{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RJT4TC3MA2PVF2PGN6YMUWANUC","short_pith_number":"pith:RJT4TC3M","canonical_record":{"source":{"id":"2201.12723","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-30T04:44:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f11da584fb444209594baf2015f077056053731c42ff576d866e727908ea2200","abstract_canon_sha256":"27061bd5e6456472f4ccaa7e582e8a3efc3c3c7e47b5d89e6501146d1cfbcc67"},"schema_version":"1.0"},"canonical_sha256":"8a67c98b6c069f52e9e66fb0ca580da0bc913c587fb1b61444c198b69aab9fae","source":{"kind":"arxiv","id":"2201.12723","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.12723","created_at":"2026-07-05T04:14:41Z"},{"alias_kind":"arxiv_version","alias_value":"2201.12723v3","created_at":"2026-07-05T04:14:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.12723","created_at":"2026-07-05T04:14:41Z"},{"alias_kind":"pith_short_12","alias_value":"RJT4TC3MA2PV","created_at":"2026-07-05T04:14:41Z"},{"alias_kind":"pith_short_16","alias_value":"RJT4TC3MA2PVF2PG","created_at":"2026-07-05T04:14:41Z"},{"alias_kind":"pith_short_8","alias_value":"RJT4TC3M","created_at":"2026-07-05T04:14:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RJT4TC3MA2PVF2PGN6YMUWANUC","target":"record","payload":{"canonical_record":{"source":{"id":"2201.12723","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-30T04:44:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f11da584fb444209594baf2015f077056053731c42ff576d866e727908ea2200","abstract_canon_sha256":"27061bd5e6456472f4ccaa7e582e8a3efc3c3c7e47b5d89e6501146d1cfbcc67"},"schema_version":"1.0"},"canonical_sha256":"8a67c98b6c069f52e9e66fb0ca580da0bc913c587fb1b61444c198b69aab9fae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:41.630427Z","signature_b64":"Gh2CDELPjzox856pkyp7h0rPtT9iykuvWvwLWCc1ywOh+fMDxZ4Dv6EkuQZ7LIZTaj9074D5i66DzMQFCiBICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a67c98b6c069f52e9e66fb0ca580da0bc913c587fb1b61444c198b69aab9fae","last_reissued_at":"2026-07-05T04:14:41.629930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:41.629930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.12723","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:14:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ngbuqiVKZ0veTKb/504xdHFHVJHgxVf5SEAM7fCJps2o+bUJNKxKhVCUGBhfst3oxLo5KOjH7mbfXp10dw/BCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:09:07.168683Z"},"content_sha256":"070fc1c9493b5ac96aecf746e07b29a66b1cdf3f85ac0acbafc05e87f6e6d630","schema_version":"1.0","event_id":"sha256:070fc1c9493b5ac96aecf746e07b29a66b1cdf3f85ac0acbafc05e87f6e6d630"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RJT4TC3MA2PVF2PGN6YMUWANUC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Frustratingly Simple Approach for End-to-End Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jing Ma, Rongsheng Zhang, Yadong Xi, Ziyang Luo","submitted_at":"2022-01-30T04:44:54Z","abstract_excerpt":"Image Captioning is a fundamental task to join vision and language, concerning about cross-modal understanding and text generation. Recent years witness the emerging attention on image captioning. Most of existing works follow a traditional two-stage training paradigm. Before training the captioning models, an extra object detector is utilized to recognize the objects in the image at first. However, they require sizeable datasets with fine-grained object annotation for training the object detector, which is a daunting task. In addition, the errors of the object detectors are easy to propagate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.12723","kind":"arxiv","version":3},"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/2201.12723/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:14:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R1x9XYT9pYwA9Mdo53k2o9d1R/YnV4HbwlppLkgr1ivo/bMXxCbjUAx51SSXXrGBxtEJ62QKX4zE3/KYBBAuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:09:07.169045Z"},"content_sha256":"ee8d648feb37c2965ce72880d63bcb35bf13fa7dc222d20657314b82d3fe9a28","schema_version":"1.0","event_id":"sha256:ee8d648feb37c2965ce72880d63bcb35bf13fa7dc222d20657314b82d3fe9a28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RJT4TC3MA2PVF2PGN6YMUWANUC/bundle.json","state_url":"https://pith.science/pith/RJT4