{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:AOVQY24TNAYUHFXLUCO2BWSEGC","short_pith_number":"pith:AOVQY24T","canonical_record":{"source":{"id":"2211.02321","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-04T08:50:09Z","cross_cats_sorted":[],"title_canon_sha256":"c67377008eb4d1a151de2da4585f37b47db7c80b50f123e9c54e40538c21598e","abstract_canon_sha256":"925d1d3f5d775f5ba987507516a5b8accc657c425ac1b82f9f05362efb69496c"},"schema_version":"1.0"},"canonical_sha256":"03ab0c6b9368314396eba09da0da4430906f42f93552ff50995be8e5ad7adb18","source":{"kind":"arxiv","id":"2211.02321","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.02321","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"arxiv_version","alias_value":"2211.02321v1","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02321","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"pith_short_12","alias_value":"AOVQY24TNAYU","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"pith_short_16","alias_value":"AOVQY24TNAYUHFXL","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"pith_short_8","alias_value":"AOVQY24T","created_at":"2026-07-05T05:13:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:AOVQY24TNAYUHFXLUCO2BWSEGC","target":"record","payload":{"canonical_record":{"source":{"id":"2211.02321","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-04T08:50:09Z","cross_cats_sorted":[],"title_canon_sha256":"c67377008eb4d1a151de2da4585f37b47db7c80b50f123e9c54e40538c21598e","abstract_canon_sha256":"925d1d3f5d775f5ba987507516a5b8accc657c425ac1b82f9f05362efb69496c"},"schema_version":"1.0"},"canonical_sha256":"03ab0c6b9368314396eba09da0da4430906f42f93552ff50995be8e5ad7adb18","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:14.136589Z","signature_b64":"v+cNLFpyDyIR+7+aGvidewkz8YzZFY6/W5vhf+p2Bx5SG2J/qPhm/sMwCe+7Cf6T9LMN11PGCUf0IcZvHW17Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03ab0c6b9368314396eba09da0da4430906f42f93552ff50995be8e5ad7adb18","last_reissued_at":"2026-07-05T05:13:14.136026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:14.136026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.02321","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:13:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nyi0FQXoujCp2yyy1fobQy2XwCuarCiy34iEXNzXm7Z2QNQaTgHbLEjW7zT2X+fxCRqFfIwyq4fl61jlBmTDCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:15:11.442829Z"},"content_sha256":"1b011edc78c83220a06df72e5ef440706576716b8de1117616f3c2eafa6314b9","schema_version":"1.0","event_id":"sha256:1b011edc78c83220a06df72e5ef440706576716b8de1117616f3c2eafa6314b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:AOVQY24TNAYUHFXLUCO2BWSEGC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OSIC: A New One-Stage Image Captioner Coined","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Wang, Meng Wang, Mingbo Zhao, Mingliang Xu, Xiaojie Jin, Zhao Zhang","submitted_at":"2022-11-04T08:50:09Z","abstract_excerpt":"Mainstream image caption models are usually two-stage captioners, i.e., calculating object features by pre-trained detector, and feeding them into a language model to generate text descriptions. However, such an operation will cause a task-based information gap to decrease the performance, since the object features in detection task are suboptimal representation and cannot provide all necessary information for subsequent text generation. Besides, object features are usually represented by the last layer features that lose the local details of input images. In this paper, we propose a novel One"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02321","kind":"arxiv","version":1},"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/2211.02321/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":"2026-07-05T05:13:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"morTIRT1jUoOd53FPPMnvJ8RqYpWs/Z9wlxfEMMLCn4hQJED4x1Irg7IbCnXyHuQpp60G7ouIR+d6uqOQF6lBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:15:11.443242Z"},"content_sha256":"c7c49fe2194768c808d5446626652930fc5a549b19c88eadd183c1d90349ea6b","schema_version":"1.0","event_id":"sha256:c7c49fe2194768c808d5446626652930fc5a549b19c88eadd183c1d90349ea6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AOVQY24TNAYUHFXLUCO2BWSEGC/bundle.json","state_url":"https