{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:2NNI5YMIDPPKH2BDWXFOVOTM72","short_pith_number":"pith:2NNI5YMI","schema_version":"1.0","canonical_sha256":"d35a8ee1881bdea3e823b5caeaba6cfeb3b623d53a9b1c2aabab7ef966099bef","source":{"kind":"arxiv","id":"1703.10476","version":2},"attestation_state":"computed","paper":{"title":"Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bernt Schiele, Lisa Anne Hendricks, Marcus Rohrbach, Mario Fritz, Rakshith Shetty","submitted_at":"2017-03-30T13:54:51Z","abstract_excerpt":"While strong progress has been made in image captioning over the last years, machine and human captions are still quite distinct. A closer look reveals that this is due to the deficiencies in the generated word distribution, vocabulary size, and strong bias in the generators towards frequent captions. Furthermore, humans -- rightfully so -- generate multiple, diverse captions, due to the inherent ambiguity in the captioning task which is not considered in today's systems.\n  To address these challenges, we change the training objective of the caption generator from reproducing groundtruth capti"},"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":"1703.10476","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-30T13:54:51Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"08fb8c72ce2f7942dbbfd3277e2aa9ab76934edcbc83b0d6c6336c0c0932ff8d","abstract_canon_sha256":"476291373d8c442d63cd65dee43f0b9934223abdbcf24adfd6b4905b6f3611c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:21.865704Z","signature_b64":"L+92KyF9gKnA5srYLAq+bLYqPBBelezxzjl55AuLfVCln9UE79BsqXbiCAbl9ewA7LWVm3aV+JgE2cGy/6wPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d35a8ee1881bdea3e823b5caeaba6cfeb3b623d53a9b1c2aabab7ef966099bef","last_reissued_at":"2026-05-18T00:31:21.864957Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:21.864957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bernt Schiele, Lisa Anne Hendricks, Marcus Rohrbach, Mario Fritz, Rakshith Shetty","submitted_at":"2017-03-30T13:54:51Z","abstract_excerpt":"While strong progress has been made in image captioning over the last years, machine and human captions are still quite distinct. A closer look reveals that this is due to the deficiencies in the generated word distribution, vocabulary size, and strong bias in the generators towards frequent captions. Furthermore, humans -- rightfully so -- generate multiple, diverse captions, due to the inherent ambiguity in the captioning task which is not considered in today's systems.\n  To address these challenges, we change the training objective of the caption generator from reproducing groundtruth capti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.10476","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":""},"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":"1703.10476","created_at":"2026-05-18T00:31:21.865073+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.10476v2","created_at":"2026-05-18T00:31:21.865073+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10476","created_at":"2026-05-18T00:31:21.865073+00:00"},{"alias_kind":"pith_short_12","alias_value":"2NNI5YMIDPPK","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"2NNI5YMIDPPKH2BD","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"2NNI5YMI","created_at":"2026-05-18T12:30:55.937587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2NNI5YMIDPPKH2BDWXFOVOTM72","json":"https://pith.science/pith/2NNI5YMIDPPKH2BDWXFOVOTM72.json","graph_json":"https://pith.science/api/pith-number/2NNI5YMIDPPKH2BDWXFOVOTM72/graph.json","events_json":"https://pith.science/api/pith-number/2NNI5YMIDPPKH2BDWXFOVOTM72/events.json","paper":"https://pith.science/paper/2NNI5YMI"},"agent_actions":{"view_html":"https://pith.science/pith/2NNI5YMIDPPKH2BDWXFOVOTM72","download_json":"https://pith.science/pith/2NNI5YMIDPPKH2BDWXFOVOTM72.json","view_paper":"https://pith.science/paper/2NNI5YMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.10476&json=true","fetch_graph":"https://pith.science/api/pith-number/2NNI5YMIDPPKH2BDWXFOVOTM72/graph.json","fetch_events":"https://pith.science/api/pith-number/2NNI5YMIDPPKH2BDWXFOVOTM72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2NNI5YMIDPPKH2BDWXFOVOTM72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2NNI5YMIDPPKH2BDWXFOVOTM72/action/storage_attestation","attest_author":"https://pith.science/pith/2NNI5YMIDPPKH2BDWXFOVOTM72/action/author_attestation","sign_citation":"https://pith.science/pith/2NNI5YMIDPPKH2BDWXFOVOTM72/action/citation_signature","submit_replication":"https://pith.science/pith/2NNI5YMIDPPKH2BDWXFOVOTM72/action/replication_record"}},"created_at":"2026-05-18T00:31:21.865073+00:00","updated_at":"2026-05-18T00:31:21.865073+00:00"}