TC3MA2PVF2PGN6YMUWANUC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RJT4TC3MA2PVF2PGN6YMUWANUC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T08:09:07Z","links":{"resolver":"https://pith.science/pith/RJT4TC3MA2PVF2PGN6YMUWANUC","bundle":"https://pith.science/pith/RJT4TC3MA2PVF2PGN6YMUWANUC/bundle.json","state":"https://pith.science/pith/RJT4TC3MA2PVF2PGN6YMUWANUC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RJT4TC3MA2PVF2PGN6YMUWANUC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RJT4TC3MA2PVF2PGN6YMUWANUC","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":"27061bd5e6456472f4ccaa7e582e8a3efc3c3c7e47b5d89e6501146d1cfbcc67","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-30T04:44:54Z","title_canon_sha256":"f11da584fb444209594baf2015f077056053731c42ff576d866e727908ea2200"},"schema_version":"1.0","source":{"id":"2201.12723","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.12723","created_at":"2026-07-05T04:14:41Z"},{"alias_kind":"arxiv_version","alias_value":"2201.12723v3","created_at":"2026-07-05T04:14:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.12723","created_at":"2026-07-05T04:14:41Z"},{"alias_kind":"pith_short_12","alias_value":"RJT4TC3MA2PV","created_at":"2026-07-05T04:14:41Z"},{"alias_kind":"pith_short_16","alias_value":"RJT4TC3MA2PVF2PG","created_at":"2026-07-05T04:14:41Z"},{"alias_kind":"pith_short_8","alias_value":"RJT4TC3M","created_at":"2026-07-05T04:14:41Z"}],"graph_snapshots":[{"event_id":"sha256:ee8d648feb37c2965ce72880d63bcb35bf13fa7dc222d20657314b82d3fe9a28","target":"graph","created_at":"2026-07-05T04:14:41Z","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/2201.12723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image Captioning is a fundamental task to join vision and language, concerning about cross-modal understanding and text generation. Recent years witness the emerging attention on image captioning. Most of existing works follow a traditional two-stage training paradigm. Before training the captioning models, an extra object detector is utilized to recognize the objects in the image at first. However, they require sizeable datasets with fine-grained object annotation for training the object detector, which is a daunting task. In addition, the errors of the object detectors are easy to propagate ","authors_text":"Jing Ma, Rongsheng Zhang, Yadong Xi, Ziyang Luo","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-30T04:44:54Z","title":"A Frustratingly Simple Approach for End-to-End Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.12723","kind":"arxiv","version":3},"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":"sha256:070fc1c9493b5ac96aecf746e07b29a66b1cdf3f85ac0acbafc05e87f6e6d630","target":"record","created_at":"2026-07-05T04:14:41Z","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":"27061bd5e6456472f4ccaa7e582e8a3efc3c3c7e47b5d89e6501146d1cfbcc67","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-30T04:44:54Z","title_canon_sha256":"f11da584fb444209594baf2015f077056053731c42ff576d866e727908ea2200"},"schema_version":"1.0","source":{"id":"2201.12723","kind":"arxiv","version":3}},"canonical_sha256":"8a67c98b6c069f52e9e66fb0ca580da0bc913c587fb1b61444c198b69aab9fae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a67c98b6c069f52e9e66fb0ca580da0bc913c587fb1b61444c198b69aab9fae","first_computed_at":"2026-07-05T04:14:41.629930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:14:41.629930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gh2CDELPjzox856pkyp7h0rPtT9iykuvWvwLWCc1ywOh+fMDxZ4Dv6EkuQZ7LIZTaj9074D5i66DzMQFCiBICA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:14:41.630427Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.12723","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:070fc1c9493b5ac96aecf746e07b29a66b1cdf3f85ac0acbafc05e87f6e6d630","sha256:ee8d648feb37c2965ce72880d63bcb35bf13fa7dc222d20657314b82d3fe9a28"],"state_sha256":"56e6dc8211c5552f44c36a7ce67604f38a3b8f1b4f68e7b684cd9fc320630204"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MVXY5QlpxFEPCk47myM4qvhot0FeY9KH6UBXXcLaJIf2Y83HYrfhaeCMseHwo9w6pnFMRN3U5M8TRM/Iwh4FAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:09:07.171062Z","bundle_sha256":"e9ad60916a81fd4c45eeeee1f60489f6674738f156f47a7f28c41729cfcf852d"}}