{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:S7MUHONQVFATVDTN2TUBG3EIWA","short_pith_number":"pith:S7MUHONQ","canonical_record":{"source":{"id":"1906.00295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-01T21:29:20Z","cross_cats_sorted":[],"title_canon_sha256":"be90c46412fa54279758b26edbcd8443d497f4385b4b6f9e9fce3e32e12b0e46","abstract_canon_sha256":"20fc4b81822694c866c14432f94ac4ab8fa521bd60c0fa17ca0fa5475fdf0c85"},"schema_version":"1.0"},"canonical_sha256":"97d943b9b0a9413a8e6dd4e8136c88b017a333d2b201c64a51bac99ff0de7fe3","source":{"kind":"arxiv","id":"1906.00295","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00295","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00295v1","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00295","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"pith_short_12","alias_value":"S7MUHONQVFAT","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"S7MUHONQVFATVDTN","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"S7MUHONQ","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:S7MUHONQVFATVDTN2TUBG3EIWA","target":"record","payload":{"canonical_record":{"source":{"id":"1906.00295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-01T21:29:20Z","cross_cats_sorted":[],"title_canon_sha256":"be90c46412fa54279758b26edbcd8443d497f4385b4b6f9e9fce3e32e12b0e46","abstract_canon_sha256":"20fc4b81822694c866c14432f94ac4ab8fa521bd60c0fa17ca0fa5475fdf0c85"},"schema_version":"1.0"},"canonical_sha256":"97d943b9b0a9413a8e6dd4e8136c88b017a333d2b201c64a51bac99ff0de7fe3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:27.536941Z","signature_b64":"HmREfLAG9EPo1UTfIJJLG6bcq+pbVmx9pHLppqNME01/krsxkOJRac8GG2yNpmlylb4JQsnidpF1WfvtONlMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97d943b9b0a9413a8e6dd4e8136c88b017a333d2b201c64a51bac99ff0de7fe3","last_reissued_at":"2026-05-17T23:44:27.536440Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:27.536440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.00295","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":"2026-05-17T23:44:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IZFvAzlurSDrTjKE8zr1lkTGRhBZ5Rj+gA7wrcIpi+irNxRtzZ7Fbvg/vMoxFhWbvMZZ+bsyYZKyfrz81pfdDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:05:16.228900Z"},"content_sha256":"d13b66cb0c35b5be8ac75707a868c1b73f7acf2b04fac338402476ddeb8fc2f6","schema_version":"1.0","event_id":"sha256:d13b66cb0c35b5be8ac75707a868c1b73f7acf2b04fac338402476ddeb8fc2f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:S7MUHONQVFATVDTN2TUBG3EIWA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"J. Zico Kolter, Louis-Philippe Morency, Paul Pu Liang, Ruslan Salakhutdinov, Shaojie Bai, Yao-Hung Hubert Tsai","submitted_at":"2019-06-01T21:29:20Z","abstract_excerpt":"Human language is often multimodal, which comprehends a mixture of natural language, facial gestures, and acoustic behaviors. However, two major challenges in modeling such multimodal human language time-series data exist: 1) inherent data non-alignment due to variable sampling rates for the sequences from each modality; and 2) long-range dependencies between elements across modalities. In this paper, we introduce the Multimodal Transformer (MulT) to generically address the above issues in an end-to-end manner without explicitly aligning the data. At the heart of our model is the directional p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00295","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":""},"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":"2026-05-17T23:44:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fyhn/KCTvd6YDPmBKuZ2wXPomRVItwm3sxKc0dpJerwfGtQcBPkU45JbjSn+pyAZ8VAsTqgxWY4krHPZWaxEBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:05:16.229518Z"},"content_sha256":"9210ed84da3ba7fef04b721f4e8de8833bd34b1815065a267aefdc80bc96b7f1","schema_version":"1.0","event_id":"sha256:9210ed84da3ba7fef04b721f4e8de8833bd34b1815065a267aefdc80bc96b7f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S7MUHONQVFATVDTN2TUBG3EIWA/bundle.json","state_url":"https://pith.science/pith/S7MUHONQVFATVDTN2TUBG3EIWA