{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HKFNZV5WBS2WJMPHUEJ2BUZ3KR","short_pith_number":"pith:HKFNZV5W","canonical_record":{"source":{"id":"1804.04603","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-10T03:25:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"244877d677810bf757a51d524000bf78dcdd74643b3dc24a2a00f18974095638","abstract_canon_sha256":"2b86499839adb804b97c8b887784a61f6d5229562fd50536621499d69be8ef59"},"schema_version":"1.0"},"canonical_sha256":"3a8adcd7b60cb564b1e7a113a0d33b5458b9b17bc12410631144effffdd9eefc","source":{"kind":"arxiv","id":"1804.04603","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.04603","created_at":"2026-05-18T00:17:59Z"},{"alias_kind":"arxiv_version","alias_value":"1804.04603v2","created_at":"2026-05-18T00:17:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.04603","created_at":"2026-05-18T00:17:59Z"},{"alias_kind":"pith_short_12","alias_value":"HKFNZV5WBS2W","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HKFNZV5WBS2WJMPH","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HKFNZV5W","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HKFNZV5WBS2WJMPHUEJ2BUZ3KR","target":"record","payload":{"canonical_record":{"source":{"id":"1804.04603","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-10T03:25:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"244877d677810bf757a51d524000bf78dcdd74643b3dc24a2a00f18974095638","abstract_canon_sha256":"2b86499839adb804b97c8b887784a61f6d5229562fd50536621499d69be8ef59"},"schema_version":"1.0"},"canonical_sha256":"3a8adcd7b60cb564b1e7a113a0d33b5458b9b17bc12410631144effffdd9eefc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:59.388460Z","signature_b64":"JW81ILz9mDwWOao94KZMqUYJsDC4yJeDuCMcVsQT1imOErypbrZF8TmQNutoIyRoGf67tKPYKphJFIX14MvPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a8adcd7b60cb564b1e7a113a0d33b5458b9b17bc12410631144effffdd9eefc","last_reissued_at":"2026-05-18T00:17:59.387744Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:59.387744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.04603","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:17:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gFebtiuv5znY1xBnlVYvRqIPjdSQRu2by6UoGKVZJPDXwP54Dt/vfWD1nLNq/QDzULrH5bUe2lCF2hHuvEVGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T20:00:06.907465Z"},"content_sha256":"6a842441eeea437b955ccedee68b4aefef1a4141bd2056109d2fee12cc5c3252","schema_version":"1.0","event_id":"sha256:6a842441eeea437b955ccedee68b4aefef1a4141bd2056109d2fee12cc5c3252"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HKFNZV5WBS2WJMPHUEJ2BUZ3KR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Outline Objects using Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jingxin Liu, Sayan Sarcar, Xiangshi Ren, Yilin Zheng, Zhenxin Wang","submitted_at":"2018-04-10T03:25:31Z","abstract_excerpt":"Image segmentation needs both local boundary position information and global object context information. The performance of the recent state-of-the-art method, fully convolutional networks, reaches a bottleneck due to the neural network limit after balancing between the two types of information simultaneously in an end-to-end training style. To overcome this problem, we divide the semantic image segmentation into temporal subtasks. First, we find a possible pixel position of some object boundary; then trace the boundary at steps within a limited length until the whole object is outlined. We pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.04603","kind":"arxiv","version":2},"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":"2026-05-18T00:17:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GRlmN1YQjHg2Awv3N86/qlLVon47ayegL84iPdlFsf4xcZaOvU+UDEgQ2WECL3dLqUMMkI2RLpFhRMgMZ4h7Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T20:00:06.908100Z"},"content_sha256":"5b77d85c2a669b7f29f10f064d1ec4a2e97ee9719481e31bbe06e4c96e7a4d74","schema_version":"1.0","event_id":"sha256:5b77d85c2a669b7f29f10f064d1ec4a2e97ee9719481e31bbe06e4c96e7a4d74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HKFNZV5WBS2WJMPHUEJ2BUZ3KR/bundle.json","state_url":"https://pith.science/pith/HKFNZV5WBS2WJMPHUEJ2BUZ3KR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HKFNZV5WBS2WJMPHUEJ2BUZ3KR/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":"2026-06-06T20:00:06Z","links":{"resolver":"https://pith.science/pith/HKFNZV5WBS2WJMPHUEJ2BUZ3KR","bundle":"https://pith.science/pith/HKFNZV5WBS2WJMPHUEJ2BUZ3KR/bundle.json","state":"https://pith.science/pith/HKFNZV5WBS2WJMPHUEJ2BUZ3KR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HKFNZV5WBS2WJMPHUEJ2BUZ3KR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HKFNZV5WBS2WJMPHUEJ2BUZ3KR","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":"2b86499839adb804b97c8b887784a61f6d5229562fd50536621499d69be8ef59","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-10T03:25:31Z","title_canon_sha256":"244877d677810bf757a51d524000bf78dcdd74643b3dc24a2a00f18974095638"},"schema_version":"1.0","source":{"id":"1804.04603","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.04603","created_at":"2026-05-18T00:17:59Z"},{"alias_kind":"arxiv_version","alias_value":"1804.04603v2","created_at":"2026-05-18T00:17:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.04603","created_at":"2026-05-18T00:17:59Z"},{"alias_kind":"pith_short_12","alias_value":"HKFNZV5WBS2W","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HKFNZV5WBS2WJMPH","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HKFNZV5W","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:5b77d85c2a669b7f29f10f064d1ec4a2e97ee9719481e31bbe06e4c96e7a4d74","target":"graph","created_at":"2026-05-18T00:17:59Z","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":"Image segmentation needs both local boundary position information and global object context information. The performance of the recent state-of-the-art method, fully convolutional networks, reaches a bottleneck due to the neural network limit after balancing between the two types of information simultaneously in an end-to-end training style. To overcome this problem, we divide the semantic image segmentation into temporal subtasks. First, we find a possible pixel position of some object boundary; then trace the boundary at steps within a limited length until the whole object is outlined. We pr","authors_text":"Jingxin Liu, Sayan Sarcar, Xiangshi Ren, Yilin Zheng, Zhenxin Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-10T03:25:31Z","title":"Outline Objects using Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.04603","kind":"arxiv","version":2},"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":"sha256:6a842441eeea437b955ccedee68b4aefef1a4141bd2056109d2fee12cc5c3252","target":"record","created_at":"2026-05-18T00:17:59Z","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":"2b86499839adb804b97c8b887784a61f6d5229562fd50536621499d69be8ef59","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-10T03:25:31Z","title_canon_sha256":"244877d677810bf757a51d524000bf78dcdd74643b3dc24a2a00f18974095638"},"schema_version":"1.0","source":{"id":"1804.04603","kind":"arxiv","version":2}},"canonical_sha256":"3a8adcd7b60cb564b1e7a113a0d33b5458b9b17bc12410631144effffdd9eefc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a8adcd7b60cb564b1e7a113a0d33b5458b9b17bc12410631144effffdd9eefc","first_computed_at":"2026-05-18T00:17:59.387744Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:59.387744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JW81ILz9mDwWOao94KZMqUYJsDC4yJeDuCMcVsQT1imOErypbrZF8TmQNutoIyRoGf67tKPYKphJFIX14MvPAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:59.388460Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.04603","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a842441eeea437b955ccedee68b4aefef1a4141bd2056109d2fee12cc5c3252","sha256:5b77d85c2a669b7f29f10f064d1ec4a2e97ee9719481e31bbe06e4c96e7a4d74"],"state_sha256":"72b3ef02c4a64900db4b14ac6a7dc338823877bd0f9f3f676697fc0c553567ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uanAlbkCkrZNk48Q1LSNxs8RqMeq7Iop5dZolg0BFTbEYD1L2eLPbNQbULQ75qPW9zcYtI/uL9k8/KPjTEorAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T20:00:06.911526Z","bundle_sha256":"f5225c3be90bd06f8ab9788712c9ff1e051e416e94f8e382b295cfc39ca96b26"}}