{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QJ6LRFOXAG6QHQLB34BANZTHUQ","short_pith_number":"pith:QJ6LRFOX","schema_version":"1.0","canonical_sha256":"827cb895d701bd03c161df0206e667a428b2720a900a667f4e018b04558d6023","source":{"kind":"arxiv","id":"1912.08226","version":2},"attestation_state":"computed","paper":{"title":"Meshed-Memory Transformer for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Lorenzo Baraldi, Marcella Cornia, Matteo Stefanini, Rita Cucchiara","submitted_at":"2019-12-17T19:03:23Z","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"},"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":"1912.08226","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-17T19:03:23Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5f658ddc469c3378b8dab1e5d264350ea18f4f216bc55ee1193488c2d1832b93","abstract_canon_sha256":"059456e82aa9ca399bf5f5aca4af13e4f8fd4d68a05ada875c3f82dfa3627abe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:49:40.583209Z","signature_b64":"fCjdtHnmsP+ZJT8uu/Dufr6+gtKJ5BnPY8o/oEOXRCcx2+xV5ySCQ41hdLRxBVFg2gDl0QeN8S/ugSsu8XauDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"827cb895d701bd03c161df0206e667a428b2720a900a667f4e018b04558d6023","last_reissued_at":"2026-07-05T00:49:40.582788Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:49:40.582788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meshed-Memory Transformer for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Lorenzo Baraldi, Marcella Cornia, Matteo Stefanini, Rita Cucchiara","submitted_at":"2019-12-17T19:03:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.08226","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.08226/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1912.08226","created_at":"2026-07-05T00:49:40.582849+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.08226v2","created_at":"2026-07-05T00:49:40.582849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.08226","created_at":"2026-07-05T00:49:40.582849+00:00"},{"alias_kind":"pith_short_12","alias_value":"QJ6LRFOXAG6Q","created_at":"2026-07-05T00:49:40.582849+00:00"},{"alias_kind":"pith_short_16","alias_value":"QJ6LRFOXAG6QHQLB","created_at":"2026-07-05T00:49:40.582849+00:00"},{"alias_kind":"pith_short_8","alias_value":"QJ6LRFOX","created_at":"2026-07-05T00:49:40.582849+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17430","citing_title":"CIAN: Multi-Stage Framework for Event-Enriched Image Captioning via Retrieval-Augmented Generation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2503.18297","citing_title":"Image-to-Text for Medical Reports Using Adaptive Co-Attention and Triple-LSTM Module","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QJ6LRFOXAG6QHQLB34BANZTHUQ","json":"https://pith.science/pith/QJ6LRFOXAG6QHQLB34BANZTHUQ.json","graph_json":"https://pith.science/api/pith-number/QJ6LRFOXAG6QHQLB34BANZTHUQ/graph.json","events_json":"https://pith.science/api/pith-number/QJ6LRFOXAG6QHQLB34BANZTHUQ/events.json","paper":"https://pith.science/paper/QJ6LRFOX"},"agent_actions":{"view_html":"https://pith.science/pith/QJ6LRFOXAG6QHQLB34BANZTHUQ","download_json":"https://pith.science/pith/QJ6LRFOXAG6QHQLB34BANZTHUQ.json","view_paper":"https://pith.science/paper/QJ6LRFOX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.08226&json=true","fetch_graph":"https://pith.science/api/pith-number/QJ6LRFOXAG6QHQLB34BANZTHUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QJ6LRFOXAG6QHQLB34BANZTHUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QJ6LRFOXAG6QHQLB34BANZTHUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QJ6LRFOXAG6QHQLB34BANZTHUQ/action/storage_attestation","attest_author":"https://pith.science/pith/QJ6LRFOXAG6QHQLB34BANZTHUQ/action/author_attestation","sign_citation":"https://pith.science/pith/QJ6LRFOXAG6QHQLB34BANZTHUQ/action/citation_signature","submit_replication":"https://pith.science/pith/QJ6LRFOXAG6QHQLB34BANZTHUQ/action/replication_record"}},"created_at":"2026-07-05T00:49:40.582849+00:00","updated_at":"2026-07-05T00:49:40.582849+00:00"}