically decreases the estimation accuracy. To tackle this dilemma, we propose a knowledge distillation method tailored for semantic segmentation t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.04688","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":"2026-05-17T23:51:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eFwgksw1gGIqAR+li3+8ay0irepPDWXVAR/oksm9Nu61YmX4UzFWLHuIyeRZ9Pm7/z/KswUEtGLw9zxLAsqCCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:02:25.290511Z"},"content_sha256":"abf018153138d899e009a403330955e4aad6f5aa95d3e3dbcfc408993fe249a6","schema_version":"1.0","event_id":"sha256:abf018153138d899e009a403330955e4aad6f5aa95d3e3dbcfc408993fe249a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E7GLASSV4CBSE4VNVBH4XBQB56/bundle.json","state_url":"https://pith.science/pith/E7GLASSV4CBSE4VNVBH4XBQB56/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E7GLASSV4CBSE4VNVBH4XBQB56/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":"2026-05-26T17:02:25Z","links":{"resolver":"https://pith.science/pith/E7GLASSV4CBSE4VNVBH4XBQB56","bundle":"https://pith.science/pith/E7GLASSV4CBSE4VNVBH4XBQB56/bundle.json","state":"https://pith.science/pith/E7GLASSV4CBSE4VNVBH4XBQB56/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E7GLASSV4CBSE4VNVBH4XBQB56/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:E7GLASSV4CBSE4VNVBH4XBQB56","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":"1cff11c1a4158e939a66fb7a237d6fdc259d6f24de279900e4c8fa7a4441e452","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-12T01:34:39Z","title_canon_sha256":"d11b68f82a04040f48486fbe5aa8acecc789f8c1d022141e0c0cdd219499910b"},"schema_version":"1.0","source":{"id":"1903.04688","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.04688","created_at":"2026-05-17T23:51:28Z"},{"alias_kind":"arxiv_version","alias_value":"1903.04688v1","created_at":"2026-05-17T23:51:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.04688","created_at":"2026-05-17T23:51:28Z"},{"alias_kind":"pith_short_12","alias_value":"E7GLASSV4CBS","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"E7GLASSV4CBSE4VN","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"E7GLASSV","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:abf018153138d899e009a403330955e4aad6f5aa95d3e3dbcfc408993fe249a6","target":"graph","created_at":"2026-05-17T23:51:28Z","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":"Both accuracy and efficiency are of significant importance to the task of semantic segmentation. Existing deep FCNs suffer from heavy computations due to a series of high-resolution feature maps for preserving the detailed knowledge in dense estimation. Although reducing the feature map resolution (i.e., applying a large overall stride) via subsampling operations (e.g., pooling and convolution striding) can instantly increase the efficiency, it dramatically decreases the estimation accuracy. To tackle this dilemma, we propose a knowledge distillation method tailored for semantic segmentation t","authors_text":"Changming Sun, Chunhua Shen, Dong Gong, Tong He, Youliang Yan, Zhi Tian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-12T01:34:39Z","title":"Knowledge Adaptation for Efficient Semantic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.04688","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:cb7d867f58a26dbb1ecd2421157527c6be08c731d75036383fa393587e389d85","target":"record","created_at":"2026-05-17T23:51:28Z","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":"1cff11c1a4158e939a66fb7a237d6fdc259d6f24de279900e4c8fa7a4441e452","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-12T01:34:39Z","title_canon_sha256":"d11b68f82a04040f48486fbe5aa8acecc789f8c1d022141e0c0cdd219499910b"},"schema_version":"1.0","source":{"id":"1903.04688","kind":"arxiv","version":1}},"canonical_sha256":"27ccb04a55e0832272ada84fcb8601efb8522d2bfaa3714367a9100f9e5c2741","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27ccb04a55e0832272ada84fcb8601efb8522d2bfaa3714367a9100f9e5c2741","first_computed_at":"2026-05-17T23:51:28.947195Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:28.947195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9yFmic098m37TvencvBOX2jdVMoADUf2egun0sk3d5KYrLDEvt6wS6FK8uPuF4mSQHUWGHSAfKCYfGOfBEP7Cw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:28.947657Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.04688","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb7d867f58a26dbb1ecd2421157527c6be08c731d75036383fa393587e389d85","sha256:abf018153138d899e009a403330955e4aad6f5aa95d3e3dbcfc408993fe249a6"],"state_sha256":"d106ccc619f161b0641cf7d0b165a1c9827f501a241d31ae47406ed5736f918e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pFPux5xVdcWxsdP3ZECK9aYwYxC/i3v7rRExnUPaUcHN9EUGXyfKqdrjApiUze69gycbTroay8YnRbGU0uEZBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T17:02:25.294108Z","bundle_sha256":"0ab90a9bd8402f6f3eb756f8feef5a2f8718dc76e17cf1b6258e0d5fa4055465"}}