{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:62CWH2RHXPYPXLMIRVN3A4MDSN","short_pith_number":"pith:62CWH2RH","canonical_record":{"source":{"id":"2105.14445","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-30T07:20:28Z","cross_cats_sorted":[],"title_canon_sha256":"6bb6a636b069f325365d0ed13ba09b4f69c5215238092fe24e50c253831bbc36","abstract_canon_sha256":"0b984cb5200bc215e0a8f364a8d2d267993815da1ab5cf0b4da1908938ff3f93"},"schema_version":"1.0"},"canonical_sha256":"f68563ea27bbf0fbad888d5bb0718393616542a6aa96a29398cb10fe5e4972c6","source":{"kind":"arxiv","id":"2105.14445","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.14445","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"arxiv_version","alias_value":"2105.14445v1","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14445","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"pith_short_12","alias_value":"62CWH2RHXPYP","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"pith_short_16","alias_value":"62CWH2RHXPYPXLMI","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"pith_short_8","alias_value":"62CWH2RH","created_at":"2026-07-05T02:44:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:62CWH2RHXPYPXLMIRVN3A4MDSN","target":"record","payload":{"canonical_record":{"source":{"id":"2105.14445","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-30T07:20:28Z","cross_cats_sorted":[],"title_canon_sha256":"6bb6a636b069f325365d0ed13ba09b4f69c5215238092fe24e50c253831bbc36","abstract_canon_sha256":"0b984cb5200bc215e0a8f364a8d2d267993815da1ab5cf0b4da1908938ff3f93"},"schema_version":"1.0"},"canonical_sha256":"f68563ea27bbf0fbad888d5bb0718393616542a6aa96a29398cb10fe5e4972c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:23.960247Z","signature_b64":"pEr1enGIaDrS69R8wdyhBHjJw8nfkVImOgWEPJk5mWLix7+RcmjLUSgimyoDIwDW/ej20ZcgQZwkQz1mWQqtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f68563ea27bbf0fbad888d5bb0718393616542a6aa96a29398cb10fe5e4972c6","last_reissued_at":"2026-07-05T02:44:23.959842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:23.959842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.14445","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:44:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kDmv5EQj+30REDFvSvrUL1VrszkR+vy3WVhFJQimbXpxE8uHJyex1Wwu1FKwY1cd2r7joR9fgvd5FVX4U/F5DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T13:58:37.481564Z"},"content_sha256":"3eb79ef1ec44ef70b51985f094214aa2e0feb5f1e940954aa01c53fb08d36111","schema_version":"1.0","event_id":"sha256:3eb79ef1ec44ef70b51985f094214aa2e0feb5f1e940954aa01c53fb08d36111"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:62CWH2RHXPYPXLMIRVN3A4MDSN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Wu, Jiwei Li, Rongbin Ouyang, Rui Yan, Shuhe Wang, Tianwei Zhang, Xiaofei Sun, Yuxian Meng","submitted_at":"2021-05-30T07:20:28Z","abstract_excerpt":"Multi-modal dialog modeling is of growing interest. In this work, we propose frameworks to resolve a specific case of multi-modal dialog generation that better mimics multi-modal dialog generation in the real world, where each dialog turn is associated with the visual context in which it takes place. Specifically, we propose to model the mutual dependency between text-visual features, where the model not only needs to learn the probability of generating the next dialog utterance given preceding dialog utterances and visual contexts, but also the probability of predicting the visual features in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14445","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/2105.14445/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":"2026-07-05T02:44:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UCbfj7Kj6zMShU5VpdTg3QVLJn9Un99alcW+Gbq4liJFMwtnSOJAf6VGVeooxeueEBHSiy1KeAPwCPXiqFXkBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T13:58:37.481940Z"},"content_sha256":"e6a84834a9632873dad549e4b743143f259f6d22205f0f3ee8b5c9bd4dd9e240","schema_version":"1.0","event_id":"sha256:e6a84834a9632873dad549e4b743143f259f6d22205f0f3ee8b5c9bd4dd9e240"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/62CWH2RHXPYPXLMIRVN3A4MDSN/bundle.json","state_url":"https://pith.science/pith/62CWH2RHXPYPXLMIRVN3A