{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GP2ERJNOQFL5RRTWYO7IRDK7GN","short_pith_number":"pith:GP2ERJNO","schema_version":"1.0","canonical_sha256":"33f448a5ae8157d8c676c3be888d5f3360917125b609f7aec8055c05f7c825c7","source":{"kind":"arxiv","id":"2005.00908","version":1},"attestation_state":"computed","paper":{"title":"Clue: Cross-modal Coherence Modeling for Caption Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Malihe Alikhani, Matthew Stone, Piyush Sharma, Radu Soricut, Shengjie Li","submitted_at":"2020-05-02T19:28:52Z","abstract_excerpt":"We use coherence relations inspired by computational models of discourse to study the information needs and goals of image captioning. Using an annotation protocol specifically devised for capturing image--caption coherence relations, we annotate 10,000 instances from publicly-available image--caption pairs. We introduce a new task for learning inferences in imagery and text, coherence relation prediction, and show that these coherence annotations can be exploited to learn relation classifiers as an intermediary step, and also train coherence-aware, controllable image captioning models. The re"},"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":"2005.00908","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-02T19:28:52Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"06351399d81ea02aab01dc6be9652331f4a7fa8fd0d2a31475c08cc6d3ab89d9","abstract_canon_sha256":"05028a5d1ed7a3bfcf6ba9beb2e291089c319d78c94f0d8d00db42c4298cdf5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:20:06.943440Z","signature_b64":"chxmyLq1+fe20yc0BEu7ydVS/07PCISqPYzux+DBXZjby2cGgKbT4hWJdN6Sx0q3UuYro6OUiJSWCVVd/0GOAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33f448a5ae8157d8c676c3be888d5f3360917125b609f7aec8055c05f7c825c7","last_reissued_at":"2026-07-05T05:20:06.942961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:20:06.942961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clue: Cross-modal Coherence Modeling for Caption Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Malihe Alikhani, Matthew Stone, Piyush Sharma, Radu Soricut, Shengjie Li","submitted_at":"2020-05-02T19:28:52Z","abstract_excerpt":"We use coherence relations inspired by computational models of discourse to study the information needs and goals of image captioning. Using an annotation protocol specifically devised for capturing image--caption coherence relations, we annotate 10,000 instances from publicly-available image--caption pairs. We introduce a new task for learning inferences in imagery and text, coherence relation prediction, and show that these coherence annotations can be exploited to learn relation classifiers as an intermediary step, and also train coherence-aware, controllable image captioning models. The re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00908","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.00908/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2005.00908","created_at":"2026-07-05T05:20:06.943020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.00908v1","created_at":"2026-07-05T05:20:06.943020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00908","created_at":"2026-07-05T05:20:06.943020+00:00"},{"alias_kind":"pith_short_12","alias_value":"GP2ERJNOQFL5","created_at":"2026-07-05T05:20:06.943020+00:00"},{"alias_kind":"pith_short_16","alias_value":"GP2ERJNOQFL5RRTW","created_at":"2026-07-05T05:20:06.943020+00:00"},{"alias_kind":"pith_short_8","alias_value":"GP2ERJNO","created_at":"2026-07-05T05:20:06.943020+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/GP2ERJNOQFL5RRTWYO7IRDK7GN","json":"https://pith.science/pith/GP2ERJNOQFL5RRTWYO7IRDK7GN.json","graph_json":"https://pith.science/api/pith-number/GP2ERJNOQFL5RRTWYO7IRDK7GN/graph.json","events_json":"https://pith.science/api/pith-number/GP2ERJNOQFL5RRTWYO7IRDK7GN/events.json","paper":"https://pith.science/paper/GP2ERJNO"},"agent_actions":{"view_html":"https://pith.science/pith/GP2ERJNOQFL5RRTWYO7IRDK7GN","download_json":"https://pith.science/pith/GP2ERJNOQFL5RRTWYO7IRDK7GN.json","view_paper":"https://pith.science/paper/GP2ERJNO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.00908&json=true","fetch_graph":"https://pith.science/api/pith-number/GP2ERJNOQFL5RRTWYO7IRDK7GN/graph.json","fetch_events":"https://pith.science/api/pith-number/GP2ERJNOQFL5RRTWYO7IRDK7GN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GP2ERJNOQFL5RRTWYO7IRDK7GN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GP2ERJNOQFL5RRTWYO7IRDK7GN/action/storage_attestation","attest_author":"https://pith.science/pith/GP2ERJNOQFL5RRTWYO7IRDK7GN/action/author_attestation","sign_citation":"https://pith.science/pith/GP2ERJNOQFL5RRTWYO7IRDK7GN/action/citation_signature","submit_replication":"https://pith.science/pith/GP2ERJNOQFL5RRTWYO7IRDK7GN/action/replication_record"}},"created_at":"2026-07-05T05:20:06.943020+00:00","updated_at":"2026-07-05T05:20:06.943020+00:00"}