://pith.science/pith/AOVQY24TNAYUHFXLUCO2BWSEGC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AOVQY24TNAYUHFXLUCO2BWSEGC/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":"2026-08-05T23:15:11Z","links":{"resolver":"https://pith.science/pith/AOVQY24TNAYUHFXLUCO2BWSEGC","bundle":"https://pith.science/pith/AOVQY24TNAYUHFXLUCO2BWSEGC/bundle.json","state":"https://pith.science/pith/AOVQY24TNAYUHFXLUCO2BWSEGC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AOVQY24TNAYUHFXLUCO2BWSEGC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:AOVQY24TNAYUHFXLUCO2BWSEGC","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":"925d1d3f5d775f5ba987507516a5b8accc657c425ac1b82f9f05362efb69496c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-04T08:50:09Z","title_canon_sha256":"c67377008eb4d1a151de2da4585f37b47db7c80b50f123e9c54e40538c21598e"},"schema_version":"1.0","source":{"id":"2211.02321","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.02321","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"arxiv_version","alias_value":"2211.02321v1","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02321","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"pith_short_12","alias_value":"AOVQY24TNAYU","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"pith_short_16","alias_value":"AOVQY24TNAYUHFXL","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"pith_short_8","alias_value":"AOVQY24T","created_at":"2026-07-05T05:13:14Z"}],"graph_snapshots":[{"event_id":"sha256:c7c49fe2194768c808d5446626652930fc5a549b19c88eadd183c1d90349ea6b","target":"graph","created_at":"2026-07-05T05:13:14Z","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/2211.02321/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mainstream image caption models are usually two-stage captioners, i.e., calculating object features by pre-trained detector, and feeding them into a language model to generate text descriptions. However, such an operation will cause a task-based information gap to decrease the performance, since the object features in detection task are suboptimal representation and cannot provide all necessary information for subsequent text generation. Besides, object features are usually represented by the last layer features that lose the local details of input images. In this paper, we propose a novel One","authors_text":"Bo Wang, Meng Wang, Mingbo Zhao, Mingliang Xu, Xiaojie Jin, Zhao Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-04T08:50:09Z","title":"OSIC: A New One-Stage Image Captioner Coined"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02321","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":"sha256:1b011edc78c83220a06df72e5ef440706576716b8de1117616f3c2eafa6314b9","target":"record","created_at":"2026-07-05T05:13:14Z","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":"925d1d3f5d775f5ba987507516a5b8accc657c425ac1b82f9f05362efb69496c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-04T08:50:09Z","title_canon_sha256":"c67377008eb4d1a151de2da4585f37b47db7c80b50f123e9c54e40538c21598e"},"schema_version":"1.0","source":{"id":"2211.02321","kind":"arxiv","version":1}},"canonical_sha256":"03ab0c6b9368314396eba09da0da4430906f42f93552ff50995be8e5ad7adb18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03ab0c6b9368314396eba09da0da4430906f42f93552ff50995be8e5ad7adb18","first_computed_at":"2026-07-05T05:13:14.136026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:13:14.136026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v+cNLFpyDyIR+7+aGvidewkz8YzZFY6/W5vhf+p2Bx5SG2J/qPhm/sMwCe+7Cf6T9LMN11PGCUf0IcZvHW17Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:13:14.136589Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.02321","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b011edc78c83220a06df72e5ef440706576716b8de1117616f3c2eafa6314b9","sha256:c7c49fe2194768c808d5446626652930fc5a549b19c88eadd183c1d90349ea6b"],"state_sha256":"e80355602f6e2f58f7bd94c1efe5349f63f41fb952a8058f7bcb7fd29ecee46d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SPvdzP7vNQhDi69kdOI14Mw4F/2neZgDKsZ1h0Md8eLeILlGHEkwundW1VS5jkmHKTmTiyOdTp6tTUIsbNWBDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:15:11.446052Z","bundle_sha256":"763c5fbf8c2a6ed0f33b2bf66d7ec82d7eda183dea310e59c20bc82d3aa40e8c"}}