4MDSN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/62CWH2RHXPYPXLMIRVN3A4MDSN/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":"2026-07-08T13:58:37Z","links":{"resolver":"https://pith.science/pith/62CWH2RHXPYPXLMIRVN3A4MDSN","bundle":"https://pith.science/pith/62CWH2RHXPYPXLMIRVN3A4MDSN/bundle.json","state":"https://pith.science/pith/62CWH2RHXPYPXLMIRVN3A4MDSN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/62CWH2RHXPYPXLMIRVN3A4MDSN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:62CWH2RHXPYPXLMIRVN3A4MDSN","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":"0b984cb5200bc215e0a8f364a8d2d267993815da1ab5cf0b4da1908938ff3f93","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-30T07:20:28Z","title_canon_sha256":"6bb6a636b069f325365d0ed13ba09b4f69c5215238092fe24e50c253831bbc36"},"schema_version":"1.0","source":{"id":"2105.14445","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.14445","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"arxiv_version","alias_value":"2105.14445v1","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14445","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"pith_short_12","alias_value":"62CWH2RHXPYP","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"pith_short_16","alias_value":"62CWH2RHXPYPXLMI","created_at":"2026-07-05T02:44:23Z"},{"alias_kind":"pith_short_8","alias_value":"62CWH2RH","created_at":"2026-07-05T02:44:23Z"}],"graph_snapshots":[{"event_id":"sha256:e6a84834a9632873dad549e4b743143f259f6d22205f0f3ee8b5c9bd4dd9e240","target":"graph","created_at":"2026-07-05T02:44:23Z","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/2105.14445/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal dialog modeling is of growing interest. In this work, we propose frameworks to resolve a specific case of multi-modal dialog generation that better mimics multi-modal dialog generation in the real world, where each dialog turn is associated with the visual context in which it takes place. Specifically, we propose to model the mutual dependency between text-visual features, where the model not only needs to learn the probability of generating the next dialog utterance given preceding dialog utterances and visual contexts, but also the probability of predicting the visual features in","authors_text":"Fei Wu, Jiwei Li, Rongbin Ouyang, Rui Yan, Shuhe Wang, Tianwei Zhang, Xiaofei Sun, Yuxian Meng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-30T07:20:28Z","title":"Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14445","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":"sha256:3eb79ef1ec44ef70b51985f094214aa2e0feb5f1e940954aa01c53fb08d36111","target":"record","created_at":"2026-07-05T02:44:23Z","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":"0b984cb5200bc215e0a8f364a8d2d267993815da1ab5cf0b4da1908938ff3f93","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-30T07:20:28Z","title_canon_sha256":"6bb6a636b069f325365d0ed13ba09b4f69c5215238092fe24e50c253831bbc36"},"schema_version":"1.0","source":{"id":"2105.14445","kind":"arxiv","version":1}},"canonical_sha256":"f68563ea27bbf0fbad888d5bb0718393616542a6aa96a29398cb10fe5e4972c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f68563ea27bbf0fbad888d5bb0718393616542a6aa96a29398cb10fe5e4972c6","first_computed_at":"2026-07-05T02:44:23.959842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:44:23.959842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pEr1enGIaDrS69R8wdyhBHjJw8nfkVImOgWEPJk5mWLix7+RcmjLUSgimyoDIwDW/ej20ZcgQZwkQz1mWQqtDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:44:23.960247Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.14445","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3eb79ef1ec44ef70b51985f094214aa2e0feb5f1e940954aa01c53fb08d36111","sha256:e6a84834a9632873dad549e4b743143f259f6d22205f0f3ee8b5c9bd4dd9e240"],"state_sha256":"cef038921577cd835ac63f1ed70479bf0141ae6bda98a079d35b2ec3641ac70a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QD2GevqcuT/7i52wIWXby2DWOEEwnAeMIlxUNK+nxBopQqatAb6GJk1fXoWm+23b07ZTzxs7nc1UxpFOZRG4Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T13:58:37.483915Z","bundle_sha256":"2c3f68337feabe7e35677d1ae06d679b498fdb9b261d128943d6bb2ccd311a50"}}