{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PEOPNZYOL2DWTRZC6RDXBQUDIS","short_pith_number":"pith:PEOPNZYO","schema_version":"1.0","canonical_sha256":"791cf6e70e5e8769c722f44770c28344a67580d062803bede526f2f4eaf2ca12","source":{"kind":"arxiv","id":"1810.09630","version":1},"attestation_state":"computed","paper":{"title":"A Neural Compositional Paradigm for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo Dai, Dahua Lin, Sanja Fidler","submitted_at":"2018-10-23T02:16:12Z","abstract_excerpt":"Mainstream captioning models often follow a sequential structure to generate captions, leading to issues such as introduction of irrelevant semantics, lack of diversity in the generated captions, and inadequate generalization performance. In this paper, we present an alternative paradigm for image captioning, which factorizes the captioning procedure into two stages: (1) extracting an explicit semantic representation from the given image; and (2) constructing the caption based on a recursive compositional procedure in a bottom-up manner. Compared to conventional ones, our paradigm better prese"},"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":"1810.09630","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-23T02:16:12Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"6c71d67e6794da3cb379260575ff42daab46d3c5d31f07e21b8c0550c7e80000","abstract_canon_sha256":"03ad3bdbee74fbd79f2fca40379e94402664623aadba82b0b3f065158608b1e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:37.054784Z","signature_b64":"uvqOELg4xFZHIUuVjP6UMvTAaAMjZqX/8m03fO7tVb5WgfClTuGvc/DAylyhYEXPcxN6UHaAWEYEIcTZuk2QBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"791cf6e70e5e8769c722f44770c28344a67580d062803bede526f2f4eaf2ca12","last_reissued_at":"2026-05-18T00:02:37.054263Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:37.054263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Neural Compositional Paradigm for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo Dai, Dahua Lin, Sanja Fidler","submitted_at":"2018-10-23T02:16:12Z","abstract_excerpt":"Mainstream captioning models often follow a sequential structure to generate captions, leading to issues such as introduction of irrelevant semantics, lack of diversity in the generated captions, and inadequate generalization performance. In this paper, we present an alternative paradigm for image captioning, which factorizes the captioning procedure into two stages: (1) extracting an explicit semantic representation from the given image; and (2) constructing the caption based on a recursive compositional procedure in a bottom-up manner. Compared to conventional ones, our paradigm better prese"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.09630","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":"1810.09630","created_at":"2026-05-18T00:02:37.054351+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.09630v1","created_at":"2026-05-18T00:02:37.054351+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.09630","created_at":"2026-05-18T00:02:37.054351+00:00"},{"alias_kind":"pith_short_12","alias_value":"PEOPNZYOL2DW","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"PEOPNZYOL2DWTRZC","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"PEOPNZYO","created_at":"2026-05-18T12:32:43.782077+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/PEOPNZYOL2DWTRZC6RDXBQUDIS","json":"https://pith.science/pith/PEOPNZYOL2DWTRZC6RDXBQUDIS.json","graph_json":"https://pith.science/api/pith-number/PEOPNZYOL2DWTRZC6RDXBQUDIS/graph.json","events_json":"https://pith.science/api/pith-number/PEOPNZYOL2DWTRZC6RDXBQUDIS/events.json","paper":"https://pith.science/paper/PEOPNZYO"},"agent_actions":{"view_html":"https://pith.science/pith/PEOPNZYOL2DWTRZC6RDXBQUDIS","download_json":"https://pith.science/pith/PEOPNZYOL2DWTRZC6RDXBQUDIS.json","view_paper":"https://pith.science/paper/PEOPNZYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.09630&json=true","fetch_graph":"https://pith.science/api/pith-number/PEOPNZYOL2DWTRZC6RDXBQUDIS/graph.json","fetch_events":"https://pith.science/api/pith-number/PEOPNZYOL2DWTRZC6RDXBQUDIS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PEOPNZYOL2DWTRZC6RDXBQUDIS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PEOPNZYOL2DWTRZC6RDXBQUDIS/action/storage_attestation","attest_author":"https://pith.science/pith/PEOPNZYOL2DWTRZC6RDXBQUDIS/action/author_attestation","sign_citation":"https://pith.science/pith/PEOPNZYOL2DWTRZC6RDXBQUDIS/action/citation_signature","submit_replication":"https://pith.science/pith/PEOPNZYOL2DWTRZC6RDXBQUDIS/action/replication_record"}},"created_at":"2026-05-18T00:02:37.054351+00:00","updated_at":"2026-05-18T00:02:37.054351+00:00"}