{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:5RU734OCOSU4YKTX4OYY5YLSNH","short_pith_number":"pith:5RU734OC","canonical_record":{"source":{"id":"1707.09531","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-29T15:38:27Z","cross_cats_sorted":[],"title_canon_sha256":"fd2a3aa8fe1fc5053f44cbed35cc7d1ab24db91a6872a967fb9fdb14c0fdf5e3","abstract_canon_sha256":"44bad539600cc974b58292ec452c39a7e434c5ffb771a2a22f610d088344ced1"},"schema_version":"1.0"},"canonical_sha256":"ec69fdf1c274a9cc2a77e3b18ee17269f0665c084de8a05ff09d38c74f617565","source":{"kind":"arxiv","id":"1707.09531","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.09531","created_at":"2026-05-18T00:24:04Z"},{"alias_kind":"arxiv_version","alias_value":"1707.09531v2","created_at":"2026-05-18T00:24:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09531","created_at":"2026-05-18T00:24:04Z"},{"alias_kind":"pith_short_12","alias_value":"5RU734OCOSU4","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5RU734OCOSU4YKTX","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5RU734OC","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:5RU734OCOSU4YKTX4OYY5YLSNH","target":"record","payload":{"canonical_record":{"source":{"id":"1707.09531","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-29T15:38:27Z","cross_cats_sorted":[],"title_canon_sha256":"fd2a3aa8fe1fc5053f44cbed35cc7d1ab24db91a6872a967fb9fdb14c0fdf5e3","abstract_canon_sha256":"44bad539600cc974b58292ec452c39a7e434c5ffb771a2a22f610d088344ced1"},"schema_version":"1.0"},"canonical_sha256":"ec69fdf1c274a9cc2a77e3b18ee17269f0665c084de8a05ff09d38c74f617565","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:04.268822Z","signature_b64":"dLzP5fHwKVUttp9MjYqANdz85rVZdPpsM1cJrdHLr9OtCWh1KpBe19a3mxtODsr4qkIdj4Dv5O/92ECxaakICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec69fdf1c274a9cc2a77e3b18ee17269f0665c084de8a05ff09d38c74f617565","last_reissued_at":"2026-05-18T00:24:04.268121Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:04.268121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.09531","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":"2026-05-18T00:24:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MP8Skb6c3BY5zoAd8HL7xxVbVdDvTsYC1YbKl7WJ7rATAfvUN49qOkYTd0JJ0YHRqMwtdqZ4TbfODblBbsb4BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T23:16:48.427528Z"},"content_sha256":"3e800009713c302e6af871c893a83443acddb19ff4190c2f07c43731b9a4d673","schema_version":"1.0","event_id":"sha256:3e800009713c302e6af871c893a83443acddb19ff4190c2f07c43731b9a4d673"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:5RU734OCOSU4YKTX4OYY5YLSNH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recurrent Scale Approximation for Object Detection in CNN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangyin Wei, Hongyang Li, Junjie Yan, Xiaogang Wang, Xiaoou Tang, Yu Liu","submitted_at":"2017-07-29T15:38:27Z","abstract_excerpt":"Since convolutional neural network (CNN) lacks an inherent mechanism to handle large scale variations, we always need to compute feature maps multiple times for multi-scale object detection, which has the bottleneck of computational cost in practice. To address this, we devise a recurrent scale approximation (RSA) to compute feature map once only, and only through this map can we approximate the rest maps on other levels. At the core of RSA is the recursive rolling out mechanism: given an initial map at a particular scale, it generates the prediction at a smaller scale that is half the size of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09531","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":"2026-05-18T00:24:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rFYoYxHaZqBDI2vkkhMMcAl/no5806qCwvoDJWy+8Um5tX6Pe0rYwWpWkjpCkuM06ejKHpec3wKaz2Vhjw3HDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T23:16:48.428202Z"},"content_sha256":"4c2abba31f1328433c1e88f81c7cd1d99f28c7bb0e190d03637ce2e4afd62f90","schema_version":"1.0","event_id":"sha256:4c2abba31f1328433c1e88f81c7cd1d99f28c7bb0e190d03637ce2e4afd62f90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5RU734OCOSU4YKTX4OYY5YLSNH/bundle.json","state_url":"https://pith.science