{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:N32HQYHEJA5UKA5LCLEXPB7HYP","short_pith_number":"pith:N32HQYHE","canonical_record":{"source":{"id":"1908.04646","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-13T13:54:31Z","cross_cats_sorted":[],"title_canon_sha256":"167a4f7e8af3d77b793866876e507b4dee4f69a59bc4ee051a785e74da73d066","abstract_canon_sha256":"03bf34d82257414d88f46e8c8bc1422620ee1d590db91f8ce68c8c69278fab0b"},"schema_version":"1.0"},"canonical_sha256":"6ef47860e4483b4503ab12c97787e7c3f552f223628d86d2f8700202edf002fd","source":{"kind":"arxiv","id":"1908.04646","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.04646","created_at":"2026-07-04T23:55:57Z"},{"alias_kind":"arxiv_version","alias_value":"1908.04646v2","created_at":"2026-07-04T23:55:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04646","created_at":"2026-07-04T23:55:57Z"},{"alias_kind":"pith_short_12","alias_value":"N32HQYHEJA5U","created_at":"2026-07-04T23:55:57Z"},{"alias_kind":"pith_short_16","alias_value":"N32HQYHEJA5UKA5L","created_at":"2026-07-04T23:55:57Z"},{"alias_kind":"pith_short_8","alias_value":"N32HQYHE","created_at":"2026-07-04T23:55:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:N32HQYHEJA5UKA5LCLEXPB7HYP","target":"record","payload":{"canonical_record":{"source":{"id":"1908.04646","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-13T13:54:31Z","cross_cats_sorted":[],"title_canon_sha256":"167a4f7e8af3d77b793866876e507b4dee4f69a59bc4ee051a785e74da73d066","abstract_canon_sha256":"03bf34d82257414d88f46e8c8bc1422620ee1d590db91f8ce68c8c69278fab0b"},"schema_version":"1.0"},"canonical_sha256":"6ef47860e4483b4503ab12c97787e7c3f552f223628d86d2f8700202edf002fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:55:57.025568Z","signature_b64":"4SukcEZcNdx4bbrsDdwi3ij98POp5u2eGRJ+ESvcfgBnT5qci32MFyCs33eCfLqqIW28uipJiRIjP8NY7zt/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ef47860e4483b4503ab12c97787e7c3f552f223628d86d2f8700202edf002fd","last_reissued_at":"2026-07-04T23:55:57.025124Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:55:57.025124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.04646","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":"2026-07-04T23:55:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F5/qU0fRDyAmfh7/3CaUVRjHTo4ZcvdHrchl62RqxyMY9b2qW1u+e/IgjqM41XUWrLxpgwYlhr+BBG+rRwkFAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T15:12:19.644798Z"},"content_sha256":"32538aa5c04dce14250ddd33d709d1ed6c10ba73f58766897a66bab396bd886f","schema_version":"1.0","event_id":"sha256:32538aa5c04dce14250ddd33d709d1ed6c10ba73f58766897a66bab396bd886f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:N32HQYHEJA5UKA5LCLEXPB7HYP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Matrix Nets: A New Deep Architecture for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdullah Rashwan, Agastya Kalra, Pascal Poupart","submitted_at":"2019-08-13T13:54:31Z","abstract_excerpt":"We present Matrix Nets (xNets), a new deep architecture for object detection. xNets map objects with different sizes and aspect ratios into layers where the sizes and the aspect ratios of the objects within their layers are nearly uniform. Hence, xNets provide a scale and aspect ratio aware architecture. We leverage xNets to enhance key-points based object detection. Our architecture achieves mAP of 47.8 on MS COCO, which is higher than any other single-shot detector while using half the number of parameters and training 3x faster than the next best architecture."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04646","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.04646/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-04T23:55:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KStzsdBpRkiG1uQlHYlBt4iLr8aJUzm/DKIIcM80v3cRhbTtQqE5cyGKprZ8MJeyPjNMKzTy1Ktq2iSVFKPuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T15:12:19.645718Z"},"content_sha256":"09e93dd901b3b2d684e50a4c0ba45731d0518811374a48a4ff92b9f301354537","schema_version":"1.0","event_id":"sha256:09e93dd901b3b2d684e50a4c0ba45731d0518811374a48a4ff92b9f301354537"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N32HQYHEJA5UKA5LCLEXPB7HYP/bundle.json","state_url":"https://pith.science