{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:4DHJZ35BEEMMVRVKKYCLK5JR4S","short_pith_number":"pith:4DHJZ35B","canonical_record":{"source":{"id":"2007.01618","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-03T11:24:43Z","cross_cats_sorted":[],"title_canon_sha256":"07eea79746d168461903853fbe0f40e4e2e9c7e6ec2b48450ba993c57656168c","abstract_canon_sha256":"ccfec7db90c26f0e57464b731cf6b4c1d768a80385467e2ee9c9b4355d01ce32"},"schema_version":"1.0"},"canonical_sha256":"e0ce9cefa12118cac6aa5604b57531e4b6bf228cd80aab8620dcf509d92a2e25","source":{"kind":"arxiv","id":"2007.01618","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.01618","created_at":"2026-07-05T01:16:03Z"},{"alias_kind":"arxiv_version","alias_value":"2007.01618v1","created_at":"2026-07-05T01:16:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.01618","created_at":"2026-07-05T01:16:03Z"},{"alias_kind":"pith_short_12","alias_value":"4DHJZ35BEEMM","created_at":"2026-07-05T01:16:03Z"},{"alias_kind":"pith_short_16","alias_value":"4DHJZ35BEEMMVRVK","created_at":"2026-07-05T01:16:03Z"},{"alias_kind":"pith_short_8","alias_value":"4DHJZ35B","created_at":"2026-07-05T01:16:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:4DHJZ35BEEMMVRVKKYCLK5JR4S","target":"record","payload":{"canonical_record":{"source":{"id":"2007.01618","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-03T11:24:43Z","cross_cats_sorted":[],"title_canon_sha256":"07eea79746d168461903853fbe0f40e4e2e9c7e6ec2b48450ba993c57656168c","abstract_canon_sha256":"ccfec7db90c26f0e57464b731cf6b4c1d768a80385467e2ee9c9b4355d01ce32"},"schema_version":"1.0"},"canonical_sha256":"e0ce9cefa12118cac6aa5604b57531e4b6bf228cd80aab8620dcf509d92a2e25","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:16:03.335151Z","signature_b64":"F/GBfQNVYBGND4DvuQx367SqKF6Exp1M59m9Fylo1SpXRyQJNlcsvzkWl+TEgRVIWZf5ALcxFsXjoO/FHPqqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0ce9cefa12118cac6aa5604b57531e4b6bf228cd80aab8620dcf509d92a2e25","last_reissued_at":"2026-07-05T01:16:03.334736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:16:03.334736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.01618","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":"2026-07-05T01:16:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YYY7PL9+UsPJBobJfAILyzmjrqJBoiszoyk6yx4rVBC50JDQ+w7sQS68DrpzgB0OQxKV/o8h9W+GimeZIwWbAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:52:50.750920Z"},"content_sha256":"f9e5df8dbe5ea5ec0c5a0e184c9359af32c8b06e04e67815aa1f1f7e48fa2b9a","schema_version":"1.0","event_id":"sha256:f9e5df8dbe5ea5ec0c5a0e184c9359af32c8b06e04e67815aa1f1f7e48fa2b9a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:4DHJZ35BEEMMVRVKKYCLK5JR4S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Balanced Symmetric Cross Entropy for Large Scale Imbalanced and Noisy Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feifei Huang, Jie Li, Xuelin Zhu","submitted_at":"2020-07-03T11:24:43Z","abstract_excerpt":"Deep convolution neural network has attracted many attentions in large-scale visual classification task, and achieves significant performance improvement compared to traditional visual analysis methods. In this paper, we explore many kinds of deep convolution neural network architectures for large-scale product recognition task, which is heavily class-imbalanced and noisy labeled data, making it more challenged. Extensive experiments show that PNASNet achieves best performance among a variety of convolutional architectures. Together with ensemble technology and negative learning loss for noisy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.01618","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.01618/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":"2026-07-05T01:16:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KJUL0m0vZqEAU/1Q2vKcRxyZhiEdJCOe+DQclngE7T3i1ZCoxKUTPpqunFZ+m9MTOhwVIWc5OjRikR9SAdhdAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:52:50.751455Z"},"content_sha256":"5a628243b59180f256ea14d5db1b0f7db23a26c41f3c1ad96bd1fd2223071f26","schema_version":"1.0","event_id":"sha256:5a628243b59180f256ea14d5db1b0f7db23a26c41f3c1ad96bd1fd2223071f26"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4DHJZ35BEEMMVRVKKYCLK5JR4S/bundle.json","state_url":"https://pith