{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:R4XVOMP4UPPCBCAC4VPWAFJPX7","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":"2898d4f60b41683a6bd9f89fd4d17e0e3383c4d19d31d80df266f132e693ad34","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-14T07:52:36Z","title_canon_sha256":"e2954e9a57faa775a6228f984836284cc9a0899196a08ae9880babdff68751f7"},"schema_version":"1.0","source":{"id":"2212.07075","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.07075","created_at":"2026-07-05T05:25:21Z"},{"alias_kind":"arxiv_version","alias_value":"2212.07075v1","created_at":"2026-07-05T05:25:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07075","created_at":"2026-07-05T05:25:21Z"},{"alias_kind":"pith_short_12","alias_value":"R4XVOMP4UPPC","created_at":"2026-07-05T05:25:21Z"},{"alias_kind":"pith_short_16","alias_value":"R4XVOMP4UPPCBCAC","created_at":"2026-07-05T05:25:21Z"},{"alias_kind":"pith_short_8","alias_value":"R4XVOMP4","created_at":"2026-07-05T05:25:21Z"}],"graph_snapshots":[{"event_id":"sha256:4e61b6a613a2cfcdb786737a931ea1fdd71d6002e3a7ad374cfeb7c7c53cfa23","target":"graph","created_at":"2026-07-05T05:25:21Z","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/2212.07075/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning models require the high-level generalization ability to describe the contents of various images in words. Most existing approaches treat the image-caption pairs equally in their training without considering the differences in their learning difficulties. Several image captioning approaches introduce curriculum learning methods that present training data with increasing levels of difficulty. However, their difficulty measurements are either based on domain-specific features or prior model training. In this paper, we propose a simple yet efficient difficulty measurement for imag","authors_text":"Akiko Aizawa, Hongkuan Zhang, Koichi Takeda, Lei Zhou, Ryohei Sasano, Saku Sugawara","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-14T07:52:36Z","title":"Cross-Modal Similarity-Based Curriculum Learning for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07075","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":"sha256:9e2d9dcfd2323ddb481cb30021e7fea6c37bc91aeb0514a4c9539d3d43148201","target":"record","created_at":"2026-07-05T05:25:21Z","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":"2898d4f60b41683a6bd9f89fd4d17e0e3383c4d19d31d80df266f132e693ad34","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-14T07:52:36Z","title_canon_sha256":"e2954e9a57faa775a6228f984836284cc9a0899196a08ae9880babdff68751f7"},"schema_version":"1.0","source":{"id":"2212.07075","kind":"arxiv","version":1}},"canonical_sha256":"8f2f5731fca3de208802e55f60152fbfd6e0162ab9003f17c776be95d504f70c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f2f5731fca3de208802e55f60152fbfd6e0162ab9003f17c776be95d504f70c","first_computed_at":"2026-07-05T05:25:21.113548Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:25:21.113548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nyhzjrrh5RVTVmPEY9JaX9rEYO+CBWQ5Ii+l2tuznibQgCwtD1viAa5qKvejRuLmLsgSP0v4hMxdmsSk1HtnBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:25:21.113916Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.07075","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e2d9dcfd2323ddb481cb30021e7fea6c37bc91aeb0514a4c9539d3d43148201","sha256:4e61b6a613a2cfcdb786737a931ea1fdd71d6002e3a7ad374cfeb7c7c53cfa23"],"state_sha256":"12807f9d38504d1f87edd2a95b069ee92618f51e2c730e062b5f152faeec8a64"}