{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZKC3MUZBT7VK7W2SDWFODZR7HV","short_pith_number":"pith:ZKC3MUZB","canonical_record":{"source":{"id":"1912.02379","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-05T04:51:11Z","cross_cats_sorted":["cs.CL","cs.CV","stat.ML"],"title_canon_sha256":"db56b816971cb85c0bcc8b8712f4ba7ec3f89b4b0e323dd7dda12ee0628d278b","abstract_canon_sha256":"b022b6a4b155a3914f54fc36d4a8226927946736b46cc2f39a04f169bc2086a9"},"schema_version":"1.0"},"canonical_sha256":"ca85b653219feaafdb521d8ae1e63f3d690fd6d1e85ba5586fe8109af50fb1a0","source":{"kind":"arxiv","id":"1912.02379","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.02379","created_at":"2026-07-05T00:51:35Z"},{"alias_kind":"arxiv_version","alias_value":"1912.02379v2","created_at":"2026-07-05T00:51:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.02379","created_at":"2026-07-05T00:51:35Z"},{"alias_kind":"pith_short_12","alias_value":"ZKC3MUZBT7VK","created_at":"2026-07-05T00:51:35Z"},{"alias_kind":"pith_short_16","alias_value":"ZKC3MUZBT7VK7W2S","created_at":"2026-07-05T00:51:35Z"},{"alias_kind":"pith_short_8","alias_value":"ZKC3MUZB","created_at":"2026-07-05T00:51:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZKC3MUZBT7VK7W2SDWFODZR7HV","target":"record","payload":{"canonical_record":{"source":{"id":"1912.02379","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-05T04:51:11Z","cross_cats_sorted":["cs.CL","cs.CV","stat.ML"],"title_canon_sha256":"db56b816971cb85c0bcc8b8712f4ba7ec3f89b4b0e323dd7dda12ee0628d278b","abstract_canon_sha256":"b022b6a4b155a3914f54fc36d4a8226927946736b46cc2f39a04f169bc2086a9"},"schema_version":"1.0"},"canonical_sha256":"ca85b653219feaafdb521d8ae1e63f3d690fd6d1e85ba5586fe8109af50fb1a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:35.344943Z","signature_b64":"OYd+nSregmF21ae2dRLvcSCzbdHXIpU7PfhdGOLu2YSjBDAS1KPR5+Wu6uqovSLu9vYD6C8KSLEpmkWioC1BAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca85b653219feaafdb521d8ae1e63f3d690fd6d1e85ba5586fe8109af50fb1a0","last_reissued_at":"2026-07-05T00:51:35.344332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:35.344332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.02379","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:51:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UxiUlY5jDDxcmuPrvKvzAaMLaUW5DjGVmAIA5BJ7t4PyfTn15DwB98QS6FjNe9PyPk40a4+IqlMct8EOs9acCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T15:20:57.806776Z"},"content_sha256":"ff48e3e18a3eacf27d8642721cef455e38f785fc207c2af6f9c06b33555bfbcf","schema_version":"1.0","event_id":"sha256:ff48e3e18a3eacf27d8642721cef455e38f785fc207c2af6f9c06b33555bfbcf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZKC3MUZBT7VK7W2SDWFODZR7HV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Das, Devi Parikh, Dhruv Batra, Vishvak Murahari","submitted_at":"2019-12-05T04:51:11Z","abstract_excerpt":"Prior work in visual dialog has focused on training deep neural models on VisDial in isolation. Instead, we present an approach to leverage pretraining on related vision-language datasets before transferring to visual dialog. We adapt the recently proposed ViLBERT (Lu et al., 2019) model for multi-turn visually-grounded conversations. Our model is pretrained on the Conceptual Captions and Visual Question Answering datasets, and finetuned on VisDial. Our best single model outperforms prior published work (including model ensembles) by more than 1% absolute on NDCG and MRR. Next, we find that ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.02379","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.02379/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:51:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WWFvuPSC/WAAJ/MzTbcMhkqDp5ZBzFVnfG3ElMejtOIne4PY3qHBeqOFwM7Vv0EGv7RdxIurGNxfkooca/0rAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T15:20:57.807289Z"},"content_sha256":"8cc5e6bd4e65b6a3b4e1ecc16fa81cd5d176066a50c3b09119c0eb08e86cf462","schema_version":"1.0","event_id":"sha256:8cc5e6bd4e65b6a3b4e1ecc16fa81cd5d176066a50c3b09119c0eb08e86cf462"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZKC3MUZBT7VK7W2SDWFODZR7HV/bundle.json","state_url":"https://pith.science/pith/ZKC3MUZBT7VK7W2SDWFODZR7HV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZKC3MUZBT7VK7W2SDWFODZR7HV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-22T15:20:57Z","links":{"resolver":"https://pith.science/pith/ZKC3MUZBT7VK7W2SDWFODZR7HV","bundle":"https://pith.science/pith/ZKC3MUZBT7VK7W2SDWFODZR7HV/bundle.json","state":"https://pith.science/pith/ZKC3MUZBT7VK7W2SDWFODZR7HV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZKC3MUZBT7VK7W2SDWFODZR7HV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZKC3MUZBT7VK7W2SDWFODZR7HV","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":"b022b6a4b155a3914f54fc36d4a8226927946736b46cc2f39a04f169bc2086a9","cross_cats_sorted":["cs.CL","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-05T04:51:11Z","title_canon_sha256":"db56b816971cb85c0bcc8b8712f4ba7ec3f89b4b0e323dd7dda12ee0628d278b"},"schema_version":"1.0","source":{"id":"1912.02379","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.02379","created_at":"2026-07-05T00:51:35Z"},{"alias_kind":"arxiv_version","alias_value":"1912.02379v2","created_at":"2026-07-05T00:51:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.02379","created_at":"2026-07-05T00:51:35Z"},{"alias_kind":"pith_short_12","alias_value":"ZKC3MUZBT7VK","created_at":"2026-07-05T00:51:35Z"},{"alias_kind":"pith_short_16","alias_value":"ZKC3MUZBT7VK7W2S","created_at":"2026-07-05T00:51:35Z"},{"alias_kind":"pith_short_8","alias_value":"ZKC3MUZB","created_at":"2026-07-05T00:51:35Z"}],"graph_snapshots":[{"event_id":"sha256:8cc5e6bd4e65b6a3b4e1ecc16fa81cd5d176066a50c3b09119c0eb08e86cf462","target":"graph","created_at":"2026-07-05T00:51:35Z","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/1912.02379/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prior work in visual dialog has focused on training deep neural models on VisDial in isolation. Instead, we present an approach to leverage pretraining on related vision-language datasets before transferring to visual dialog. We adapt the recently proposed ViLBERT (Lu et al., 2019) model for multi-turn visually-grounded conversations. Our model is pretrained on the Conceptual Captions and Visual Question Answering datasets, and finetuned on VisDial. Our best single model outperforms prior published work (including model ensembles) by more than 1% absolute on NDCG and MRR. Next, we find that ad","authors_text":"Abhishek Das, Devi Parikh, Dhruv Batra, Vishvak Murahari","cross_cats":["cs.CL","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-05T04:51:11Z","title":"Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.02379","kind":"arxiv","version":2},"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:ff48e3e18a3eacf27d8642721cef455e38f785fc207c2af6f9c06b33555bfbcf","target":"record","created_at":"2026-07-05T00:51:35Z","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":"b022b6a4b155a3914f54fc36d4a8226927946736b46cc2f39a04f169bc2086a9","cross_cats_sorted":["cs.CL","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-05T04:51:11Z","title_canon_sha256":"db56b816971cb85c0bcc8b8712f4ba7ec3f89b4b0e323dd7dda12ee0628d278b"},"schema_version":"1.0","source":{"id":"1912.02379","kind":"arxiv","version":2}},"canonical_sha256":"ca85b653219feaafdb521d8ae1e63f3d690fd6d1e85ba5586fe8109af50fb1a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca85b653219feaafdb521d8ae1e63f3d690fd6d1e85ba5586fe8109af50fb1a0","first_computed_at":"2026-07-05T00:51:35.344332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:51:35.344332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OYd+nSregmF21ae2dRLvcSCzbdHXIpU7PfhdGOLu2YSjBDAS1KPR5+Wu6uqovSLu9vYD6C8KSLEpmkWioC1BAA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:51:35.344943Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.02379","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff48e3e18a3eacf27d8642721cef455e38f785fc207c2af6f9c06b33555bfbcf","sha256:8cc5e6bd4e65b6a3b4e1ecc16fa81cd5d176066a50c3b09119c0eb08e86cf462"],"state_sha256":"fb098a235da0e5e71ca81cfb67ea23cad3a1c5b2289064f7e15f731a372e8b58"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4xLGZGotiKFcnci92c7EToah+qB+d6Ggz8kEl/fnNCsejuuAdRHc29xFQuDRuZ1kWrUAexoIkG08caUal0AZCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T15:20:57.812400Z","bundle_sha256":"ab5e11f55b6be81219f84def5db3eba723cfcb033c5ede358f4b2da990b9389b"}}