{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:4W3VMLQUQ4QVZVFWLMZJKHVO3W","short_pith_number":"pith:4W3VMLQU","canonical_record":{"source":{"id":"1902.09326","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-25T14:58:35Z","cross_cats_sorted":[],"title_canon_sha256":"2cbab8325fdf9cce8c00b6afa83f131e4373538a8b510036628ee75f23e5696b","abstract_canon_sha256":"dd16e6de1b77a794c9803ca88d72915e76c3233d970e80868f53a4d3fa16ebb0"},"schema_version":"1.0"},"canonical_sha256":"e5b7562e1487215cd4b65b32951eaeddafca8387f7dee021581103cb390a183c","source":{"kind":"arxiv","id":"1902.09326","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.09326","created_at":"2026-05-17T23:48:19Z"},{"alias_kind":"arxiv_version","alias_value":"1902.09326v3","created_at":"2026-05-17T23:48:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09326","created_at":"2026-05-17T23:48:19Z"},{"alias_kind":"pith_short_12","alias_value":"4W3VMLQUQ4QV","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4W3VMLQUQ4QVZVFW","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4W3VMLQU","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:4W3VMLQUQ4QVZVFWLMZJKHVO3W","target":"record","payload":{"canonical_record":{"source":{"id":"1902.09326","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-25T14:58:35Z","cross_cats_sorted":[],"title_canon_sha256":"2cbab8325fdf9cce8c00b6afa83f131e4373538a8b510036628ee75f23e5696b","abstract_canon_sha256":"dd16e6de1b77a794c9803ca88d72915e76c3233d970e80868f53a4d3fa16ebb0"},"schema_version":"1.0"},"canonical_sha256":"e5b7562e1487215cd4b65b32951eaeddafca8387f7dee021581103cb390a183c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:19.910396Z","signature_b64":"DvirfbiKxTbk3tL1H/MvVqc810D8IgtNLGm4FNoqC4OWWjXB9u+sHIPTtZWXx0CAMvmkrxs5J5hsGe0WeJagBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5b7562e1487215cd4b65b32951eaeddafca8387f7dee021581103cb390a183c","last_reissued_at":"2026-05-17T23:48:19.909651Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:19.909651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.09326","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:48:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oHxh9YmOVFiNCzICm7TcRtjQ1TTlhoqgGkv++JM+Jvdw1+Uml3fmmSF5vreHqg1n4vP59aR1TZpukKc5BhLPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T00:53:01.064749Z"},"content_sha256":"5d85490d660a7acce30de55e4c7894d98cf4537d854905b48bb7a38d9401f7e3","schema_version":"1.0","event_id":"sha256:5d85490d660a7acce30de55e4c7894d98cf4537d854905b48bb7a38d9401f7e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:4W3VMLQUQ4QVZVFWLMZJKHVO3W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Making History Matter: History-Advantage Sequence Training for Visual Dialog","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanwang Zhang, Tianhao Yang, Zheng-Jun Zha","submitted_at":"2019-02-25T14:58:35Z","abstract_excerpt":"We study the multi-round response generation in visual dialog, where a response is generated according to a visually grounded conversational history. Given a triplet: an image, Q&A history, and current question, all the prevailing methods follow a codec (i.e., encoder-decoder) fashion in a supervised learning paradigm: a multimodal encoder encodes the triplet into a feature vector, which is then fed into the decoder for the current answer generation, supervised by the ground-truth. However, this conventional supervised learning does NOT take into account the impact of imperfect history, violat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09326","kind":"arxiv","version":3},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:48:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"InpAMfgY339JmvxRMWg3aGUGdR7rGEDvqsln3snoqPMADzmTH3QoOOFNobHKU2+LKOrz+0E6Ov7dtm9CdlMRAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T00:53:01.065417Z"},"content_sha256":"765213086efb518989948ad0a8158e98b4132a94e18df0dacd6802adb530e249","schema_version":"1.0","event_id":"sha256:765213086efb518989948ad0a8158e98b4132a94e18df0dacd6802adb530e249"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4W3VMLQUQ4QVZVFWLMZJKHVO3W/bundle.json","state_url":"https://pith.science/pith/4W3VMLQUQ4QVZVFWLMZJKHVO3W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4W3VMLQUQ4QVZVFWLMZJKHVO3W/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":"2026-06-05T00:53:01Z","links":{"resolver":"https://pith.science/pith/4W3VMLQUQ4QVZVFWLMZJKHVO3W","bundle":"https://pith.science/pith/4W3VMLQUQ4QVZVFWLMZJKHVO3W/bundle.json","state":"https://pith.science/pith/4W3VMLQUQ4QVZVFWLMZJKHVO3W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4W3VMLQUQ4QVZVFWLMZJKHVO3W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4W3VMLQUQ4QVZVFWLMZJKHVO3W","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":"dd16e6de1b77a794c9803ca88d72915e76c3233d970e80868f53a4d3fa16ebb0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-25T14:58:35Z","title_canon_sha256":"2cbab8325fdf9cce8c00b6afa83f131e4373538a8b510036628ee75f23e5696b"},"schema_version":"1.0","source":{"id":"1902.09326","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.09326","created_at":"2026-05-17T23:48:19Z"},{"alias_kind":"arxiv_version","alias_value":"1902.09326v3","created_at":"2026-05-17T23:48:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09326","created_at":"2026-05-17T23:48:19Z"},{"alias_kind":"pith_short_12","alias_value":"4W3VMLQUQ4QV","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4W3VMLQUQ4QVZVFW","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4W3VMLQU","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:765213086efb518989948ad0a8158e98b4132a94e18df0dacd6802adb530e249","target":"graph","created_at":"2026-05-17T23:48:19Z","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"},"paper":{"abstract_excerpt":"We study the multi-round response generation in visual dialog, where a response is generated according to a visually grounded conversational history. Given a triplet: an image, Q&A history, and current question, all the prevailing methods follow a codec (i.e., encoder-decoder) fashion in a supervised learning paradigm: a multimodal encoder encodes the triplet into a feature vector, which is then fed into the decoder for the current answer generation, supervised by the ground-truth. However, this conventional supervised learning does NOT take into account the impact of imperfect history, violat","authors_text":"Hanwang Zhang, Tianhao Yang, Zheng-Jun Zha","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-25T14:58:35Z","title":"Making History Matter: History-Advantage Sequence Training for Visual Dialog"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09326","kind":"arxiv","version":3},"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":"sha256:5d85490d660a7acce30de55e4c7894d98cf4537d854905b48bb7a38d9401f7e3","target":"record","created_at":"2026-05-17T23:48:19Z","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":"dd16e6de1b77a794c9803ca88d72915e76c3233d970e80868f53a4d3fa16ebb0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-25T14:58:35Z","title_canon_sha256":"2cbab8325fdf9cce8c00b6afa83f131e4373538a8b510036628ee75f23e5696b"},"schema_version":"1.0","source":{"id":"1902.09326","kind":"arxiv","version":3}},"canonical_sha256":"e5b7562e1487215cd4b65b32951eaeddafca8387f7dee021581103cb390a183c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5b7562e1487215cd4b65b32951eaeddafca8387f7dee021581103cb390a183c","first_computed_at":"2026-05-17T23:48:19.909651Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:19.909651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DvirfbiKxTbk3tL1H/MvVqc810D8IgtNLGm4FNoqC4OWWjXB9u+sHIPTtZWXx0CAMvmkrxs5J5hsGe0WeJagBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:19.910396Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.09326","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d85490d660a7acce30de55e4c7894d98cf4537d854905b48bb7a38d9401f7e3","sha256:765213086efb518989948ad0a8158e98b4132a94e18df0dacd6802adb530e249"],"state_sha256":"2dd4231ce359096a242dd1e4357ffbc83081184fac6455ecb1eac894fa3cb7cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XwfK4iX3L80jOOzEnsyc8hIAPtQjujxMrGWuct+TaRCC9LZrkcbt+/8hwyO90k8cK9o3IcbTXdIIsUYE5lf8DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T00:53:01.068677Z","bundle_sha256":"9aba3c05493a8796b26b6de89e9e98082a01ac1bc5b0f67b8d16fbd7f233ee3d"}}