{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TCF3APMDD26J7PNQZOZYZX3IGR","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":"29fad2caccc8b81f78571d10c30c249366ce44c579169516f402eaa5fd7089b7","cross_cats_sorted":["cs.CL","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-06T11:04:08Z","title_canon_sha256":"519b23fdccbce00499d428298831a5e010ed38a923b1db136dbbd51ea5958107"},"schema_version":"1.0","source":{"id":"1912.03063","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.03063","created_at":"2026-07-05T00:24:30Z"},{"alias_kind":"arxiv_version","alias_value":"1912.03063v1","created_at":"2026-07-05T00:24:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.03063","created_at":"2026-07-05T00:24:30Z"},{"alias_kind":"pith_short_12","alias_value":"TCF3APMDD26J","created_at":"2026-07-05T00:24:30Z"},{"alias_kind":"pith_short_16","alias_value":"TCF3APMDD26J7PNQ","created_at":"2026-07-05T00:24:30Z"},{"alias_kind":"pith_short_8","alias_value":"TCF3APMD","created_at":"2026-07-05T00:24:30Z"}],"graph_snapshots":[{"event_id":"sha256:948664d1796c4f24a701a28547e8c0894e87909e5a9ceac593896778f04cbb12","target":"graph","created_at":"2026-07-05T00:24:30Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1912.03063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The large adoption of the self-attention (i.e. transformer model) and BERT-like training principles has recently resulted in a number of high performing models on a large panoply of vision-and-language problems (such as Visual Question Answering (VQA), image retrieval, etc.). In this paper we claim that these State-Of-The-Art (SOTA) approaches perform reasonably well in structuring information inside a single modality but, despite their impressive performances , they tend to struggle to identify fine-grained inter-modality relationships. Indeed, such relations are frequently assumed to be impl","authors_text":"Christian Wolf (LIRIS), Corentin Kervadec (LIRIS), Grigory Antipov, Moez Baccouche","cross_cats":["cs.CL","cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-06T11:04:08Z","title":"Weak Supervision helps Emergence of Word-Object Alignment and improves Vision-Language Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.03063","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:d2e92c7ba48f2f3edb1268cf7c78de23b30e28dd50d358d13bca9b8d4fd3c106","target":"record","created_at":"2026-07-05T00:24:30Z","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":"29fad2caccc8b81f78571d10c30c249366ce44c579169516f402eaa5fd7089b7","cross_cats_sorted":["cs.CL","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-06T11:04:08Z","title_canon_sha256":"519b23fdccbce00499d428298831a5e010ed38a923b1db136dbbd51ea5958107"},"schema_version":"1.0","source":{"id":"1912.03063","kind":"arxiv","version":1}},"canonical_sha256":"988bb03d831ebc9fbdb0cbb38cdf683479d75a3734304ecef76fdad44a929d3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"988bb03d831ebc9fbdb0cbb38cdf683479d75a3734304ecef76fdad44a929d3a","first_computed_at":"2026-07-05T00:24:30.149608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:24:30.149608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Scr9U0+7o7+fjO/0FFCAKNXvbBs7HHkD7rrZBRhUzL0a3mAsMrJBv7BWyPIJnosS+2dXgVijNNLVr+F7WvjBw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:24:30.150028Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.03063","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2e92c7ba48f2f3edb1268cf7c78de23b30e28dd50d358d13bca9b8d4fd3c106","sha256:948664d1796c4f24a701a28547e8c0894e87909e5a9ceac593896778f04cbb12"],"state_sha256":"e22223b62eb1c0ebc1fffff11b969f405837408d24a57121082ed75f8b6919ac"}