{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MVQDRVDEROC4K6HTIKN4ZBMSUS","short_pith_number":"pith:MVQDRVDE","schema_version":"1.0","canonical_sha256":"656038d4648b85c578f3429bcc8592a4aca4d2e74f492bb689729a227142e508","source":{"kind":"arxiv","id":"1805.00314","version":1},"attestation_state":"computed","paper":{"title":"Object Counts! Bringing Explicit Detections Back into Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Josiah Wang, Lucia Specia, Pranava Madhyastha","submitted_at":"2018-04-23T14:51:46Z","abstract_excerpt":"The use of explicit object detectors as an intermediate step to image captioning - which used to constitute an essential stage in early work - is often bypassed in the currently dominant end-to-end approaches, where the language model is conditioned directly on a mid-level image embedding. We argue that explicit detections provide rich semantic information, and can thus be used as an interpretable representation to better understand why end-to-end image captioning systems work well. We provide an in-depth analysis of end-to-end image captioning by exploring a variety of cues that can be derive"},"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":"1805.00314","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-23T14:51:46Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0eea5f6d746cf54d309521cf911b67f5a64b3549e0e4a9433ace379cecceaad6","abstract_canon_sha256":"d83df872d12e6bb2ce624f1d6fd14a236c0ea8f4cf6dae5e833d035f12e73ee3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:09.952175Z","signature_b64":"KSjhZ6LlvNYASt0YxqEc0jo1IN0qRj6svkFIr6sZle9wGxvDKcMx7hlITGe/9eVnfmwc9JjUQhNNtLdEohqfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"656038d4648b85c578f3429bcc8592a4aca4d2e74f492bb689729a227142e508","last_reissued_at":"2026-05-18T00:17:09.951395Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:09.951395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Object Counts! Bringing Explicit Detections Back into Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Josiah Wang, Lucia Specia, Pranava Madhyastha","submitted_at":"2018-04-23T14:51:46Z","abstract_excerpt":"The use of explicit object detectors as an intermediate step to image captioning - which used to constitute an essential stage in early work - is often bypassed in the currently dominant end-to-end approaches, where the language model is conditioned directly on a mid-level image embedding. We argue that explicit detections provide rich semantic information, and can thus be used as an interpretable representation to better understand why end-to-end image captioning systems work well. We provide an in-depth analysis of end-to-end image captioning by exploring a variety of cues that can be derive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.00314","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":""},"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":"1805.00314","created_at":"2026-05-18T00:17:09.951525+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.00314v1","created_at":"2026-05-18T00:17:09.951525+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.00314","created_at":"2026-05-18T00:17:09.951525+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVQDRVDEROC4","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVQDRVDEROC4K6HT","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVQDRVDE","created_at":"2026-05-18T12:32:40.477152+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/MVQDRVDEROC4K6HTIKN4ZBMSUS","json":"https://pith.science/pith/MVQDRVDEROC4K6HTIKN4ZBMSUS.json","graph_json":"https://pith.science/api/pith-number/MVQDRVDEROC4K6HTIKN4ZBMSUS/graph.json","events_json":"https://pith.science/api/pith-number/MVQDRVDEROC4K6HTIKN4ZBMSUS/events.json","paper":"https://pith.science/paper/MVQDRVDE"},"agent_actions":{"view_html":"https://pith.science/pith/MVQDRVDEROC4K6HTIKN4ZBMSUS","download_json":"https://pith.science/pith/MVQDRVDEROC4K6HTIKN4ZBMSUS.json","view_paper":"https://pith.science/paper/MVQDRVDE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.00314&json=true","fetch_graph":"https://pith.science/api/pith-number/MVQDRVDEROC4K6HTIKN4ZBMSUS/graph.json","fetch_events":"https://pith.science/api/pith-number/MVQDRVDEROC4K6HTIKN4ZBMSUS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVQDRVDEROC4K6HTIKN4ZBMSUS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVQDRVDEROC4K6HTIKN4ZBMSUS/action/storage_attestation","attest_author":"https://pith.science/pith/MVQDRVDEROC4K6HTIKN4ZBMSUS/action/author_attestation","sign_citation":"https://pith.science/pith/MVQDRVDEROC4K6HTIKN4ZBMSUS/action/citation_signature","submit_replication":"https://pith.science/pith/MVQDRVDEROC4K6HTIKN4ZBMSUS/action/replication_record"}},"created_at":"2026-05-18T00:17:09.951525+00:00","updated_at":"2026-05-18T00:17:09.951525+00:00"}