{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IYYJFQ6SCY44BMRRF2X7REIBTZ","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":"9ef07deefcad07d2d6ae8cd5eb8850f46777ecf2bbeeab89f243551007d8b0ea","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-28T15:22:36Z","title_canon_sha256":"9f18bb3803dacd0aa36d27255c261560c6e07da31c1c07dc093d5a8f3dc157bc"},"schema_version":"1.0","source":{"id":"2101.12059","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.12059","created_at":"2026-07-05T02:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"2101.12059v2","created_at":"2026-07-05T02:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.12059","created_at":"2026-07-05T02:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"IYYJFQ6SCY44","created_at":"2026-07-05T02:10:49Z"},{"alias_kind":"pith_short_16","alias_value":"IYYJFQ6SCY44BMRR","created_at":"2026-07-05T02:10:49Z"},{"alias_kind":"pith_short_8","alias_value":"IYYJFQ6S","created_at":"2026-07-05T02:10:49Z"}],"graph_snapshots":[{"event_id":"sha256:953edfdc2e7eed79458437f6323856ffd7b41b44e086f8ff498bdc7b708e3fd3","target":"graph","created_at":"2026-07-05T02:10:49Z","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/2101.12059/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present \\textsc{Vx2Text}, a framework for text generation from multimodal inputs consisting of video plus text, speech, or audio. In order to leverage transformer networks, which have been shown to be effective at modeling language, each modality is first converted into a set of language embeddings by a learnable tokenizer. This allows our approach to perform multimodal fusion in the language space, thus eliminating the need for ad-hoc cross-modal fusion modules. To address the non-differentiability of tokenization on continuous inputs (e.g., video or audio), we utilize a relaxation scheme ","authors_text":"Devi Parikh, Gedas Bertasius, Jue Wang, Lorenzo Torresani, Shih-Fu Chang, Xudong Lin","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-28T15:22:36Z","title":"VX2TEXT: End-to-End Learning of Video-Based Text Generation From Multimodal Inputs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.12059","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":"sha256:07ec9ed1b80e9c4f80a22dd56ef23715c6edbd915f1c2d002ed3c3bee24f06e6","target":"record","created_at":"2026-07-05T02:10:49Z","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":"9ef07deefcad07d2d6ae8cd5eb8850f46777ecf2bbeeab89f243551007d8b0ea","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-28T15:22:36Z","title_canon_sha256":"9f18bb3803dacd0aa36d27255c261560c6e07da31c1c07dc093d5a8f3dc157bc"},"schema_version":"1.0","source":{"id":"2101.12059","kind":"arxiv","version":2}},"canonical_sha256":"463092c3d21639c0b2312eaff891019e72d412930cb16667673c360ab90b634f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"463092c3d21639c0b2312eaff891019e72d412930cb16667673c360ab90b634f","first_computed_at":"2026-07-05T02:10:49.418648Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:10:49.418648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jn7n9imIQMlUrpsJaxzYPBs9BRpvyxXOGY0qHOd4Nq5WZD05sw0v8ezPnVu5HxSjcPfM7jQ6sBupknsIFvkXBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:10:49.419058Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.12059","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07ec9ed1b80e9c4f80a22dd56ef23715c6edbd915f1c2d002ed3c3bee24f06e6","sha256:953edfdc2e7eed79458437f6323856ffd7b41b44e086f8ff498bdc7b708e3fd3"],"state_sha256":"c2b1d00a6a97229ca439fa01bd98cb01685c21080b3fa4dc5f6376d306bf380b"}