{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QJ6LRFOXAG6QHQLB34BANZTHUQ","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":"059456e82aa9ca399bf5f5aca4af13e4f8fd4d68a05ada875c3f82dfa3627abe","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-17T19:03:23Z","title_canon_sha256":"5f658ddc469c3378b8dab1e5d264350ea18f4f216bc55ee1193488c2d1832b93"},"schema_version":"1.0","source":{"id":"1912.08226","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.08226","created_at":"2026-07-05T00:49:40Z"},{"alias_kind":"arxiv_version","alias_value":"1912.08226v2","created_at":"2026-07-05T00:49:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.08226","created_at":"2026-07-05T00:49:40Z"},{"alias_kind":"pith_short_12","alias_value":"QJ6LRFOXAG6Q","created_at":"2026-07-05T00:49:40Z"},{"alias_kind":"pith_short_16","alias_value":"QJ6LRFOXAG6QHQLB","created_at":"2026-07-05T00:49:40Z"},{"alias_kind":"pith_short_8","alias_value":"QJ6LRFOX","created_at":"2026-07-05T00:49:40Z"}],"graph_snapshots":[{"event_id":"sha256:9cb629ee36af2faa72e3bbde5e3d9c8846a0a42d2affa62a63d64f94479c8365","target":"graph","created_at":"2026-07-05T00:49:40Z","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/1912.08226/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer-based architectures represent the state of the art in sequence modeling tasks like machine translation and language understanding. Their applicability to multi-modal contexts like image captioning, however, is still largely under-explored. With the aim of filling this gap, we present M$^2$ - a Meshed Transformer with Memory for Image Captioning. The architecture improves both the image encoding and the language generation steps: it learns a multi-level representation of the relationships between image regions integrating learned a priori knowledge, and uses a mesh-like connectivity","authors_text":"Lorenzo Baraldi, Marcella Cornia, Matteo Stefanini, Rita Cucchiara","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-17T19:03:23Z","title":"Meshed-Memory Transformer for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.08226","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:d12bb8f66c6c0d2e33ffc46d57648a74feec0bd5cbf538df3337322fc35beef4","target":"record","created_at":"2026-07-05T00:49:40Z","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":"059456e82aa9ca399bf5f5aca4af13e4f8fd4d68a05ada875c3f82dfa3627abe","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-17T19:03:23Z","title_canon_sha256":"5f658ddc469c3378b8dab1e5d264350ea18f4f216bc55ee1193488c2d1832b93"},"schema_version":"1.0","source":{"id":"1912.08226","kind":"arxiv","version":2}},"canonical_sha256":"827cb895d701bd03c161df0206e667a428b2720a900a667f4e018b04558d6023","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"827cb895d701bd03c161df0206e667a428b2720a900a667f4e018b04558d6023","first_computed_at":"2026-07-05T00:49:40.582788Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:49:40.582788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fCjdtHnmsP+ZJT8uu/Dufr6+gtKJ5BnPY8o/oEOXRCcx2+xV5ySCQ41hdLRxBVFg2gDl0QeN8S/ugSsu8XauDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:49:40.583209Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.08226","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d12bb8f66c6c0d2e33ffc46d57648a74feec0bd5cbf538df3337322fc35beef4","sha256:9cb629ee36af2faa72e3bbde5e3d9c8846a0a42d2affa62a63d64f94479c8365"],"state_sha256":"a0a759aa78ef0c7b5337def6ac9afde556690f8958e2ea556ee095d7624bbd20"}