{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:4Q6ACBZPRGORL5FJXM34BKZFSQ","short_pith_number":"pith:4Q6ACBZP","schema_version":"1.0","canonical_sha256":"e43c01072f899d15f4a9bb37c0ab259419fc6e93c353a09c041887b2d14df57b","source":{"kind":"arxiv","id":"1612.09161","version":2},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1612.09161","created_at":"2026-05-18T00:38:36.137147+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.09161v2","created_at":"2026-05-18T00:38:36.137147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.09161","created_at":"2026-05-18T00:38:36.137147+00:00"},{"alias_kind":"pith_short_12","alias_value":"4Q6ACBZPRGOR","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_16","alias_value":"4Q6ACBZPRGORL5FJ","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_8","alias_value":"4Q6ACBZP","created_at":"2026-05-18T12:29:58.707656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4Q6ACBZPRGORL5FJXM34BKZFSQ","json":"https://pith.science/pith/4Q6ACBZPRGORL5FJXM34BKZFSQ.json","graph_json":"https://pith.science/api/pith-number/4Q6ACBZPRGORL5FJXM34BKZFSQ/graph.json","events_json":"https://pith.science/api/pith-number/4Q6ACBZPRGORL5FJXM34BKZFSQ/events.json","paper":"https://pith.science/paper/4Q6ACBZP"},"agent_actions":{"view_html":"https://pith.science/pith/4Q6ACBZPRGORL5FJXM34BKZFSQ","download_json":"https://pith.science/pith/4Q6ACBZPRGORL5FJXM34BKZFSQ.json","view_paper":"https://pith.science/paper/4Q6ACBZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.09161&json=true","fetch_graph":"https://pith.science/api/pith-number/4Q6ACBZPRGORL5FJXM34BKZFSQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4Q6ACBZPRGORL5FJXM34BKZFSQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4Q6ACBZPRGORL5FJXM34BKZFSQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4Q6ACBZPRGORL5FJXM34BKZFSQ/action/storage_attestation","attest_author":"https://pith.science/pith/4Q6ACBZPRGORL5FJXM34BKZFSQ/action/author_attestation","sign_citation":"https://pith.science/pith/4Q6ACBZPRGORL5FJXM34BKZFSQ/action/citation_signature","submit_replication":"https://pith.science/pith/4Q6ACBZPRGORL5FJXM34BKZFSQ/action/replication_record"}},"created_at":"2026-05-18T00:38:36.137147+00:00","updated_at":"2026-05-18T00:38:36.137147+00:00"}