{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:Z757LF4STIMYH6QZBNI7SEI7LC","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":"d977f9e8eeab6121f4d30e3e416639821ca9f4d3f06b4cb5ffdbbf6ad7532299","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-24T23:15:56Z","title_canon_sha256":"01bdd0e244fba259f7b5d3add7f8d365b8e4d531fa4225709b76ee529b10d826"},"schema_version":"1.0","source":{"id":"1611.08321","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.08321","created_at":"2026-05-18T00:56:39Z"},{"alias_kind":"arxiv_version","alias_value":"1611.08321v1","created_at":"2026-05-18T00:56:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.08321","created_at":"2026-05-18T00:56:39Z"},{"alias_kind":"pith_short_12","alias_value":"Z757LF4STIMY","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"Z757LF4STIMYH6QZ","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"Z757LF4S","created_at":"2026-05-18T12:30:53Z"}],"graph_snapshots":[{"event_id":"sha256:0f6d37fdd148fdd32c31b7a272a0972487593037974ea876b5c541c960185b73","target":"graph","created_at":"2026-05-18T00:56:39Z","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":"In this paper, we focus on training and evaluating effective word embeddings with both text and visual information. More specifically, we introduce a large-scale dataset with 300 million sentences describing over 40 million images crawled and downloaded from publicly available Pins (i.e. an image with sentence descriptions uploaded by users) on Pinterest. This dataset is more than 200 times larger than MS COCO, the standard large-scale image dataset with sentence descriptions. In addition, we construct an evaluation dataset to directly assess the effectiveness of word embeddings in terms of fi","authors_text":"Alan Yuille, Jiajing Xu, Junhua Mao, Yushi Jing","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-24T23:15:56Z","title":"Training and Evaluating Multimodal Word Embeddings with Large-scale Web Annotated Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.08321","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":"sha256:8f47e5c84c6f0a41675816372525b2e698652809dad9581b87858e3a6887a479","target":"record","created_at":"2026-05-18T00:56:39Z","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":"d977f9e8eeab6121f4d30e3e416639821ca9f4d3f06b4cb5ffdbbf6ad7532299","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-24T23:15:56Z","title_canon_sha256":"01bdd0e244fba259f7b5d3add7f8d365b8e4d531fa4225709b76ee529b10d826"},"schema_version":"1.0","source":{"id":"1611.08321","kind":"arxiv","version":1}},"canonical_sha256":"cffbf597929a1983fa190b51f9111f5884033f64721f39cde67268a4bf60259a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cffbf597929a1983fa190b51f9111f5884033f64721f39cde67268a4bf60259a","first_computed_at":"2026-05-18T00:56:39.449652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:56:39.449652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3QXSFoxy2mIm5I67OvGd278DVv4UtKJ4RJGhqQ8U30mzAJd7OJyH11ZrGL3jEMJnaZef/17iMLLBoS6+JqBdAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:56:39.450388Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.08321","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f47e5c84c6f0a41675816372525b2e698652809dad9581b87858e3a6887a479","sha256:0f6d37fdd148fdd32c31b7a272a0972487593037974ea876b5c541c960185b73"],"state_sha256":"82187f0e722ba95c6e09de004d7212751754a64ad1688b53763a922679612dfc"}