{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:6CXT4U7JGLFX7F7SDKDSFYJB5Q","short_pith_number":"pith:6CXT4U7J","canonical_record":{"source":{"id":"1705.04456","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-12T07:52:27Z","cross_cats_sorted":[],"title_canon_sha256":"8c60fe2eb10f04af5119c663e4b6c9050845c8c087c88b464ecc43a3b356aea5","abstract_canon_sha256":"8be512d3a71d99492863d3672567572f0138e688aec6ab17ef001c04cf2138f9"},"schema_version":"1.0"},"canonical_sha256":"f0af3e53e932cb7f97f21a8722e121ec3acced5796d1afdc1b50cbae038cee32","source":{"kind":"arxiv","id":"1705.04456","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.04456","created_at":"2026-05-18T00:40:28Z"},{"alias_kind":"arxiv_version","alias_value":"1705.04456v1","created_at":"2026-05-18T00:40:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.04456","created_at":"2026-05-18T00:40:28Z"},{"alias_kind":"pith_short_12","alias_value":"6CXT4U7JGLFX","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6CXT4U7JGLFX7F7S","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6CXT4U7J","created_at":"2026-05-18T12:31:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:6CXT4U7JGLFX7F7SDKDSFYJB5Q","target":"record","payload":{"canonical_record":{"source":{"id":"1705.04456","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-12T07:52:27Z","cross_cats_sorted":[],"title_canon_sha256":"8c60fe2eb10f04af5119c663e4b6c9050845c8c087c88b464ecc43a3b356aea5","abstract_canon_sha256":"8be512d3a71d99492863d3672567572f0138e688aec6ab17ef001c04cf2138f9"},"schema_version":"1.0"},"canonical_sha256":"f0af3e53e932cb7f97f21a8722e121ec3acced5796d1afdc1b50cbae038cee32","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:28.397031Z","signature_b64":"s0p/9kEBJH99029jJHwCqbfh+uLutFewUjEUsQJE2ov1RsnWtlOTF8z2d5xJxB1C6bFKFnhPJClhvqsgChP0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0af3e53e932cb7f97f21a8722e121ec3acced5796d1afdc1b50cbae038cee32","last_reissued_at":"2026-05-18T00:40:28.396399Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:28.396399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.04456","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":"2026-05-18T00:40:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CBmZAVrXYt/jvzV0gRpR11smZWQ+IVgjVm9lg13949EYJvGv8PffVLvgjN9zCtCVy3bzbolJAxlqG11hfaM3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:21:03.906229Z"},"content_sha256":"bdeb37c8c95ba6c3d7c6642a81fd8e4398425cdc93e58c991751280b72ff3276","schema_version":"1.0","event_id":"sha256:bdeb37c8c95ba6c3d7c6642a81fd8e4398425cdc93e58c991751280b72ff3276"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:6CXT4U7JGLFX7F7SDKDSFYJB5Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Refine Object Contours with a Top-Down Fully Convolutional Encoder-Decoder Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Yao, Jing Han, Li Li, Xiaohu Lu, Yahui Liu","submitted_at":"2017-05-12T07:52:27Z","abstract_excerpt":"We develop a novel deep contour detection algorithm with a top-down fully convolutional encoder-decoder network. Our proposed method, named TD-CEDN, solves two important issues in this low-level vision problem: (1) learning multi-scale and multi-level features; and (2) applying an effective top-down refined approach in the networks. TD-CEDN performs the pixel-wise prediction by means of leveraging features at all layers of the net. Unlike skip connections and previous encoder-decoder methods, we first learn a coarse feature map after the encoder stage in a feedforward pass, and then refine thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.04456","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":"2026-05-18T00:40:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ipAVBXSR5JxC3VCT9vFxqk+8GaSxqy2uvI0SMV/4Ln6DaHs02dE6laA76nf0ia0TUTx+irF8h+FdZS8d/KymAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:21:03.906998Z"},"content_sha256":"459606a0a33ff2cf9008d11a67cccf7ed75de8f3c42c4c520ea970a37be23484","schema_version":"1.0","event_id":"sha256:459606a0a33ff2cf9008d11a67cccf7ed75de8f3c42c4c520ea970a37be23484"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6CXT4U7JGLFX7F7SDKDSFYJB5Q/bundle.json","state_url":"https