{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HQDMT3T2ARTCBNHPHSVSBNLGBJ","short_pith_number":"pith:HQDMT3T2","canonical_record":{"source":{"id":"2412.00174","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T18:53:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c095c408e6bf4efbb65d7a1183d3a7b5b39bb0248d1e7fa5702dfb974092d229","abstract_canon_sha256":"38bbb799f2984c4f4ecb3be32a707c66b631c89c99f3598bff44345c82aebfc6"},"schema_version":"1.0"},"canonical_sha256":"3c06c9ee7a046620b4ef3cab20b5660a5b496645b93a6acc0a8146a5d93ed67c","source":{"kind":"arxiv","id":"2412.00174","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00174","created_at":"2026-07-05T09:42:37Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00174v1","created_at":"2026-07-05T09:42:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00174","created_at":"2026-07-05T09:42:37Z"},{"alias_kind":"pith_short_12","alias_value":"HQDMT3T2ARTC","created_at":"2026-07-05T09:42:37Z"},{"alias_kind":"pith_short_16","alias_value":"HQDMT3T2ARTCBNHP","created_at":"2026-07-05T09:42:37Z"},{"alias_kind":"pith_short_8","alias_value":"HQDMT3T2","created_at":"2026-07-05T09:42:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HQDMT3T2ARTCBNHPHSVSBNLGBJ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.00174","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T18:53:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c095c408e6bf4efbb65d7a1183d3a7b5b39bb0248d1e7fa5702dfb974092d229","abstract_canon_sha256":"38bbb799f2984c4f4ecb3be32a707c66b631c89c99f3598bff44345c82aebfc6"},"schema_version":"1.0"},"canonical_sha256":"3c06c9ee7a046620b4ef3cab20b5660a5b496645b93a6acc0a8146a5d93ed67c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:37.240477Z","signature_b64":"YUWcxsG84WMjZ1PQ4KxbnxhSu7Jv3iNqJRNJTg8Kx0aIhhs/4NhZIDLXludSYk2ZDZOGfk+Wtw4eaWdvscZkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c06c9ee7a046620b4ef3cab20b5660a5b496645b93a6acc0a8146a5d93ed67c","last_reissued_at":"2026-07-05T09:42:37.239900Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:37.239900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.00174","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":"2026-07-05T09:42:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E8X5UmQYMNFqqhdfB75LtigqbgQSRJ3BwC4nBVt5NvXAz89pVmuHFjP9a9v4Bw/n9iJC1rn21U80lLrYVcMOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:08:22.816599Z"},"content_sha256":"357a7b4eb4add6703ed4c249e707af7cf669c8b1dfa467e612ab916b912ed1d5","schema_version":"1.0","event_id":"sha256:357a7b4eb4add6703ed4c249e707af7cf669c8b1dfa467e612ab916b912ed1d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HQDMT3T2ARTCBNHPHSVSBNLGBJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Huaizhong Zhang, Jianping Jiang, Lei Yang, Tianxiang Ren, Weiye Xiao, Yang Gao, Zhengyu Lin, Zhiqian Lin, Zhongang Cai, Ziwei Liu","submitted_at":"2024-11-29T18:53:40Z","abstract_excerpt":"Human beings are social animals. How to equip 3D autonomous characters with similar social intelligence that can perceive, understand and interact with humans remains an open yet foundamental problem. In this paper, we introduce SOLAMI, the first end-to-end Social vision-Language-Action (VLA) Modeling framework for Immersive interaction with 3D autonomous characters. Specifically, SOLAMI builds 3D autonomous characters from three aspects: (1) Social VLA Architecture: We propose a unified social VLA framework to generate multimodal response (speech and motion) based on the user's multimodal inp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00174","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/2412.00174/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":"2026-07-05T09:42:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZPOf7olZSXtHCrD8Ajsenhm5JxIRlzd89iG6pfFlkIeYBX00tAUxylOGR+ZNc7mngfhpFq+/a6tpMbrC1y7NBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:08:22.817142Z"},"content_sha256":"68de85391201e8fb108e35a6cb69a5b784ebcfef7440b0b94f0e881a85b2050e","schema_version":"1.0","event_id":"sha256:68de85391201e8fb108e35a6cb69a5b784ebcfef7440b0b94f0e881a85b2050e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HQDMT3T2ARTCBNHPHSVSBNLGBJ/bundle.json","state_url":"https://pith.science/pith/HQDMT3T2ARTCBNHPHSVSBNLGBJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HQDMT3T2ARTCBNHPHSVSBNLGBJ/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":"2026-08-09T22:08:22Z","links":{"resolver":"https://pith.science/pith/HQDMT3T2ARTCBNHPHSVSBNLGBJ","bundle":"https://pith.science/pith/HQDMT3T2ARTCBNHPHSVSBNLGBJ/bundle.json","state":"https://pith.science/pith/HQDMT3T2ARTCBNHPHSVSBNLGBJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HQDMT3T2ARTCBNHPHSVSBNLGBJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HQDMT3T2ARTCBNHPHSVSBNLGBJ","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":"38bbb799f2984c4f4ecb3be32a707c66b631c89c99f3598bff44345c82aebfc6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T18:53:40Z","title_canon_sha256":"c095c408e6bf4efbb65d7a1183d3a7b5b39bb0248d1e7fa5702dfb974092d229"},"schema_version":"1.0","source":{"id":"2412.00174","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00174","created_at":"2026-07-05T09:42:37Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00174v1","created_at":"2026-07-05T09:42:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00174","created_at":"2026-07-05T09:42:37Z"},{"alias_kind":"pith_short_12","alias_value":"HQDMT3T2ARTC","created_at":"2026-07-05T09:42:37Z"},{"alias_kind":"pith_short_16","alias_value":"HQDMT3T2ARTCBNHP","created_at":"2026-07-05T09:42:37Z"},{"alias_kind":"pith_short_8","alias_value":"HQDMT3T2","created_at":"2026-07-05T09:42:37Z"}],"graph_snapshots":[{"event_id":"sha256:68de85391201e8fb108e35a6cb69a5b784ebcfef7440b0b94f0e881a85b2050e","target":"graph","created_at":"2026-07-05T09:42:37Z","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/2412.00174/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human beings are social animals. How to equip 3D autonomous characters with similar social intelligence that can perceive, understand and interact with humans remains an open yet foundamental problem. In this paper, we introduce SOLAMI, the first end-to-end Social vision-Language-Action (VLA) Modeling framework for Immersive interaction with 3D autonomous characters. Specifically, SOLAMI builds 3D autonomous characters from three aspects: (1) Social VLA Architecture: We propose a unified social VLA framework to generate multimodal response (speech and motion) based on the user's multimodal inp","authors_text":"Huaizhong Zhang, Jianping Jiang, Lei Yang, Tianxiang Ren, Weiye Xiao, Yang Gao, Zhengyu Lin, Zhiqian Lin, Zhongang Cai, Ziwei Liu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T18:53:40Z","title":"SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00174","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":"sha256:357a7b4eb4add6703ed4c249e707af7cf669c8b1dfa467e612ab916b912ed1d5","target":"record","created_at":"2026-07-05T09:42:37Z","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":"38bbb799f2984c4f4ecb3be32a707c66b631c89c99f3598bff44345c82aebfc6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T18:53:40Z","title_canon_sha256":"c095c408e6bf4efbb65d7a1183d3a7b5b39bb0248d1e7fa5702dfb974092d229"},"schema_version":"1.0","source":{"id":"2412.00174","kind":"arxiv","version":1}},"canonical_sha256":"3c06c9ee7a046620b4ef3cab20b5660a5b496645b93a6acc0a8146a5d93ed67c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c06c9ee7a046620b4ef3cab20b5660a5b496645b93a6acc0a8146a5d93ed67c","first_computed_at":"2026-07-05T09:42:37.239900Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:37.239900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YUWcxsG84WMjZ1PQ4KxbnxhSu7Jv3iNqJRNJTg8Kx0aIhhs/4NhZIDLXludSYk2ZDZOGfk+Wtw4eaWdvscZkCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:37.240477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.00174","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:357a7b4eb4add6703ed4c249e707af7cf669c8b1dfa467e612ab916b912ed1d5","sha256:68de85391201e8fb108e35a6cb69a5b784ebcfef7440b0b94f0e881a85b2050e"],"state_sha256":"3827a23ea2daa8ced8fa5cc037bbf831ec4fc573190384fab354e97ac91d3e63"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5pZJdZxYMbNS335dgJY8iCNbNkgh0jMgvuuLVP2ZPncKk32DM03bcqlG5iDWVz3RX9/O/Hi3A7Qi8k5sUjf2DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:08:22.826153Z","bundle_sha256":"87199b91147158ea5d3c09233c1b0e7fd4f8da25522d78516bfb3c97005d31b2"}}