{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:RVK3GXK5HR3JHHPBIEOZKUS6IG","short_pith_number":"pith:RVK3GXK5","canonical_record":{"source":{"id":"1505.01554","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-07T00:56:15Z","cross_cats_sorted":[],"title_canon_sha256":"bfd88897b73e065ba7e7b3efb7d12dceb9168def3dda1065bf6ac1b8742cb715","abstract_canon_sha256":"7fc6342f3455616bd2cd90fa813ca3ca0533f3f608c36659fd909da3ef244c67"},"schema_version":"1.0"},"canonical_sha256":"8d55b35d5d3c76939de1411d95525e41925cb8a1baf6101967879d463ad59e31","source":{"kind":"arxiv","id":"1505.01554","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.01554","created_at":"2026-05-18T01:30:48Z"},{"alias_kind":"arxiv_version","alias_value":"1505.01554v2","created_at":"2026-05-18T01:30:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.01554","created_at":"2026-05-18T01:30:48Z"},{"alias_kind":"pith_short_12","alias_value":"RVK3GXK5HR3J","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"RVK3GXK5HR3JHHPB","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"RVK3GXK5","created_at":"2026-05-18T12:29:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:RVK3GXK5HR3JHHPBIEOZKUS6IG","target":"record","payload":{"canonical_record":{"source":{"id":"1505.01554","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-07T00:56:15Z","cross_cats_sorted":[],"title_canon_sha256":"bfd88897b73e065ba7e7b3efb7d12dceb9168def3dda1065bf6ac1b8742cb715","abstract_canon_sha256":"7fc6342f3455616bd2cd90fa813ca3ca0533f3f608c36659fd909da3ef244c67"},"schema_version":"1.0"},"canonical_sha256":"8d55b35d5d3c76939de1411d95525e41925cb8a1baf6101967879d463ad59e31","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:30:48.894017Z","signature_b64":"Fj8d3AZUyC8UvTiV7IbCl7JcubsIWpcbL2691E40n/X/KMz5R2rS2Wf2N+JcT1YIPru4qjHXDute8gkcQOz8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d55b35d5d3c76939de1411d95525e41925cb8a1baf6101967879d463ad59e31","last_reissued_at":"2026-05-18T01:30:48.893551Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:30:48.893551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1505.01554","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":"2026-05-18T01:30:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xJrQofZdpd258h3zl/oybFuHnh//kIBExA3IGyt3WTaVTEj1h6w0xGGTx/iOS3OZUmCmaqEq5un1uEeJ+HlPDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T22:54:21.630459Z"},"content_sha256":"a7dfc5298b4a1fbcdd57417000317113a09f24f8f800bf77a6499729398f7cf3","schema_version":"1.0","event_id":"sha256:a7dfc5298b4a1fbcdd57417000317113a09f24f8f800bf77a6499729398f7cf3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:RVK3GXK5HR3JHHPBIEOZKUS6IG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Webly Supervised Learning of Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Gupta, Xinlei Chen","submitted_at":"2015-05-07T00:56:15Z","abstract_excerpt":"We present an approach to utilize large amounts of web data for learning CNNs. Specifically inspired by curriculum learning, we present a two-step approach for CNN training. First, we use easy images to train an initial visual representation. We then use this initial CNN and adapt it to harder, more realistic images by leveraging the structure of data and categories. We demonstrate that our two-stage CNN outperforms a fine-tuned CNN trained on ImageNet on Pascal VOC 2012. We also demonstrate the strength of webly supervised learning by localizing objects in web images and training a R-CNN styl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.01554","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":"2026-05-18T01:30:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XIjedeiXQj7g40uhsXIClIJgj5eZZQ3SP1NTYFgwrpJn5y19eY+oyLo/m7SRv1K1eTOVW9DNzxgQoZINzoTzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T22:54:21.631125Z"},"content_sha256":"9bcd3109d91b128847f8947ba6ef4bbe8459d12eac86703fca62460d87e5f553","schema_version":"1.0","event_id":"sha256:9bcd3109d91b128847f8947ba6ef4bbe8459d12eac86703fca62460d87e5f553"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RVK3GXK5HR3JHHPBIEOZKUS6IG/bundle.json","state_url":"https://pith.science/