{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:QYJQVUJH5RRUTW5WUFFDRDUACU","short_pith_number":"pith:QYJQVUJH","canonical_record":{"source":{"id":"1504.00325","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-01T18:13:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"27e9451a05a8d9e1914fb4e4b184987319406c9265ef9626528b6e4842849697","abstract_canon_sha256":"5c051bb131ac18e4db82c1274bf842a997952239bd84feba788a830c2a0365c5"},"schema_version":"1.0"},"canonical_sha256":"86130ad127ec6349dbb6a14a388e8015080841bdd9bf676990a7cfa1ae2d2c2c","source":{"kind":"arxiv","id":"1504.00325","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1504.00325","created_at":"2026-07-04T19:27:40Z"},{"alias_kind":"arxiv_version","alias_value":"1504.00325v2","created_at":"2026-07-04T19:27:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.00325","created_at":"2026-07-04T19:27:40Z"},{"alias_kind":"pith_short_12","alias_value":"QYJQVUJH5RRU","created_at":"2026-07-04T19:27:40Z"},{"alias_kind":"pith_short_16","alias_value":"QYJQVUJH5RRUTW5W","created_at":"2026-07-04T19:27:40Z"},{"alias_kind":"pith_short_8","alias_value":"QYJQVUJH","created_at":"2026-07-04T19:27:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:QYJQVUJH5RRUTW5WUFFDRDUACU","target":"record","payload":{"canonical_record":{"source":{"id":"1504.00325","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-01T18:13:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"27e9451a05a8d9e1914fb4e4b184987319406c9265ef9626528b6e4842849697","abstract_canon_sha256":"5c051bb131ac18e4db82c1274bf842a997952239bd84feba788a830c2a0365c5"},"schema_version":"1.0"},"canonical_sha256":"86130ad127ec6349dbb6a14a388e8015080841bdd9bf676990a7cfa1ae2d2c2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T19:27:40.956599Z","signature_b64":"MSVk3mPbdpKTGRHlzJ+rxciZGW6WJxZJFwRgQARAVl99SbMGS5bfbpkD+8bG75ketjkMP1aZbFYGnrjnRY4MDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86130ad127ec6349dbb6a14a388e8015080841bdd9bf676990a7cfa1ae2d2c2c","last_reissued_at":"2026-07-04T19:27:40.956092Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T19:27:40.956092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1504.00325","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T19:27:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9h/qOLVDWIe7s7Nkx5WPwZXEsjPjuPve2TKkFBuffZJglZbiCa1I9XTeQ9T9FFk7uxPZ0aidXfGjNurX1TlYBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:06:46.622192Z"},"content_sha256":"e0c1d52c92562b65854b2364c8aa798a0f664380911717560397bff8913da11c","schema_version":"1.0","event_id":"sha256:e0c1d52c92562b65854b2364c8aa798a0f664380911717560397bff8913da11c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:QYJQVUJH5RRUTW5WUFFDRDUACU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Microsoft COCO Captions: Data Collection and Evaluation Server","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Microsoft COCO Caption dataset collects over 1.5 million human captions for more than 330,000 images and supplies an evaluation server using standard metrics.","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"C. Lawrence Zitnick, Hao Fang, Piotr Dollar, Ramakrishna Vedantam, Saurabh Gupta, Tsung-Yi Lin, Xinlei Chen","submitted_at":"2015-04-01T18:13:43Z","abstract_excerpt":"In this paper we describe the Microsoft COCO Caption dataset and evaluation server. When completed, the dataset will contain over one and a half million captions describing over 330,000 images. For the training and validation images, five independent human generated captions will be provided. To ensure consistency in evaluation of automatic caption generation algorithms, an evaluation server is used. The evaluation server receives candidate captions and scores them using several popular metrics, including BLEU, METEOR, ROUGE and CIDEr. Instructions for using the evaluation server are provided."},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"When completed, the dataset will contain over one and a half million captions describing over 330,000 images. For the training and validation images, five independent human generated captions will be provided.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The collected human captions are sufficiently consistent, high-quality, and representative to serve as reliable ground truth for automatic systems.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Microsoft COCO Captions provides 1.5 million human captions across 330,000 images and a public server to evaluate captioning models with BLEU, METEOR, ROUGE, and CIDEr.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Microsoft COCO Caption dataset collects over 1.5 million human captions for more than 330,000 images and supplies an evaluation server using standard metrics.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"826efb0dd2ec9457e594c4ab7500fe81b91988f9bd80bc4fece064be7ed13dba"},"source":{"id":"1504.00325","kind":"arxiv","version":2},"verdict":{"id":"883e5980-1b50-4150-9aa0-c218a141968b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T21:32:41.651000Z","strongest_claim":"When completed, the dataset will contain over one and a half million captions describing over 330,000 images. For the training and validation images, five independent human generated captions will be provided.","one_line_summary":"Microsoft COCO Captions provides 1.5 million human captions across 330,000 images and a public server to evaluate captioning models with BLEU, METEOR, ROUGE, and CIDEr.