{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GHJ6VYBT2UK6MPTJBU7CUQIHZG","short_pith_number":"pith:GHJ6VYBT","canonical_record":{"source":{"id":"2506.00958","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-01T11:07:25Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"d825b4913867eb4e3d6084fb3696119bf153f47b70855d07b59234f284ba146f","abstract_canon_sha256":"a9992b22cf6cc8a9538e17181f2db2975f85562a1cb1220463f8be4e5ad95228"},"schema_version":"1.0"},"canonical_sha256":"31d3eae033d515e63e690d3e2a4107c9af0d5ce53f9e66a6118cd9b33e04dc94","source":{"kind":"arxiv","id":"2506.00958","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00958","created_at":"2026-07-05T11:13:43Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00958v1","created_at":"2026-07-05T11:13:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00958","created_at":"2026-07-05T11:13:43Z"},{"alias_kind":"pith_short_12","alias_value":"GHJ6VYBT2UK6","created_at":"2026-07-05T11:13:43Z"},{"alias_kind":"pith_short_16","alias_value":"GHJ6VYBT2UK6MPTJ","created_at":"2026-07-05T11:13:43Z"},{"alias_kind":"pith_short_8","alias_value":"GHJ6VYBT","created_at":"2026-07-05T11:13:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GHJ6VYBT2UK6MPTJBU7CUQIHZG","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00958","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-01T11:07:25Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"d825b4913867eb4e3d6084fb3696119bf153f47b70855d07b59234f284ba146f","abstract_canon_sha256":"a9992b22cf6cc8a9538e17181f2db2975f85562a1cb1220463f8be4e5ad95228"},"schema_version":"1.0"},"canonical_sha256":"31d3eae033d515e63e690d3e2a4107c9af0d5ce53f9e66a6118cd9b33e04dc94","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:43.547633Z","signature_b64":"mtzyHpuEWsibTpSk9/ULlk/ACmdylVCntTRJfHH32dh8rnTca/thmx1ukREhW+sGoBTM+Tbn+YKxaRojuyppCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31d3eae033d515e63e690d3e2a4107c9af0d5ce53f9e66a6118cd9b33e04dc94","last_reissued_at":"2026-07-05T11:13:43.547220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:43.547220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00958","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":"2026-07-05T11:13:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"whn2GDP8luz98ypE3xXLvbFzBc50tZ5MsWMjeiREMvXApGqdjJ5xESeXQCGO9YXpGWF1DJ0hxR6iA6s45MQ9DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T13:03:59.369659Z"},"content_sha256":"70b1e9ab1cf622044e7e077cddc46b0157ea6b2601723a527b401893693e5b4d","schema_version":"1.0","event_id":"sha256:70b1e9ab1cf622044e7e077cddc46b0157ea6b2601723a527b401893693e5b4d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GHJ6VYBT2UK6MPTJBU7CUQIHZG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Cheoljong Yang, Jisoo Kim, Jiwan Chung, Junhyeok Kim, Sangkyu Lee, Sunghyun Lee, Youngjae Yu, Youngmin Kim","submitted_at":"2025-06-01T11:07:25Z","abstract_excerpt":"Nonverbal communication is integral to human interaction, with gestures, facial expressions, and body language conveying critical aspects of intent and emotion. However, existing large language models (LLMs) fail to effectively incorporate these nonverbal elements, limiting their capacity to create fully immersive conversational experiences. We introduce MARS, a multimodal language model designed to understand and generate nonverbal cues alongside text, bridging this gap in conversational AI. Our key innovation is VENUS, a large-scale dataset comprising annotated videos with time-aligned text,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00958","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/2506.00958/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":"2026-07-05T11:13:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kCJI4BbIXVykBo1vfshl05iCCOmB3TzeC1bx1SjUtXM3mYWjbFSVgAHOR+yNuWeDLIW7czblBzrvkf/BPzZJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T13:03:59.370172Z"},"content_sha256":"069e1129348c25089901cb4bf0efc46f347afeb9a9a0d37f1b504cdb85493a32","schema_version":"1.0","event_id":"sha256:069e1129348c25089901cb4bf0efc46f347afeb9a9a0d37f1b504cdb85493a32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GHJ6VYBT2UK6MPTJBU7CUQIHZG/bundle.json","state_url":"https://pith.science/pith/GHJ6VYBT2UK6MPTJBU