{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:V4VLFVQSCZYSJB2Q4K62C3BYGS","short_pith_number":"pith:V4VLFVQS","canonical_record":{"source":{"id":"1703.08050","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-23T12:55:34Z","cross_cats_sorted":[],"title_canon_sha256":"caf4cfb6bbabbff3edb04957fbe4cdcf85c9a83b4924b24e29b21de6515da2cb","abstract_canon_sha256":"4339d25c7b45ce3f95d578d4b1d703261910baf8ebe85f325d43a13ebbbbeaf7"},"schema_version":"1.0"},"canonical_sha256":"af2ab2d6121671248750e2bda16c3834a1710243185e47d796bc764933e12711","source":{"kind":"arxiv","id":"1703.08050","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.08050","created_at":"2026-05-18T00:19:42Z"},{"alias_kind":"arxiv_version","alias_value":"1703.08050v3","created_at":"2026-05-18T00:19:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.08050","created_at":"2026-05-18T00:19:42Z"},{"alias_kind":"pith_short_12","alias_value":"V4VLFVQSCZYS","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"V4VLFVQSCZYSJB2Q","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"V4VLFVQS","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:V4VLFVQSCZYSJB2Q4K62C3BYGS","target":"record","payload":{"canonical_record":{"source":{"id":"1703.08050","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-23T12:55:34Z","cross_cats_sorted":[],"title_canon_sha256":"caf4cfb6bbabbff3edb04957fbe4cdcf85c9a83b4924b24e29b21de6515da2cb","abstract_canon_sha256":"4339d25c7b45ce3f95d578d4b1d703261910baf8ebe85f325d43a13ebbbbeaf7"},"schema_version":"1.0"},"canonical_sha256":"af2ab2d6121671248750e2bda16c3834a1710243185e47d796bc764933e12711","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:42.376283Z","signature_b64":"8pq6xNJCY/+cjg9ZabkZVXh9d69uG+UeWrki3jbwfyWbCiqqHBWBgrhAHTZ6casTm8G9EgWJTGNB3aJCKi6qDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af2ab2d6121671248750e2bda16c3834a1710243185e47d796bc764933e12711","last_reissued_at":"2026-05-18T00:19:42.375619Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:42.375619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.08050","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:19:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kiFGW/PmknYC4DznyVIv+2f8hEZsp5MIEuQ5XEv3YukhuK/5QzFx3T6781tB3vCmKme54fbvxxjtAa/Aijj5DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T00:28:20.052202Z"},"content_sha256":"de5cecb85ea26b3ce0e03fb4330a52379e3837201c39a40c6b1586c61a69bafc","schema_version":"1.0","event_id":"sha256:de5cecb85ea26b3ce0e03fb4330a52379e3837201c39a40c6b1586c61a69bafc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:V4VLFVQSCZYSJB2Q4K62C3BYGS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is Second-order Information Helpful for Large-scale Visual Recognition?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangtao Xie, Peihua Li, Qilong Wang, Wangmeng Zuo","submitted_at":"2017-03-23T12:55:34Z","abstract_excerpt":"By stacking layers of convolution and nonlinearity, convolutional networks (ConvNets) effectively learn from low-level to high-level features and discriminative representations. Since the end goal of large-scale recognition is to delineate complex boundaries of thousands of classes, adequate exploration of feature distributions is important for realizing full potentials of ConvNets. However, state-of-the-art works concentrate only on deeper or wider architecture design, while rarely exploring feature statistics higher than first-order. We take a step towards addressing this problem. Our method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.08050","kind":"arxiv","version":3},"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":"2026-05-18T00:19:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vKO+IL8DKxDKUOW4TTuxpln86EfzhTQrG7i/q6K2TW/bjgEQKpdLgxmAEOZONGEIdkPMIlT6bscQylLWZV4tDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T00:28:20.052604Z"},"content_sha256":"ad647cb0e8c40831d66b359b9cd166bed330ca34b3ace5416ec53aea4034148e","schema_version":"1.0","event_id":"sha256:ad647cb0e8c40831d66b359b9cd166bed330ca34b3ace5416ec53aea4034148e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V4VLFVQSCZYSJB2Q4K62C3BYGS/bundle.json","state_url":"https://pith.science/pith/V4VLFVQSCZYSJB2Q4K62C3BYGS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V4VLFVQSCZYSJB2Q4K62C3BYGS/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":"2026-06-23T00:28:20Z","links":{"resolver":"https://pith.science/pith/V4VLFVQSCZYSJB2Q4K62C3BYGS","bundle":"https://pith.science/pith/V4VLFVQSCZYSJB2Q4K62C3BYGS/bundle.json","state":"https://pith.science/pith/V4VLFVQSCZYSJB2Q4K62C3BYGS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V4VLFVQSCZYSJB2Q4K62C3BYGS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:V4VLFVQSCZYSJB2Q4K62C3BYGS","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":"4339d25c7b45ce3f95d578d4b1d703261910baf8ebe85f325d43a13ebbbbeaf7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-23T12:55:34Z","title_canon_sha256":"caf4cfb6bbabbff3edb04957fbe4cdcf85c9a83b4924b24e29b21de6515da2cb"},"schema_version":"1.0","source":{"id":"1703.08050","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.08050","created_at":"2026-05-18T00:19:42Z"},{"alias_kind":"arxiv_version","alias_value":"1703.08050v3","created_at":"2026-05-18T00:19:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.08050","created_at":"2026-05-18T00:19:42Z"},{"alias_kind":"pith_short_12","alias_value":"V4VLFVQSCZYS","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"V4VLFVQSCZYSJB2Q","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"V4VLFVQS","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:ad647cb0e8c40831d66b359b9cd166bed330ca34b3ace5416ec53aea4034148e","target":"graph","created_at":"2026-05-18T00:19:42Z","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":"By stacking layers of convolution and nonlinearity, convolutional networks (ConvNets) effectively learn from low-level to high-level features and discriminative representations. Since the end goal of large-scale recognition is to delineate complex boundaries of thousands of classes, adequate exploration of feature distributions is important for realizing full potentials of ConvNets. However, state-of-the-art works concentrate only on deeper or wider architecture design, while rarely exploring feature statistics higher than first-order. We take a step towards addressing this problem. Our method","authors_text":"Jiangtao Xie, Peihua Li, Qilong Wang, Wangmeng Zuo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-23T12:55:34Z","title":"Is Second-order Information Helpful for Large-scale Visual Recognition?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.08050","kind":"arxiv","version":3},"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:de5cecb85ea26b3ce0e03fb4330a52379e3837201c39a40c6b1586c61a69bafc","target":"record","created_at":"2026-05-18T00:19:42Z","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":"4339d25c7b45ce3f95d578d4b1d703261910baf8ebe85f325d43a13ebbbbeaf7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-23T12:55:34Z","title_canon_sha256":"caf4cfb6bbabbff3edb04957fbe4cdcf85c9a83b4924b24e29b21de6515da2cb"},"schema_version":"1.0","source":{"id":"1703.08050","kind":"arxiv","version":3}},"canonical_sha256":"af2ab2d6121671248750e2bda16c3834a1710243185e47d796bc764933e12711","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af2ab2d6121671248750e2bda16c3834a1710243185e47d796bc764933e12711","first_computed_at":"2026-05-18T00:19:42.375619Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:42.375619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8pq6xNJCY/+cjg9ZabkZVXh9d69uG+UeWrki3jbwfyWbCiqqHBWBgrhAHTZ6casTm8G9EgWJTGNB3aJCKi6qDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:42.376283Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.08050","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de5cecb85ea26b3ce0e03fb4330a52379e3837201c39a40c6b1586c61a69bafc","sha256:ad647cb0e8c40831d66b359b9cd166bed330ca34b3ace5416ec53aea4034148e"],"state_sha256":"2cef45ca9a51cb6f5ebf7070e0278ad1955662547b297aa58894033f113860e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FbYn7E4B8zGUXv7uDrv7cIY+D/bvkwuG4pK3Ymj8iUE8ApaxqfcdbH1jQNtg88jCGQ9+MHz/oDj+VDYH8FqnDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-23T00:28:20.054736Z","bundle_sha256":"5a4dcccbe06cdbd5b08ea82f7a6670d7acbfa036e7b92c9c506233624c9db87d"}}