{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:O4RJEF26TSDYFK3P5ZECDJ4OJS","short_pith_number":"pith:O4RJEF26","schema_version":"1.0","canonical_sha256":"772292175e9c8782ab6fee4821a78e4c967a847a9ccc56f1fe5a8769762424f9","source":{"kind":"arxiv","id":"1607.08822","version":1},"attestation_state":"computed","paper":{"title":"SPICE: Semantic Propositional Image Caption Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Basura Fernando, Mark Johnson, Peter Anderson, Stephen Gould","submitted_at":"2016-07-29T14:26:27Z","abstract_excerpt":"There is considerable interest in the task of automatically generating image captions. However, evaluation is challenging. Existing automatic evaluation metrics are primarily sensitive to n-gram overlap, which is neither necessary nor sufficient for the task of simulating human judgment. We hypothesize that semantic propositional content is an important component of human caption evaluation, and propose a new automated caption evaluation metric defined over scene graphs coined SPICE. Extensive evaluations across a range of models and datasets indicate that SPICE captures human judgments over m"},"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":"1607.08822","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-07-29T14:26:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"64e763a690d2245a817a3113a223dc1e0456d40c689473f0e7e3b1007704581b","abstract_canon_sha256":"0f6b7a1d5af4dc20a439927991b04d5426e5efc5ef099140bc37be752d9d7b05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:10:15.832598Z","signature_b64":"hQW+Bbsf2BWYkzWt6GqTWobMiv38pCIjW0eTvwlnKBC741tsTnebIVFksaxzTy80I9GGzjDQwB10i1875GBmDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"772292175e9c8782ab6fee4821a78e4c967a847a9ccc56f1fe5a8769762424f9","last_reissued_at":"2026-05-18T01:10:15.832096Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:10:15.832096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPICE: Semantic Propositional Image Caption Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Basura Fernando, Mark Johnson, Peter Anderson, Stephen Gould","submitted_at":"2016-07-29T14:26:27Z","abstract_excerpt":"There is considerable interest in the task of automatically generating image captions. However, evaluation is challenging. Existing automatic evaluation metrics are primarily sensitive to n-gram overlap, which is neither necessary nor sufficient for the task of simulating human judgment. We hypothesize that semantic propositional content is an important component of human caption evaluation, and propose a new automated caption evaluation metric defined over scene graphs coined SPICE. Extensive evaluations across a range of models and datasets indicate that SPICE captures human judgments over m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.08822","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":"1607.08822","created_at":"2026-05-18T01:10:15.832165+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.08822v1","created_at":"2026-05-18T01:10:15.832165+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.08822","created_at":"2026-05-18T01:10:15.832165+00:00"},{"alias_kind":"pith_short_12","alias_value":"O4RJEF26TSDY","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"O4RJEF26TSDYFK3P","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"O4RJEF26","created_at":"2026-05-18T12:30:36.002864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.20278","citing_title":"ClaimDiff-RL: Fine-Grained Caption Reinforcement Learning through Visual Claim Comparison","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2509.16538","citing_title":"VC-Inspector: Advancing Reference-free Evaluation of Video Captions with Factual Analysis","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07394","citing_title":"BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O4RJEF26TSDYFK3P5ZECDJ4OJS","json":"https://pith.science/pith/O4RJEF26TSDYFK3P5ZECDJ4OJS.json","graph_json":"https://pith.science/api/pith-number/O4RJEF26TSDYFK3P5ZECDJ4OJS/graph.json","events_json":"https://pith.science/api/pith-number/O4RJEF26TSDYFK3P5ZECDJ4OJS/events.json","paper":"https://pith.science/paper/O4RJEF26"},"agent_actions":{"view_html":"https://pith.science/pith/O4RJEF26TSDYFK3P5ZECDJ4OJS","download_json":"https://pith.science/pith/O4RJEF26TSDYFK3P5ZECDJ4OJS.json","view_paper":"https://pith.science/paper/O4RJEF26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.08822&json=true","fetch_graph":"https://pith.science/api/pith-number/O4RJEF26TSDYFK3P5ZECDJ4OJS/graph.json","fetch_events":"https://pith.science/api/pith-number/O4RJEF26TSDYFK3P5ZECDJ4OJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O4RJEF26TSDYFK3P5ZECDJ4OJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O4RJEF26TSDYFK3P5ZECDJ4OJS/action/storage_attestation","attest_author":"https://pith.science/pith/O4RJEF26TSDYFK3P5ZECDJ4OJS/action/author_attestation","sign_citation":"https://pith.science/pith/O4RJEF26TSDYFK3P5ZECDJ4OJS/action/citation_signature","submit_replication":"https://pith.science/pith/O4RJEF26TSDYFK3P5ZECDJ4OJS/action/replication_record"}},"created_at":"2026-05-18T01:10:15.832165+00:00","updated_at":"2026-05-18T01:10:15.832165+00:00"}