7CUQIHZG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GHJ6VYBT2UK6MPTJBU7CUQIHZG/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":"2026-08-22T13:03:59Z","links":{"resolver":"https://pith.science/pith/GHJ6VYBT2UK6MPTJBU7CUQIHZG","bundle":"https://pith.science/pith/GHJ6VYBT2UK6MPTJBU7CUQIHZG/bundle.json","state":"https://pith.science/pith/GHJ6VYBT2UK6MPTJBU7CUQIHZG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GHJ6VYBT2UK6MPTJBU7CUQIHZG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GHJ6VYBT2UK6MPTJBU7CUQIHZG","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":"a9992b22cf6cc8a9538e17181f2db2975f85562a1cb1220463f8be4e5ad95228","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-01T11:07:25Z","title_canon_sha256":"d825b4913867eb4e3d6084fb3696119bf153f47b70855d07b59234f284ba146f"},"schema_version":"1.0","source":{"id":"2506.00958","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00958","created_at":"2026-07-05T11:13:43Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00958v1","created_at":"2026-07-05T11:13:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00958","created_at":"2026-07-05T11:13:43Z"},{"alias_kind":"pith_short_12","alias_value":"GHJ6VYBT2UK6","created_at":"2026-07-05T11:13:43Z"},{"alias_kind":"pith_short_16","alias_value":"GHJ6VYBT2UK6MPTJ","created_at":"2026-07-05T11:13:43Z"},{"alias_kind":"pith_short_8","alias_value":"GHJ6VYBT","created_at":"2026-07-05T11:13:43Z"}],"graph_snapshots":[{"event_id":"sha256:069e1129348c25089901cb4bf0efc46f347afeb9a9a0d37f1b504cdb85493a32","target":"graph","created_at":"2026-07-05T11:13:43Z","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/2506.00958/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Nonverbal communication is integral to human interaction, with gestures, facial expressions, and body language conveying critical aspects of intent and emotion. However, existing large language models (LLMs) fail to effectively incorporate these nonverbal elements, limiting their capacity to create fully immersive conversational experiences. We introduce MARS, a multimodal language model designed to understand and generate nonverbal cues alongside text, bridging this gap in conversational AI. Our key innovation is VENUS, a large-scale dataset comprising annotated videos with time-aligned text,","authors_text":"Cheoljong Yang, Jisoo Kim, Jiwan Chung, Junhyeok Kim, Sangkyu Lee, Sunghyun Lee, Youngjae Yu, Youngmin Kim","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-01T11:07:25Z","title":"Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00958","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":"sha256:70b1e9ab1cf622044e7e077cddc46b0157ea6b2601723a527b401893693e5b4d","target":"record","created_at":"2026-07-05T11:13:43Z","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":"a9992b22cf6cc8a9538e17181f2db2975f85562a1cb1220463f8be4e5ad95228","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-01T11:07:25Z","title_canon_sha256":"d825b4913867eb4e3d6084fb3696119bf153f47b70855d07b59234f284ba146f"},"schema_version":"1.0","source":{"id":"2506.00958","kind":"arxiv","version":1}},"canonical_sha256":"31d3eae033d515e63e690d3e2a4107c9af0d5ce53f9e66a6118cd9b33e04dc94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31d3eae033d515e63e690d3e2a4107c9af0d5ce53f9e66a6118cd9b33e04dc94","first_computed_at":"2026-07-05T11:13:43.547220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:43.547220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mtzyHpuEWsibTpSk9/ULlk/ACmdylVCntTRJfHH32dh8rnTca/thmx1ukREhW+sGoBTM+Tbn+YKxaRojuyppCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:43.547633Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00958","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70b1e9ab1cf622044e7e077cddc46b0157ea6b2601723a527b401893693e5b4d","sha256:069e1129348c25089901cb4bf0efc46f347afeb9a9a0d37f1b504cdb85493a32"],"state_sha256":"424a28d4afe0b92374ee3c187d9cb1f84e56d5d640ef67586823d60e65ac1194"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S2+oNMym67sdAaZ2eF0FngnvEXjdZWyhk3lEzaVel2s5hDvUgtpzmxH5wfpZX0Jk+Jx+O7UbaQ+wYaMdi1NRAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T13:03:59.373847Z","bundle_sha256":"fef4c05b6dcfd5ad99872aa42d43c6a5699d25f3f578abbb713140ddf8915d5b"}}