{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:E34SSF2V35XGU6BUPZZ5KHTHFE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"77788d3e9912bab93162cb4b50351d9cfb3ce6bf35a9dcaeacd27c566ccce2f4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-17T15:27:37Z","title_canon_sha256":"9d5d4307a27ec8a632838559e6e320eadeff168a03c8b943258621b971a30c81"},"schema_version":"1.0","source":{"id":"2007.09049","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.09049","created_at":"2026-07-05T01:20:06Z"},{"alias_kind":"arxiv_version","alias_value":"2007.09049v1","created_at":"2026-07-05T01:20:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.09049","created_at":"2026-07-05T01:20:06Z"},{"alias_kind":"pith_short_12","alias_value":"E34SSF2V35XG","created_at":"2026-07-05T01:20:06Z"},{"alias_kind":"pith_short_16","alias_value":"E34SSF2V35XGU6BU","created_at":"2026-07-05T01:20:06Z"},{"alias_kind":"pith_short_8","alias_value":"E34SSF2V","created_at":"2026-07-05T01:20:06Z"}],"graph_snapshots":[{"event_id":"sha256:3219b275f69b5f8ab9d03ea07649e1d3ae7a6f106f6ebe06d9c3410ff2b674df","target":"graph","created_at":"2026-07-05T01:20:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2007.09049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating natural language descriptions for videos, i.e., video captioning, essentially requires step-by-step reasoning along the generation process. For example, to generate the sentence \"a man is shooting a basketball\", we need to first locate and describe the subject \"man\", next reason out the man is \"shooting\", then describe the object \"basketball\" of shooting. However, existing visual reasoning methods designed for visual question answering are not appropriate to video captioning, for it requires more complex visual reasoning on videos over both space and time, and dynamic module composi","authors_text":"Daqing Liu, Ganchao Tan, Meng Wang, Zheng-Jun Zha","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-17T15:27:37Z","title":"Learning to Discretely Compose Reasoning Module Networks for Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.09049","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1ccd690913852067fb363fa71fdf88ff91ee80ccfe289eebaf6bc52034af582e","target":"record","created_at":"2026-07-05T01:20:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"77788d3e9912bab93162cb4b50351d9cfb3ce6bf35a9dcaeacd27c566ccce2f4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-17T15:27:37Z","title_canon_sha256":"9d5d4307a27ec8a632838559e6e320eadeff168a03c8b943258621b971a30c81"},"schema_version":"1.0","source":{"id":"2007.09049","kind":"arxiv","version":1}},"canonical_sha256":"26f9291755df6e6a78347e73d51e67290d91f17a2beba4459db7323375597455","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26f9291755df6e6a78347e73d51e67290d91f17a2beba4459db7323375597455","first_computed_at":"2026-07-05T01:20:06.378905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:20:06.378905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IASge2NezMTKIozd4b8ltk1bqBNDm5YFrszMlGURWx71g5r38aTPMeggsv7msjUqc0NolwKlIRt4J8dZIFNaCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:20:06.379383Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.09049","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ccd690913852067fb363fa71fdf88ff91ee80ccfe289eebaf6bc52034af582e","sha256:3219b275f69b5f8ab9d03ea07649e1d3ae7a6f106f6ebe06d9c3410ff2b674df"],"state_sha256":"85157850235d38e439ac23a039ccd1fbd8cea4be2b5095ca194982179b461e1f"}