/pith/5RU734OCOSU4YKTX4OYY5YLSNH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5RU734OCOSU4YKTX4OYY5YLSNH/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":"2026-05-24T23:16:48Z","links":{"resolver":"https://pith.science/pith/5RU734OCOSU4YKTX4OYY5YLSNH","bundle":"https://pith.science/pith/5RU734OCOSU4YKTX4OYY5YLSNH/bundle.json","state":"https://pith.science/pith/5RU734OCOSU4YKTX4OYY5YLSNH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5RU734OCOSU4YKTX4OYY5YLSNH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:5RU734OCOSU4YKTX4OYY5YLSNH","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":"44bad539600cc974b58292ec452c39a7e434c5ffb771a2a22f610d088344ced1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-29T15:38:27Z","title_canon_sha256":"fd2a3aa8fe1fc5053f44cbed35cc7d1ab24db91a6872a967fb9fdb14c0fdf5e3"},"schema_version":"1.0","source":{"id":"1707.09531","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.09531","created_at":"2026-05-18T00:24:04Z"},{"alias_kind":"arxiv_version","alias_value":"1707.09531v2","created_at":"2026-05-18T00:24:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09531","created_at":"2026-05-18T00:24:04Z"},{"alias_kind":"pith_short_12","alias_value":"5RU734OCOSU4","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5RU734OCOSU4YKTX","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5RU734OC","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:4c2abba31f1328433c1e88f81c7cd1d99f28c7bb0e190d03637ce2e4afd62f90","target":"graph","created_at":"2026-05-18T00:24:04Z","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":"Since convolutional neural network (CNN) lacks an inherent mechanism to handle large scale variations, we always need to compute feature maps multiple times for multi-scale object detection, which has the bottleneck of computational cost in practice. To address this, we devise a recurrent scale approximation (RSA) to compute feature map once only, and only through this map can we approximate the rest maps on other levels. At the core of RSA is the recursive rolling out mechanism: given an initial map at a particular scale, it generates the prediction at a smaller scale that is half the size of","authors_text":"Fangyin Wei, Hongyang Li, Junjie Yan, Xiaogang Wang, Xiaoou Tang, Yu Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-29T15:38:27Z","title":"Recurrent Scale Approximation for Object Detection in CNN"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09531","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":"sha256:3e800009713c302e6af871c893a83443acddb19ff4190c2f07c43731b9a4d673","target":"record","created_at":"2026-05-18T00:24:04Z","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":"44bad539600cc974b58292ec452c39a7e434c5ffb771a2a22f610d088344ced1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-29T15:38:27Z","title_canon_sha256":"fd2a3aa8fe1fc5053f44cbed35cc7d1ab24db91a6872a967fb9fdb14c0fdf5e3"},"schema_version":"1.0","source":{"id":"1707.09531","kind":"arxiv","version":2}},"canonical_sha256":"ec69fdf1c274a9cc2a77e3b18ee17269f0665c084de8a05ff09d38c74f617565","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec69fdf1c274a9cc2a77e3b18ee17269f0665c084de8a05ff09d38c74f617565","first_computed_at":"2026-05-18T00:24:04.268121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:24:04.268121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dLzP5fHwKVUttp9MjYqANdz85rVZdPpsM1cJrdHLr9OtCWh1KpBe19a3mxtODsr4qkIdj4Dv5O/92ECxaakICw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:24:04.268822Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.09531","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e800009713c302e6af871c893a83443acddb19ff4190c2f07c43731b9a4d673","sha256:4c2abba31f1328433c1e88f81c7cd1d99f28c7bb0e190d03637ce2e4afd62f90"],"state_sha256":"b2e4b5e3ba06227c0169fb61bff4e951288521ceea9c3af9ab2b77d81a62b5aa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l22WOmXjNBdbGwRW83NcFXHk8WoYD3eCYc3zEZlsPWXWKy6apoM/HrE/uHYOeLvNDxh0RcHOWQKcWnIPFCr2Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T23:16:48.432117Z","bundle_sha256":"49b7eb7a546a30f6bb48eb2aba4360b834068c0d262259e5f271e8df084afd05"}}