.science/pith/4DHJZ35BEEMMVRVKKYCLK5JR4S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4DHJZ35BEEMMVRVKKYCLK5JR4S/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":"2026-08-08T23:52:50Z","links":{"resolver":"https://pith.science/pith/4DHJZ35BEEMMVRVKKYCLK5JR4S","bundle":"https://pith.science/pith/4DHJZ35BEEMMVRVKKYCLK5JR4S/bundle.json","state":"https://pith.science/pith/4DHJZ35BEEMMVRVKKYCLK5JR4S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4DHJZ35BEEMMVRVKKYCLK5JR4S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4DHJZ35BEEMMVRVKKYCLK5JR4S","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":"ccfec7db90c26f0e57464b731cf6b4c1d768a80385467e2ee9c9b4355d01ce32","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-03T11:24:43Z","title_canon_sha256":"07eea79746d168461903853fbe0f40e4e2e9c7e6ec2b48450ba993c57656168c"},"schema_version":"1.0","source":{"id":"2007.01618","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.01618","created_at":"2026-07-05T01:16:03Z"},{"alias_kind":"arxiv_version","alias_value":"2007.01618v1","created_at":"2026-07-05T01:16:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.01618","created_at":"2026-07-05T01:16:03Z"},{"alias_kind":"pith_short_12","alias_value":"4DHJZ35BEEMM","created_at":"2026-07-05T01:16:03Z"},{"alias_kind":"pith_short_16","alias_value":"4DHJZ35BEEMMVRVK","created_at":"2026-07-05T01:16:03Z"},{"alias_kind":"pith_short_8","alias_value":"4DHJZ35B","created_at":"2026-07-05T01:16:03Z"}],"graph_snapshots":[{"event_id":"sha256:5a628243b59180f256ea14d5db1b0f7db23a26c41f3c1ad96bd1fd2223071f26","target":"graph","created_at":"2026-07-05T01:16:03Z","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/2007.01618/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep convolution neural network has attracted many attentions in large-scale visual classification task, and achieves significant performance improvement compared to traditional visual analysis methods. In this paper, we explore many kinds of deep convolution neural network architectures for large-scale product recognition task, which is heavily class-imbalanced and noisy labeled data, making it more challenged. Extensive experiments show that PNASNet achieves best performance among a variety of convolutional architectures. Together with ensemble technology and negative learning loss for noisy","authors_text":"Feifei Huang, Jie Li, Xuelin Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-03T11:24:43Z","title":"Balanced Symmetric Cross Entropy for Large Scale Imbalanced and Noisy Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.01618","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:f9e5df8dbe5ea5ec0c5a0e184c9359af32c8b06e04e67815aa1f1f7e48fa2b9a","target":"record","created_at":"2026-07-05T01:16:03Z","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":"ccfec7db90c26f0e57464b731cf6b4c1d768a80385467e2ee9c9b4355d01ce32","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-03T11:24:43Z","title_canon_sha256":"07eea79746d168461903853fbe0f40e4e2e9c7e6ec2b48450ba993c57656168c"},"schema_version":"1.0","source":{"id":"2007.01618","kind":"arxiv","version":1}},"canonical_sha256":"e0ce9cefa12118cac6aa5604b57531e4b6bf228cd80aab8620dcf509d92a2e25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0ce9cefa12118cac6aa5604b57531e4b6bf228cd80aab8620dcf509d92a2e25","first_computed_at":"2026-07-05T01:16:03.334736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:16:03.334736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F/GBfQNVYBGND4DvuQx367SqKF6Exp1M59m9Fylo1SpXRyQJNlcsvzkWl+TEgRVIWZf5ALcxFsXjoO/FHPqqAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:16:03.335151Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.01618","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9e5df8dbe5ea5ec0c5a0e184c9359af32c8b06e04e67815aa1f1f7e48fa2b9a","sha256:5a628243b59180f256ea14d5db1b0f7db23a26c41f3c1ad96bd1fd2223071f26"],"state_sha256":"8a673cbc1beea4ff78ae544ed07dd1ca4b350dd0a09ca5a0ac240cb367b54775"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F8phzGNUooZ1WZoX5Qqk5vLEyfcBwuVUkMBcyoQYfXPoEAscSrddV2OC/yD/1j0XLuYGgj8c7W7kB8JymVvbBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T23:52:50.756116Z","bundle_sha256":"dbb32f25848c05269cfd2fc36a64bd7af20d93b3f99923cbc5b7ce01d269a63a"}}