pith/RVK3GXK5HR3JHHPBIEOZKUS6IG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RVK3GXK5HR3JHHPBIEOZKUS6IG/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":"2026-06-06T22:54:21Z","links":{"resolver":"https://pith.science/pith/RVK3GXK5HR3JHHPBIEOZKUS6IG","bundle":"https://pith.science/pith/RVK3GXK5HR3JHHPBIEOZKUS6IG/bundle.json","state":"https://pith.science/pith/RVK3GXK5HR3JHHPBIEOZKUS6IG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RVK3GXK5HR3JHHPBIEOZKUS6IG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:RVK3GXK5HR3JHHPBIEOZKUS6IG","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":"7fc6342f3455616bd2cd90fa813ca3ca0533f3f608c36659fd909da3ef244c67","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-07T00:56:15Z","title_canon_sha256":"bfd88897b73e065ba7e7b3efb7d12dceb9168def3dda1065bf6ac1b8742cb715"},"schema_version":"1.0","source":{"id":"1505.01554","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.01554","created_at":"2026-05-18T01:30:48Z"},{"alias_kind":"arxiv_version","alias_value":"1505.01554v2","created_at":"2026-05-18T01:30:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.01554","created_at":"2026-05-18T01:30:48Z"},{"alias_kind":"pith_short_12","alias_value":"RVK3GXK5HR3J","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"RVK3GXK5HR3JHHPB","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"RVK3GXK5","created_at":"2026-05-18T12:29:39Z"}],"graph_snapshots":[{"event_id":"sha256:9bcd3109d91b128847f8947ba6ef4bbe8459d12eac86703fca62460d87e5f553","target":"graph","created_at":"2026-05-18T01:30:48Z","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":"We present an approach to utilize large amounts of web data for learning CNNs. Specifically inspired by curriculum learning, we present a two-step approach for CNN training. First, we use easy images to train an initial visual representation. We then use this initial CNN and adapt it to harder, more realistic images by leveraging the structure of data and categories. We demonstrate that our two-stage CNN outperforms a fine-tuned CNN trained on ImageNet on Pascal VOC 2012. We also demonstrate the strength of webly supervised learning by localizing objects in web images and training a R-CNN styl","authors_text":"Abhinav Gupta, Xinlei Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-07T00:56:15Z","title":"Webly Supervised Learning of Convolutional Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.01554","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:a7dfc5298b4a1fbcdd57417000317113a09f24f8f800bf77a6499729398f7cf3","target":"record","created_at":"2026-05-18T01:30:48Z","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":"7fc6342f3455616bd2cd90fa813ca3ca0533f3f608c36659fd909da3ef244c67","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-07T00:56:15Z","title_canon_sha256":"bfd88897b73e065ba7e7b3efb7d12dceb9168def3dda1065bf6ac1b8742cb715"},"schema_version":"1.0","source":{"id":"1505.01554","kind":"arxiv","version":2}},"canonical_sha256":"8d55b35d5d3c76939de1411d95525e41925cb8a1baf6101967879d463ad59e31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d55b35d5d3c76939de1411d95525e41925cb8a1baf6101967879d463ad59e31","first_computed_at":"2026-05-18T01:30:48.893551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:30:48.893551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fj8d3AZUyC8UvTiV7IbCl7JcubsIWpcbL2691E40n/X/KMz5R2rS2Wf2N+JcT1YIPru4qjHXDute8gkcQOz8Dw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:30:48.894017Z","signed_message":"canonical_sha256_bytes"},"source_id":"1505.01554","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7dfc5298b4a1fbcdd57417000317113a09f24f8f800bf77a6499729398f7cf3","sha256:9bcd3109d91b128847f8947ba6ef4bbe8459d12eac86703fca62460d87e5f553"],"state_sha256":"d5cbdb44d051c417493b5ab4c40d49ae4cbdbe54872daed3d1c2475eedd83ef0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DCPBg63Y+J5Gns7r/KtZ0MBtk1BCGFQ4jrRr8At5rRRmDo/O1vowBS4h1d0CKbcc4lbQiXaQazPSuOIXXh6BDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T22:54:21.634670Z","bundle_sha256":"475e3e2149569ff52bc9c4a093f986f5c10ff08779d2a89b45632593901c9154"}}