{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:4Q6ACBZPRGORL5FJXM34BKZFSQ","short_pith_number":"pith:4Q6ACBZP","canonical_record":{"source":{"id":"1612.09161","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-29T14:50:53Z","cross_cats_sorted":[],"title_canon_sha256":"6c3248d4c72978e4ee5fb980154e71ddf651e5e9d3aed4494e3770d276aba0e1","abstract_canon_sha256":"b3449860ed4c87acacf75cc7511023a603d6788756e4c30e2f9a42edf80588af"},"schema_version":"1.0"},"canonical_sha256":"e43c01072f899d15f4a9bb37c0ab259419fc6e93c353a09c041887b2d14df57b","source":{"kind":"arxiv","id":"1612.09161","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.09161","created_at":"2026-05-18T00:38:36Z"},{"alias_kind":"arxiv_version","alias_value":"1612.09161v2","created_at":"2026-05-18T00:38:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.09161","created_at":"2026-05-18T00:38:36Z"},{"alias_kind":"pith_short_12","alias_value":"4Q6ACBZPRGOR","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_16","alias_value":"4Q6ACBZPRGORL5FJ","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_8","alias_value":"4Q6ACBZP","created_at":"2026-05-18T12:29:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:4Q6ACBZPRGORL5FJXM34BKZFSQ","target":"record","payload":{"canonical_record":{"source":{"id":"1612.09161","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-29T14:50:53Z","cross_cats_sorted":[],"title_canon_sha256":"6c3248d4c72978e4ee5fb980154e71ddf651e5e9d3aed4494e3770d276aba0e1","abstract_canon_sha256":"b3449860ed4c87acacf75cc7511023a603d6788756e4c30e2f9a42edf80588af"},"schema_version":"1.0"},"canonical_sha256":"e43c01072f899d15f4a9bb37c0ab259419fc6e93c353a09c041887b2d14df57b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:36.137712Z","signature_b64":"4fTLpVF2CuPNlJ6Cbb1eXBB9mh2Bg99zozZG1a7XPsIgk+V05eLsLZYHNOABQK7E/rOvDtg93a8vJsRWwA0CBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e43c01072f899d15f4a9bb37c0ab259419fc6e93c353a09c041887b2d14df57b","last_reissued_at":"2026-05-18T00:38:36.137028Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:36.137028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.09161","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":"2026-05-18T00:38:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qBj5dIyUCpKBEo84Y7slWk6MiCHwztL2IIOIXiWeKbH8Mm+3u8Wwk1/BArR+ucgVYUutfVEMmiMX4qJEGbO5BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T04:21:02.499431Z"},"content_sha256":"4e77ac1c48af3a2fd136b707bdc7c6968c592c9761bac71c4b3f5973bd99128f","schema_version":"1.0","event_id":"sha256:4e77ac1c48af3a2fd136b707bdc7c6968c592c9761bac71c4b3f5973bd99128f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:4Q6ACBZPRGORL5FJXM34BKZFSQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Visual N-Grams from Web Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Allan Jabri, Ang Li, Armand Joulin, Laurens van der Maaten","submitted_at":"2016-12-29T14:50:53Z","abstract_excerpt":"Real-world image recognition systems need to recognize tens of thousands of classes that constitute a plethora of visual concepts. The traditional approach of annotating thousands of images per class for training is infeasible in such a scenario, prompting the use of webly supervised data. This paper explores the training of image-recognition systems on large numbers of images and associated user comments. In particular, we develop visual n-gram models that can predict arbitrary phrases that are relevant to the content of an image. Our visual n-gram models are feed-forward convolutional networ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.09161","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":"2026-05-18T00:38:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LykNM8kwyNtQfjAxsgSSlUfGuZgJlZ+9Xrr4VM0QcqpUJSuqkEvvshrZp6d8Dei9Ajo8fbyWh+ULwZ2MC4I7DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T04:21:02.499784Z"},"content_sha256":"1591b250dac23b55578aa8507b1963eca6a4cebe105f87e9549e371273fda277","schema_version":"1.0","event_id":"sha256:1591b250dac23b55578aa8507b1963eca6a4cebe105f87e9549e371273fda277"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4Q6ACBZPRGORL5FJXM34BKZFSQ/bundle.json","state_url":"https://pith.science