/pith/N32HQYHEJA5UKA5LCLEXPB7HYP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N32HQYHEJA5UKA5LCLEXPB7HYP/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":"2026-08-15T15:12:19Z","links":{"resolver":"https://pith.science/pith/N32HQYHEJA5UKA5LCLEXPB7HYP","bundle":"https://pith.science/pith/N32HQYHEJA5UKA5LCLEXPB7HYP/bundle.json","state":"https://pith.science/pith/N32HQYHEJA5UKA5LCLEXPB7HYP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N32HQYHEJA5UKA5LCLEXPB7HYP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:N32HQYHEJA5UKA5LCLEXPB7HYP","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":"03bf34d82257414d88f46e8c8bc1422620ee1d590db91f8ce68c8c69278fab0b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-13T13:54:31Z","title_canon_sha256":"167a4f7e8af3d77b793866876e507b4dee4f69a59bc4ee051a785e74da73d066"},"schema_version":"1.0","source":{"id":"1908.04646","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.04646","created_at":"2026-07-04T23:55:57Z"},{"alias_kind":"arxiv_version","alias_value":"1908.04646v2","created_at":"2026-07-04T23:55:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04646","created_at":"2026-07-04T23:55:57Z"},{"alias_kind":"pith_short_12","alias_value":"N32HQYHEJA5U","created_at":"2026-07-04T23:55:57Z"},{"alias_kind":"pith_short_16","alias_value":"N32HQYHEJA5UKA5L","created_at":"2026-07-04T23:55:57Z"},{"alias_kind":"pith_short_8","alias_value":"N32HQYHE","created_at":"2026-07-04T23:55:57Z"}],"graph_snapshots":[{"event_id":"sha256:09e93dd901b3b2d684e50a4c0ba45731d0518811374a48a4ff92b9f301354537","target":"graph","created_at":"2026-07-04T23:55:57Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.04646/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Matrix Nets (xNets), a new deep architecture for object detection. xNets map objects with different sizes and aspect ratios into layers where the sizes and the aspect ratios of the objects within their layers are nearly uniform. Hence, xNets provide a scale and aspect ratio aware architecture. We leverage xNets to enhance key-points based object detection. Our architecture achieves mAP of 47.8 on MS COCO, which is higher than any other single-shot detector while using half the number of parameters and training 3x faster than the next best architecture.","authors_text":"Abdullah Rashwan, Agastya Kalra, Pascal Poupart","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-13T13:54:31Z","title":"Matrix Nets: A New Deep Architecture for Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04646","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":"sha256:32538aa5c04dce14250ddd33d709d1ed6c10ba73f58766897a66bab396bd886f","target":"record","created_at":"2026-07-04T23:55:57Z","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":"03bf34d82257414d88f46e8c8bc1422620ee1d590db91f8ce68c8c69278fab0b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-13T13:54:31Z","title_canon_sha256":"167a4f7e8af3d77b793866876e507b4dee4f69a59bc4ee051a785e74da73d066"},"schema_version":"1.0","source":{"id":"1908.04646","kind":"arxiv","version":2}},"canonical_sha256":"6ef47860e4483b4503ab12c97787e7c3f552f223628d86d2f8700202edf002fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ef47860e4483b4503ab12c97787e7c3f552f223628d86d2f8700202edf002fd","first_computed_at":"2026-07-04T23:55:57.025124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:55:57.025124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4SukcEZcNdx4bbrsDdwi3ij98POp5u2eGRJ+ESvcfgBnT5qci32MFyCs33eCfLqqIW28uipJiRIjP8NY7zt/DA==","signature_status":"signed_v1","signed_at":"2026-07-04T23:55:57.025568Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.04646","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32538aa5c04dce14250ddd33d709d1ed6c10ba73f58766897a66bab396bd886f","sha256:09e93dd901b3b2d684e50a4c0ba45731d0518811374a48a4ff92b9f301354537"],"state_sha256":"88ab3afe26e800ad0fcc9b465deea5c47a643af3c37b7a1be472dd4620217239"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DMB/ak43R32JbBIU8AMF/1P7Jbb9ju2+uiBFq1QUYRWF1WrZQ4EQjoAwWpg0zvgHqeedcT7yUhU7aVZGcb/0DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T15:12:19.652049Z","bundle_sha256":"73f20834a70daf19bde72d218d46c4ad3854e56ca6276a0ea0b976cdf9cff2d4"}}