://pith.science/pith/6CXT4U7JGLFX7F7SDKDSFYJB5Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6CXT4U7JGLFX7F7SDKDSFYJB5Q/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":"2026-05-30T09:21:03Z","links":{"resolver":"https://pith.science/pith/6CXT4U7JGLFX7F7SDKDSFYJB5Q","bundle":"https://pith.science/pith/6CXT4U7JGLFX7F7SDKDSFYJB5Q/bundle.json","state":"https://pith.science/pith/6CXT4U7JGLFX7F7SDKDSFYJB5Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6CXT4U7JGLFX7F7SDKDSFYJB5Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:6CXT4U7JGLFX7F7SDKDSFYJB5Q","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":"8be512d3a71d99492863d3672567572f0138e688aec6ab17ef001c04cf2138f9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-12T07:52:27Z","title_canon_sha256":"8c60fe2eb10f04af5119c663e4b6c9050845c8c087c88b464ecc43a3b356aea5"},"schema_version":"1.0","source":{"id":"1705.04456","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.04456","created_at":"2026-05-18T00:40:28Z"},{"alias_kind":"arxiv_version","alias_value":"1705.04456v1","created_at":"2026-05-18T00:40:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.04456","created_at":"2026-05-18T00:40:28Z"},{"alias_kind":"pith_short_12","alias_value":"6CXT4U7JGLFX","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6CXT4U7JGLFX7F7S","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6CXT4U7J","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:459606a0a33ff2cf9008d11a67cccf7ed75de8f3c42c4c520ea970a37be23484","target":"graph","created_at":"2026-05-18T00:40:28Z","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":"We develop a novel deep contour detection algorithm with a top-down fully convolutional encoder-decoder network. Our proposed method, named TD-CEDN, solves two important issues in this low-level vision problem: (1) learning multi-scale and multi-level features; and (2) applying an effective top-down refined approach in the networks. TD-CEDN performs the pixel-wise prediction by means of leveraging features at all layers of the net. Unlike skip connections and previous encoder-decoder methods, we first learn a coarse feature map after the encoder stage in a feedforward pass, and then refine thi","authors_text":"Jian Yao, Jing Han, Li Li, Xiaohu Lu, Yahui Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-12T07:52:27Z","title":"Learning to Refine Object Contours with a Top-Down Fully Convolutional Encoder-Decoder Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.04456","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:bdeb37c8c95ba6c3d7c6642a81fd8e4398425cdc93e58c991751280b72ff3276","target":"record","created_at":"2026-05-18T00:40:28Z","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":"8be512d3a71d99492863d3672567572f0138e688aec6ab17ef001c04cf2138f9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-12T07:52:27Z","title_canon_sha256":"8c60fe2eb10f04af5119c663e4b6c9050845c8c087c88b464ecc43a3b356aea5"},"schema_version":"1.0","source":{"id":"1705.04456","kind":"arxiv","version":1}},"canonical_sha256":"f0af3e53e932cb7f97f21a8722e121ec3acced5796d1afdc1b50cbae038cee32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0af3e53e932cb7f97f21a8722e121ec3acced5796d1afdc1b50cbae038cee32","first_computed_at":"2026-05-18T00:40:28.396399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:28.396399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s0p/9kEBJH99029jJHwCqbfh+uLutFewUjEUsQJE2ov1RsnWtlOTF8z2d5xJxB1C6bFKFnhPJClhvqsgChP0CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:28.397031Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.04456","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bdeb37c8c95ba6c3d7c6642a81fd8e4398425cdc93e58c991751280b72ff3276","sha256:459606a0a33ff2cf9008d11a67cccf7ed75de8f3c42c4c520ea970a37be23484"],"state_sha256":"ad4c72344daa7e1aae10866a2a1f40d650a41f6c615f780b87c929c39dc9a384"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WtooSzhCCY22F/Sn6X9FB68l6i5tmDPbn4NjGcpekGC0Xeu+Z3ZJbRWfl5QVDLFMMT+7HOBJ+MEa5Hv94Tr6Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T09:21:03.910608Z","bundle_sha256":"089cc5b32c2bbc20c7a239ebbbe27f57305381ac0b3ae67adfee5b1eb7648eb0"}}