{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:REYRUNEEWNGUS7ORGQ3F23YMBI","short_pith_number":"pith:REYRUNEE","schema_version":"1.0","canonical_sha256":"89311a3484b34d497dd134365d6f0c0a237fdbb75d669ae9024bfbc67716101f","source":{"kind":"arxiv","id":"1812.05634","version":2},"attestation_state":"computed","paper":{"title":"Adversarial Inference for Multi-Sentence Video Description","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anna Rohrbach, Jae Sung Park, Marcus Rohrbach, Trevor Darrell","submitted_at":"2018-12-13T19:07:17Z","abstract_excerpt":"While significant progress has been made in the image captioning task, video description is still in its infancy due to the complex nature of video data. Generating multi-sentence descriptions for long videos is even more challenging. Among the main issues are the fluency and coherence of the generated descriptions, and their relevance to the video. Recently, reinforcement and adversarial learning based methods have been explored to improve the image captioning models; however, both types of methods suffer from a number of issues, e.g. poor readability and high redundancy for RL and stability "},"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":"1812.05634","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-13T19:07:17Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"06bddcfc0edf461157cdea6cae639d689bd5f257b79014e343e2929392e81d7e","abstract_canon_sha256":"2f9e2e4e1c3f9a033cb1d6928791b0d13f11db26f424e970cdaf05e028524e04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:31.195943Z","signature_b64":"xVbPK4rwHA4d31fgADH2gsMnJay8DZ6KqvJenL8C80OyFbNAR33yMVnjrRDyFBW3qAonQJK0ormg1L0wJ1kaBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89311a3484b34d497dd134365d6f0c0a237fdbb75d669ae9024bfbc67716101f","last_reissued_at":"2026-05-17T23:48:31.195336Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:31.195336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Inference for Multi-Sentence Video Description","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anna Rohrbach, Jae Sung Park, Marcus Rohrbach, Trevor Darrell","submitted_at":"2018-12-13T19:07:17Z","abstract_excerpt":"While significant progress has been made in the image captioning task, video description is still in its infancy due to the complex nature of video data. Generating multi-sentence descriptions for long videos is even more challenging. Among the main issues are the fluency and coherence of the generated descriptions, and their relevance to the video. Recently, reinforcement and adversarial learning based methods have been explored to improve the image captioning models; however, both types of methods suffer from a number of issues, e.g. poor readability and high redundancy for RL and stability "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.05634","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":"1812.05634","created_at":"2026-05-17T23:48:31.195437+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.05634v2","created_at":"2026-05-17T23:48:31.195437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.05634","created_at":"2026-05-17T23:48:31.195437+00:00"},{"alias_kind":"pith_short_12","alias_value":"REYRUNEEWNGU","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"REYRUNEEWNGUS7OR","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"REYRUNEE","created_at":"2026-05-18T12:32:50.500415+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/REYRUNEEWNGUS7ORGQ3F23YMBI","json":"https://pith.science/pith/REYRUNEEWNGUS7ORGQ3F23YMBI.json","graph_json":"https://pith.science/api/pith-number/REYRUNEEWNGUS7ORGQ3F23YMBI/graph.json","events_json":"https://pith.science/api/pith-number/REYRUNEEWNGUS7ORGQ3F23YMBI/events.json","paper":"https://pith.science/paper/REYRUNEE"},"agent_actions":{"view_html":"https://pith.science/pith/REYRUNEEWNGUS7ORGQ3F23YMBI","download_json":"https://pith.science/pith/REYRUNEEWNGUS7ORGQ3F23YMBI.json","view_paper":"https://pith.science/paper/REYRUNEE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.05634&json=true","fetch_graph":"https://pith.science/api/pith-number/REYRUNEEWNGUS7ORGQ3F23YMBI/graph.json","fetch_events":"https://pith.science/api/pith-number/REYRUNEEWNGUS7ORGQ3F23YMBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/REYRUNEEWNGUS7ORGQ3F23YMBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/REYRUNEEWNGUS7ORGQ3F23YMBI/action/storage_attestation","attest_author":"https://pith.science/pith/REYRUNEEWNGUS7ORGQ3F23YMBI/action/author_attestation","sign_citation":"https://pith.science/pith/REYRUNEEWNGUS7ORGQ3F23YMBI/action/citation_signature","submit_replication":"https://pith.science/pith/REYRUNEEWNGUS7ORGQ3F23YMBI/action/replication_record"}},"created_at":"2026-05-17T23:48:31.195437+00:00","updated_at":"2026-05-17T23:48:31.195437+00:00"}