{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:S6ZQMDW7O3AB3Q2JFBDGGRVWXG","short_pith_number":"pith:S6ZQMDW7","canonical_record":{"source":{"id":"2209.09768","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-20T14:51:38Z","cross_cats_sorted":[],"title_canon_sha256":"1865fc78f80d458bbcdbea23de6692492f4954d03c580982fcc92e3d0ad05eec","abstract_canon_sha256":"50bef5a320e3b4e37271767dabb3ee50a3b3b8cff6bec32c2300c5e2c00fa511"},"schema_version":"1.0"},"canonical_sha256":"97b3060edf76c01dc34928466346b6b99e2984c1aca1d739b07efe4a3a336200","source":{"kind":"arxiv","id":"2209.09768","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.09768","created_at":"2026-07-05T04:59:34Z"},{"alias_kind":"arxiv_version","alias_value":"2209.09768v1","created_at":"2026-07-05T04:59:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.09768","created_at":"2026-07-05T04:59:34Z"},{"alias_kind":"pith_short_12","alias_value":"S6ZQMDW7O3AB","created_at":"2026-07-05T04:59:34Z"},{"alias_kind":"pith_short_16","alias_value":"S6ZQMDW7O3AB3Q2J","created_at":"2026-07-05T04:59:34Z"},{"alias_kind":"pith_short_8","alias_value":"S6ZQMDW7","created_at":"2026-07-05T04:59:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:S6ZQMDW7O3AB3Q2JFBDGGRVWXG","target":"record","payload":{"canonical_record":{"source":{"id":"2209.09768","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-20T14:51:38Z","cross_cats_sorted":[],"title_canon_sha256":"1865fc78f80d458bbcdbea23de6692492f4954d03c580982fcc92e3d0ad05eec","abstract_canon_sha256":"50bef5a320e3b4e37271767dabb3ee50a3b3b8cff6bec32c2300c5e2c00fa511"},"schema_version":"1.0"},"canonical_sha256":"97b3060edf76c01dc34928466346b6b99e2984c1aca1d739b07efe4a3a336200","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:59:34.155190Z","signature_b64":"pGWLHzTrQRCFftlDzS6HsM310EvRgPqRuti44ZJhGabkui6dTq4731k1djC12IyErplFLdwFgCnaNHXmwAQ6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97b3060edf76c01dc34928466346b6b99e2984c1aca1d739b07efe4a3a336200","last_reissued_at":"2026-07-05T04:59:34.154787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:59:34.154787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.09768","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":"2026-07-05T04:59:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f52ahz8Pu4vWBffBGpGqTlcthbxgnrrvZfTb5n/ninPLN9QLi1kVcEtsKt6HTA1zWwG9cec39TNazlkxmcbIAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:03:47.375724Z"},"content_sha256":"e2386cc6b709b3fdffe1c28da8817eebe0f60e2499706d7c90333cc55e5a31d5","schema_version":"1.0","event_id":"sha256:e2386cc6b709b3fdffe1c28da8817eebe0f60e2499706d7c90333cc55e5a31d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:S6ZQMDW7O3AB3Q2JFBDGGRVWXG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Efficient End-to-End Transformer with Progressive Tri-modal Attention for Multi-modal Emotion Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Qin, Pai Peng, Yang Wu, Yanyan Zhao, Zhenyu Zhang","submitted_at":"2022-09-20T14:51:38Z","abstract_excerpt":"Recent works on multi-modal emotion recognition move towards end-to-end models, which can extract the task-specific features supervised by the target task compared with the two-phase pipeline. However, previous methods only model the feature interactions between the textual and either acoustic and visual modalities, ignoring capturing the feature interactions between the acoustic and visual modalities. In this paper, we propose the multi-modal end-to-end transformer (ME2ET), which can effectively model the tri-modal features interaction among the textual, acoustic, and visual modalities at the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.09768","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/2209.09768/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":"2026-07-05T04:59:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JSHAj47gNHS01sZz2SEScNZNqCuD2S747ACoyirIBM/oo0zfgfyYfvWeQBroG1r1sXeA9FSCZ+nEMNO64Uw6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:03:47.376232Z"},"content_sha256":"bbb74fe8f115704f422f0df048ae53ffc8b470bf07172d7ec0f9cde9b0def58b","schema_version":"1.0","event_id":"sha256:bbb74fe8f115704f422f0df048ae53ffc8b470bf07172d7ec0f9cde9b0def58b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S6ZQMDW7O3AB3Q2JFBDGGRVWXG/bundle.json","state_url":"https://pith