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S7MUHONQVFATVDTN2TUBG3EIWA/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":"2026-05-26T06:05:16Z","links":{"resolver":"https://pith.science/pith/S7MUHONQVFATVDTN2TUBG3EIWA","bundle":"https://pith.science/pith/S7MUHONQVFATVDTN2TUBG3EIWA/bundle.json","state":"https://pith.science/pith/S7MUHONQVFATVDTN2TUBG3EIWA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S7MUHONQVFATVDTN2TUBG3EIWA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:S7MUHONQVFATVDTN2TUBG3EIWA","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":"20fc4b81822694c866c14432f94ac4ab8fa521bd60c0fa17ca0fa5475fdf0c85","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-01T21:29:20Z","title_canon_sha256":"be90c46412fa54279758b26edbcd8443d497f4385b4b6f9e9fce3e32e12b0e46"},"schema_version":"1.0","source":{"id":"1906.00295","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00295","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00295v1","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00295","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"pith_short_12","alias_value":"S7MUHONQVFAT","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"S7MUHONQVFATVDTN","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"S7MUHONQ","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:9210ed84da3ba7fef04b721f4e8de8833bd34b1815065a267aefdc80bc96b7f1","target":"graph","created_at":"2026-05-17T23:44:27Z","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":"Human language is often multimodal, which comprehends a mixture of natural language, facial gestures, and acoustic behaviors. However, two major challenges in modeling such multimodal human language time-series data exist: 1) inherent data non-alignment due to variable sampling rates for the sequences from each modality; and 2) long-range dependencies between elements across modalities. In this paper, we introduce the Multimodal Transformer (MulT) to generically address the above issues in an end-to-end manner without explicitly aligning the data. At the heart of our model is the directional p","authors_text":"J. Zico Kolter, Louis-Philippe Morency, Paul Pu Liang, Ruslan Salakhutdinov, Shaojie Bai, Yao-Hung Hubert Tsai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-01T21:29:20Z","title":"Multimodal Transformer for Unaligned Multimodal Language Sequences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00295","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:d13b66cb0c35b5be8ac75707a868c1b73f7acf2b04fac338402476ddeb8fc2f6","target":"record","created_at":"2026-05-17T23:44:27Z","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":"20fc4b81822694c866c14432f94ac4ab8fa521bd60c0fa17ca0fa5475fdf0c85","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-01T21:29:20Z","title_canon_sha256":"be90c46412fa54279758b26edbcd8443d497f4385b4b6f9e9fce3e32e12b0e46"},"schema_version":"1.0","source":{"id":"1906.00295","kind":"arxiv","version":1}},"canonical_sha256":"97d943b9b0a9413a8e6dd4e8136c88b017a333d2b201c64a51bac99ff0de7fe3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97d943b9b0a9413a8e6dd4e8136c88b017a333d2b201c64a51bac99ff0de7fe3","first_computed_at":"2026-05-17T23:44:27.536440Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:27.536440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HmREfLAG9EPo1UTfIJJLG6bcq+pbVmx9pHLppqNME01/krsxkOJRac8GG2yNpmlylb4JQsnidpF1WfvtONlMAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:27.536941Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.00295","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d13b66cb0c35b5be8ac75707a868c1b73f7acf2b04fac338402476ddeb8fc2f6","sha256:9210ed84da3ba7fef04b721f4e8de8833bd34b1815065a267aefdc80bc96b7f1"],"state_sha256":"366f0645c1816edc07b7b45e47d2004d6766a6f13b773b6dc153ae899780ebcd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LCd49Q4QVHou8udbGs7jsr1ySGUiq7wAvKZyPo2U7D9odjMLl8ppAk6HQ1yOhP7djCzlPAj6G3tDJjqfsc+9AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T06:05:16.232777Z","bundle_sha256":"efeea7421cd9515fed31e5697948e1c9ffdacd12592e169e0792bebb2bfe48c9"}}