{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4QDOXFWSILBJRLCVIGOPOFUNYB","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":"836c2fc484e2da195220294f346cf70348e0056ca73c810c0d62f950b9e10609","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-24T13:33:23Z","title_canon_sha256":"f8f88110d3ab1a05aad5d558168fd0aa57800547248ee4fffc9d84b82836a421"},"schema_version":"1.0","source":{"id":"2110.12442","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.12442","created_at":"2026-07-05T03:25:20Z"},{"alias_kind":"arxiv_version","alias_value":"2110.12442v1","created_at":"2026-07-05T03:25:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12442","created_at":"2026-07-05T03:25:20Z"},{"alias_kind":"pith_short_12","alias_value":"4QDOXFWSILBJ","created_at":"2026-07-05T03:25:20Z"},{"alias_kind":"pith_short_16","alias_value":"4QDOXFWSILBJRLCV","created_at":"2026-07-05T03:25:20Z"},{"alias_kind":"pith_short_8","alias_value":"4QDOXFWS","created_at":"2026-07-05T03:25:20Z"}],"graph_snapshots":[{"event_id":"sha256:4a81ebb5d1f59dd1c0a2ba2fa18fa1f576a264a9f809aeb77e687c15d143ccb5","target":"graph","created_at":"2026-07-05T03:25:20Z","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/2110.12442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic Image Captioning is the never-ending effort of creating syntactically and validating the accuracy of textual descriptions of an image in natural language with context. The encoder-decoder structure used throughout existing Bengali Image Captioning (BIC) research utilized abstract image feature vectors as the encoder's input. We propose a novel transformer-based architecture with an attention mechanism with a pre-trained ResNet-101 model image encoder for feature extraction from images. Experiments demonstrate that the language decoder in our technique captures fine-grained informatio","authors_text":"Faria Afrin, Md Abdullah Al Nasim, Md Aminul Haque Palash, Raisa Mallik, Sathishkumar Samiappan, Sourav Saha","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-24T13:33:23Z","title":"Bangla Image Caption Generation through CNN-Transformer based Encoder-Decoder Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12442","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:e9bc2dc2d77114881db7d120680307be78a66ce2eb5e2dae4b43331c3cd89d50","target":"record","created_at":"2026-07-05T03:25:20Z","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":"836c2fc484e2da195220294f346cf70348e0056ca73c810c0d62f950b9e10609","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-24T13:33:23Z","title_canon_sha256":"f8f88110d3ab1a05aad5d558168fd0aa57800547248ee4fffc9d84b82836a421"},"schema_version":"1.0","source":{"id":"2110.12442","kind":"arxiv","version":1}},"canonical_sha256":"e406eb96d242c298ac55419cf7168dc04ebae4ede964b061704456ab3944593d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e406eb96d242c298ac55419cf7168dc04ebae4ede964b061704456ab3944593d","first_computed_at":"2026-07-05T03:25:20.433446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:25:20.433446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CofI5QG4fPS45jDSCqhdLGpj3GZcVyP8zPa8OT+qq/Gy/HPc5zPLAe+yXCgg98rpvqEUbXzxiaEPfcmOE2rMBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:25:20.433772Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.12442","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9bc2dc2d77114881db7d120680307be78a66ce2eb5e2dae4b43331c3cd89d50","sha256:4a81ebb5d1f59dd1c0a2ba2fa18fa1f576a264a9f809aeb77e687c15d143ccb5"],"state_sha256":"164d80c933074d79aaec117da21addf80900e43da36382fd8daf9553ffbfbb8f"}