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The collected human captions are sufficiently consistent, high-quality, and representative to serve as reliable ground truth for automatic systems.","pith_extraction_headline":"Microsoft COCO Caption dataset collects over 1.5 million human captions for more than 330,000 images and supplies an evaluation server using standard metrics."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1504.00325/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":46,"sample":[{"doi":"","year":2001,"title":"Learning the semantics of words and pictures","work_id":"3d416005-6a1b-49d5-8f37-b63f1c63620e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2003,"title":"Matching words and pictures","work_id":"8c3cdf6a-7603-4345-87e8-53ab047bcdfd","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2003,"title":"A model for learning the semantics of pictures","work_id":"cba48426-6ab4-41b6-a631-bc85c357bb8c","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2011,"title":"Baby talk: Understanding and generating simple image descriptions","work_id":"2e7ce5fc-9fa8-494f-8a33-0667124a90f1","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2012,"title":"Midge: Generating image descriptions from computer vision detections","work_id":"0514fdca-124c-4da4-bd00-fc17d4f2d3b4","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":46,"snapshot_sha256":"3e2264debdc0f04a5840870ddf58c8d62a0c3e09bd10576102b7991f0a429154","internal_anchors":2},"formal_canon":{"evidence_count":3,"snapshot_sha256":"ab4bb1e5b840010db755f491924ef30e27289a5b83b09e13b3ae7d79f9e43788"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"883e5980-1b50-4150-9aa0-c218a141968b"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T19:27:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YwArtqeF71PVgsgnjXoDN/x/3oY/+zDbME7Ew5KQWYSDp+Tl7tHsVZ4FDoHzmCflTHPw2YnMPoBjbBTcXY6zDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:06:46.623008Z"},"content_sha256":"8bd9b42c13fab0275b540a3415b6bd95a6fca1adc4e459f28dcb2d11c69c64f2","schema_version":"1.0","event_id":"sha256:8bd9b42c13fab0275b540a3415b6bd95a6fca1adc4e459f28dcb2d11c69c64f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QYJQVUJH5RRUTW5WUFFDRDUACU/bundle.json","state_url":"https://pith.science/pith/QYJQVUJH5RRUTW5WUFFDRDUACU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QYJQVUJH5RRUTW5WUFFDRDUACU/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":"2026-08-06T09:06:46Z","links":{"resolver":"https://pith.science/pith/QYJQVUJH5RRUTW5WUFFDRDUACU","bundle":"https://pith.science/pith/QYJQVUJH5RRUTW5WUFFDRDUACU/bundle.json","state":"https://pith.science/pith/QYJQVUJH5RRUTW5WUFFDRDUACU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QYJQVUJH5RRUTW5WUFFDRDUACU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:QYJQVUJH5RRUTW5WUFFDRDUACU","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":"5c051bb131ac18e4db82c1274bf842a997952239bd84feba788a830c2a0365c5","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-01T18:13:43Z","title_canon_sha256":"27e9451a05a8d9e1914fb4e4b184987319406c9265ef9626528b6e4842849697"},"schema_version":"1.0","source":{"id":"1504.00325","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1504.00325","created_at":"2026-07-04T19:27:40Z"},{"alias_kind":"arxiv_version","alias_value":"1504.00325v2","created_at":"2026-07-04T19:27:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.00325","created_at":"2026-07-04T19:27:40Z"},{"alias_kind":"pith_short_12","alias_value":"QYJQVUJH5RRU","created_at":"2026-07-04T19:27:40Z"},{"alias_kind":"pith_short_16","alias_value":"QYJQVUJH5RRUTW5W","created_at":"2026-07-04T19:27:40Z"},{"alias_kind":"pith_short_8","alias_value":"QYJQVUJH","created_at":"2026-07-04T19:27:40Z"}],"graph_snapshots":[{"event_id":"sha256:8bd9b42c13fab0275b540a3415b6bd95a6fca1adc4e459f28dcb2d11c69c64f2","target":"graph","created_at":"2026-07-04T19:27:40Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"When completed, the dataset will contain over one and a half million captions describing over 330,000 images. For the training and validation images, five independent human generated captions will be provided."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The collected human captions are sufficiently consistent, high-quality, and representative to serve as reliable ground truth for automatic systems."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Microsoft COCO Captions provides 1.5 million human captions across 330,000 images and a public server to evaluate captioning models with BLEU, METEOR, ROUGE, and CIDEr."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Microsoft COCO Caption dataset collects over 1.5 million human captions for more than 330,000 images and supplies an evaluation server using standard metrics."