.science/pith/S6ZQMDW7O3AB3Q2JFBDGGRVWXG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S6ZQMDW7O3AB3Q2JFBDGGRVWXG/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":"2026-08-04T20:03:47Z","links":{"resolver":"https://pith.science/pith/S6ZQMDW7O3AB3Q2JFBDGGRVWXG","bundle":"https://pith.science/pith/S6ZQMDW7O3AB3Q2JFBDGGRVWXG/bundle.json","state":"https://pith.science/pith/S6ZQMDW7O3AB3Q2JFBDGGRVWXG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S6ZQMDW7O3AB3Q2JFBDGGRVWXG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:S6ZQMDW7O3AB3Q2JFBDGGRVWXG","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":"50bef5a320e3b4e37271767dabb3ee50a3b3b8cff6bec32c2300c5e2c00fa511","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-20T14:51:38Z","title_canon_sha256":"1865fc78f80d458bbcdbea23de6692492f4954d03c580982fcc92e3d0ad05eec"},"schema_version":"1.0","source":{"id":"2209.09768","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.09768","created_at":"2026-07-05T04:59:34Z"},{"alias_kind":"arxiv_version","alias_value":"2209.09768v1","created_at":"2026-07-05T04:59:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.09768","created_at":"2026-07-05T04:59:34Z"},{"alias_kind":"pith_short_12","alias_value":"S6ZQMDW7O3AB","created_at":"2026-07-05T04:59:34Z"},{"alias_kind":"pith_short_16","alias_value":"S6ZQMDW7O3AB3Q2J","created_at":"2026-07-05T04:59:34Z"},{"alias_kind":"pith_short_8","alias_value":"S6ZQMDW7","created_at":"2026-07-05T04:59:34Z"}],"graph_snapshots":[{"event_id":"sha256:bbb74fe8f115704f422f0df048ae53ffc8b470bf07172d7ec0f9cde9b0def58b","target":"graph","created_at":"2026-07-05T04:59:34Z","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/2209.09768/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent works on multi-modal emotion recognition move towards end-to-end models, which can extract the task-specific features supervised by the target task compared with the two-phase pipeline. However, previous methods only model the feature interactions between the textual and either acoustic and visual modalities, ignoring capturing the feature interactions between the acoustic and visual modalities. In this paper, we propose the multi-modal end-to-end transformer (ME2ET), which can effectively model the tri-modal features interaction among the textual, acoustic, and visual modalities at the","authors_text":"Bing Qin, Pai Peng, Yang Wu, Yanyan Zhao, Zhenyu Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-20T14:51:38Z","title":"An Efficient End-to-End Transformer with Progressive Tri-modal Attention for Multi-modal Emotion Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.09768","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:e2386cc6b709b3fdffe1c28da8817eebe0f60e2499706d7c90333cc55e5a31d5","target":"record","created_at":"2026-07-05T04:59:34Z","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":"50bef5a320e3b4e37271767dabb3ee50a3b3b8cff6bec32c2300c5e2c00fa511","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-20T14:51:38Z","title_canon_sha256":"1865fc78f80d458bbcdbea23de6692492f4954d03c580982fcc92e3d0ad05eec"},"schema_version":"1.0","source":{"id":"2209.09768","kind":"arxiv","version":1}},"canonical_sha256":"97b3060edf76c01dc34928466346b6b99e2984c1aca1d739b07efe4a3a336200","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97b3060edf76c01dc34928466346b6b99e2984c1aca1d739b07efe4a3a336200","first_computed_at":"2026-07-05T04:59:34.154787Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:59:34.154787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pGWLHzTrQRCFftlDzS6HsM310EvRgPqRuti44ZJhGabkui6dTq4731k1djC12IyErplFLdwFgCnaNHXmwAQ6Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:59:34.155190Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.09768","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2386cc6b709b3fdffe1c28da8817eebe0f60e2499706d7c90333cc55e5a31d5","sha256:bbb74fe8f115704f422f0df048ae53ffc8b470bf07172d7ec0f9cde9b0def58b"],"state_sha256":"f25ca3193e285c06c3a95ad83b572ee212c23ed736e92878aad52951b24ef601"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Poi3vBrsdPaXJt6q+J2OfIqrsbX5t3HFbXlv9FD7UwbB372l3FGZTGPLpiZry1Kxj1Mei6xNnksNWHvBtVVDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:03:47.380145Z","bundle_sha256":"5aea5f5c368332b9e16a44fcc3a8e6c46278c74c46a5a8ca4a6b4a1056769fd3"}}