/pith/4Q6ACBZPRGORL5FJXM34BKZFSQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4Q6ACBZPRGORL5FJXM34BKZFSQ/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":"2026-06-04T04:21:02Z","links":{"resolver":"https://pith.science/pith/4Q6ACBZPRGORL5FJXM34BKZFSQ","bundle":"https://pith.science/pith/4Q6ACBZPRGORL5FJXM34BKZFSQ/bundle.json","state":"https://pith.science/pith/4Q6ACBZPRGORL5FJXM34BKZFSQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4Q6ACBZPRGORL5FJXM34BKZFSQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:4Q6ACBZPRGORL5FJXM34BKZFSQ","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":"b3449860ed4c87acacf75cc7511023a603d6788756e4c30e2f9a42edf80588af","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-29T14:50:53Z","title_canon_sha256":"6c3248d4c72978e4ee5fb980154e71ddf651e5e9d3aed4494e3770d276aba0e1"},"schema_version":"1.0","source":{"id":"1612.09161","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.09161","created_at":"2026-05-18T00:38:36Z"},{"alias_kind":"arxiv_version","alias_value":"1612.09161v2","created_at":"2026-05-18T00:38:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.09161","created_at":"2026-05-18T00:38:36Z"},{"alias_kind":"pith_short_12","alias_value":"4Q6ACBZPRGOR","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_16","alias_value":"4Q6ACBZPRGORL5FJ","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_8","alias_value":"4Q6ACBZP","created_at":"2026-05-18T12:29:58Z"}],"graph_snapshots":[{"event_id":"sha256:1591b250dac23b55578aa8507b1963eca6a4cebe105f87e9549e371273fda277","target":"graph","created_at":"2026-05-18T00:38:36Z","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":"Real-world image recognition systems need to recognize tens of thousands of classes that constitute a plethora of visual concepts. The traditional approach of annotating thousands of images per class for training is infeasible in such a scenario, prompting the use of webly supervised data. This paper explores the training of image-recognition systems on large numbers of images and associated user comments. In particular, we develop visual n-gram models that can predict arbitrary phrases that are relevant to the content of an image. Our visual n-gram models are feed-forward convolutional networ","authors_text":"Allan Jabri, Ang Li, Armand Joulin, Laurens van der Maaten","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-29T14:50:53Z","title":"Learning Visual N-Grams from Web Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.09161","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":"sha256:4e77ac1c48af3a2fd136b707bdc7c6968c592c9761bac71c4b3f5973bd99128f","target":"record","created_at":"2026-05-18T00:38:36Z","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":"b3449860ed4c87acacf75cc7511023a603d6788756e4c30e2f9a42edf80588af","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-29T14:50:53Z","title_canon_sha256":"6c3248d4c72978e4ee5fb980154e71ddf651e5e9d3aed4494e3770d276aba0e1"},"schema_version":"1.0","source":{"id":"1612.09161","kind":"arxiv","version":2}},"canonical_sha256":"e43c01072f899d15f4a9bb37c0ab259419fc6e93c353a09c041887b2d14df57b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e43c01072f899d15f4a9bb37c0ab259419fc6e93c353a09c041887b2d14df57b","first_computed_at":"2026-05-18T00:38:36.137028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:36.137028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4fTLpVF2CuPNlJ6Cbb1eXBB9mh2Bg99zozZG1a7XPsIgk+V05eLsLZYHNOABQK7E/rOvDtg93a8vJsRWwA0CBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:36.137712Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.09161","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e77ac1c48af3a2fd136b707bdc7c6968c592c9761bac71c4b3f5973bd99128f","sha256:1591b250dac23b55578aa8507b1963eca6a4cebe105f87e9549e371273fda277"],"state_sha256":"9f5d71cd690cab882dece732fe08d76d1740bf92399c8b6fc78031d067a1dcc2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KB25x/FI/xeX6GZZNfIQf4VqzLPvGCgxBmgG817uk5K3zyqq13jCh8Sf5ArnXD5aRN5yCOMRKtfzQV4uCJH2Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T04:21:02.501883Z","bundle_sha256":"3381d6bab1eb3f3ea490ed3b0d0be36e014da5e8865dbafe4f280edfd42af959"}}