}],"snapshot_sha256":"826efb0dd2ec9457e594c4ab7500fe81b91988f9bd80bc4fece064be7ed13dba"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"ab4bb1e5b840010db755f491924ef30e27289a5b83b09e13b3ae7d79f9e43788"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1504.00325/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper we describe the Microsoft COCO Caption dataset and evaluation server. When completed, the dataset will contain over one and a half million captions describing over 330,000 images. For the training and validation images, five independent human generated captions will be provided. To ensure consistency in evaluation of automatic caption generation algorithms, an evaluation server is used. The evaluation server receives candidate captions and scores them using several popular metrics, including BLEU, METEOR, ROUGE and CIDEr. Instructions for using the evaluation server are provided.","authors_text":"C. Lawrence Zitnick, Hao Fang, Piotr Dollar, Ramakrishna Vedantam, Saurabh Gupta, Tsung-Yi Lin, Xinlei Chen","cross_cats":["cs.CL"],"headline":"Microsoft COCO Caption dataset collects over 1.5 million human captions for more than 330,000 images and supplies an evaluation server using standard metrics.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-01T18:13:43Z","title":"Microsoft COCO Captions: Data Collection and Evaluation Server"},"references":{"count":46,"internal_anchors":2,"resolved_work":46,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Learning the semantics of words and pictures","work_id":"3d416005-6a1b-49d5-8f37-b63f1c63620e","year":2001},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Matching words and pictures","work_id":"8c3cdf6a-7603-4345-87e8-53ab047bcdfd","year":2003},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"A model for learning the semantics of pictures","work_id":"cba48426-6ab4-41b6-a631-bc85c357bb8c","year":2003},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Baby talk: Understanding and generating simple image descriptions","work_id":"2e7ce5fc-9fa8-494f-8a33-0667124a90f1","year":2011},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Midge: Generating image descriptions from computer vision detections","work_id":"0514fdca-124c-4da4-bd00-fc17d4f2d3b4","year":2012}],"snapshot_sha256":"3e2264debdc0f04a5840870ddf58c8d62a0c3e09bd10576102b7991f0a429154"},"source":{"id":"1504.00325","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T21:32:41.651000Z","id":"883e5980-1b50-4150-9aa0-c218a141968b","model_set":{"reader":"grok-4.3"},"one_line_summary":"Microsoft COCO Captions provides 1.5 million human captions across 330,000 images and a public server to evaluate captioning models with BLEU, METEOR, ROUGE, and CIDEr.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Microsoft COCO Caption dataset collects over 1.5 million human captions for more than 330,000 images and supplies an evaluation server using standard metrics.","strongest_claim":"When completed, the dataset will contain over one and a half million captions describing over 330,000 images. For the training and validation images, five independent human generated captions will be provided.","weakest_assumption":"The collected human captions are sufficiently consistent, high-quality, and representative to serve as reliable ground truth for automatic systems."}},"verdict_id":"883e5980-1b50-4150-9aa0-c218a141968b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e0c1d52c92562b65854b2364c8aa798a0f664380911717560397bff8913da11c","target":"record","created_at":"2026-07-04T19:27:40Z","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":"5c051bb131ac18e4db82c1274bf842a997952239bd84feba788a830c2a0365c5","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-01T18:13:43Z","title_canon_sha256":"27e9451a05a8d9e1914fb4e4b184987319406c9265ef9626528b6e4842849697"},"schema_version":"1.0","source":{"id":"1504.00325","kind":"arxiv","version":2}},"canonical_sha256":"86130ad127ec6349dbb6a14a388e8015080841bdd9bf676990a7cfa1ae2d2c2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86130ad127ec6349dbb6a14a388e8015080841bdd9bf676990a7cfa1ae2d2c2c","first_computed_at":"2026-07-04T19:27:40.956092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T19:27:40.956092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MSVk3mPbdpKTGRHlzJ+rxciZGW6WJxZJFwRgQARAVl99SbMGS5bfbpkD+8bG75ketjkMP1aZbFYGnrjnRY4MDQ==","signature_status":"signed_v1","signed_at":"2026-07-04T19:27:40.956599Z","signed_message":"canonical_sha256_bytes"},"source_id":"1504.00325","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0c1d52c92562b65854b2364c8aa798a0f664380911717560397bff8913da11c","sha256:8bd9b42c13fab0275b540a3415b6bd95a6fca1adc4e459f28dcb2d11c69c64f2"],"state_sha256":"8793086edfafc95f654d8815711a99a9df4b04839be43122e8ce0303e0eccc1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tUv4ILM+kd7152gCf+ccaTIc7/xVzUyWhMXBVfGp3273LCh34ipMmrvN3b4O9Vwtw2D+R5hfgF8sir0gYGlvCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:06:46.629428Z","bundle_sha256":"19bc1f6eefc16ebf17a9e6eccfd6333be5af656e40fd94fa1f642d76ecb5d02c"}}