{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:A66RZ2TCA5ER6VFTIF72EWEDPR","short_pith_number":"pith:A66RZ2TC","canonical_record":{"source":{"id":"2509.02466","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T16:20:20Z","cross_cats_sorted":[],"title_canon_sha256":"99b8a4a61d4aca2b99e2ebc7efacb0dbdb5ca1f0258e7d7781bd5f677e615614","abstract_canon_sha256":"d3f2ff90bd846e35a730bb744056f61eb9db3fca89949f3b2558548c2a48ec42"},"schema_version":"1.0"},"canonical_sha256":"07bd1cea6207491f54b3417fa258837c74e6d384617fb9fecdb78d2cdf783189","source":{"kind":"arxiv","id":"2509.02466","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02466","created_at":"2026-07-05T12:04:19Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02466v1","created_at":"2026-07-05T12:04:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02466","created_at":"2026-07-05T12:04:19Z"},{"alias_kind":"pith_short_12","alias_value":"A66RZ2TCA5ER","created_at":"2026-07-05T12:04:19Z"},{"alias_kind":"pith_short_16","alias_value":"A66RZ2TCA5ER6VFT","created_at":"2026-07-05T12:04:19Z"},{"alias_kind":"pith_short_8","alias_value":"A66RZ2TC","created_at":"2026-07-05T12:04:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:A66RZ2TCA5ER6VFTIF72EWEDPR","target":"record","payload":{"canonical_record":{"source":{"id":"2509.02466","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T16:20:20Z","cross_cats_sorted":[],"title_canon_sha256":"99b8a4a61d4aca2b99e2ebc7efacb0dbdb5ca1f0258e7d7781bd5f677e615614","abstract_canon_sha256":"d3f2ff90bd846e35a730bb744056f61eb9db3fca89949f3b2558548c2a48ec42"},"schema_version":"1.0"},"canonical_sha256":"07bd1cea6207491f54b3417fa258837c74e6d384617fb9fecdb78d2cdf783189","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:19.302027Z","signature_b64":"+jh1264DNatFVUNHYu+BS5MnmloABQCsFl//GeWh6uuzSXWFGVxfEUOZirNf6fT6s+XAYTaDUQA07qlREiXbCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07bd1cea6207491f54b3417fa258837c74e6d384617fb9fecdb78d2cdf783189","last_reissued_at":"2026-07-05T12:04:19.301529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:19.301529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.02466","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":"2026-07-05T12:04:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NdMaF7sW75yGlieKA+mVsghcWV6OuNpnhJJ66Is2zP5RKAbLUnmmrX94XOSACV42q8dP95XwR5qCDiVNHFeXBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:35:50.440475Z"},"content_sha256":"74748574e3e3c7ed9ba13890009ba409901b44c4a44997149088f66293d3f9b7","schema_version":"1.0","event_id":"sha256:74748574e3e3c7ed9ba13890009ba409901b44c4a44997149088f66293d3f9b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:A66RZ2TCA5ER6VFTIF72EWEDPR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TeRA: Rethinking Text-guided Realistic 3D Avatar Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Zhu, Jiawei Zhang, Li Wang, Xinxin Zuo, Xun Cao, Yanwen Wang, Yifei Zeng, Yiyu Zhuang","submitted_at":"2025-09-02T16:20:20Z","abstract_excerpt":"In this paper, we rethink text-to-avatar generative models by proposing TeRA, a more efficient and effective framework than the previous SDS-based models and general large 3D generative models. Our approach employs a two-stage training strategy for learning a native 3D avatar generative model. Initially, we distill a decoder to derive a structured latent space from a large human reconstruction model. Subsequently, a text-controlled latent diffusion model is trained to generate photorealistic 3D human avatars within this latent space. TeRA enhances the model performance by eliminating slow iter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02466","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/2509.02466/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":"2026-07-05T12:04:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NCkXLa7t0/+z3MW+tF7/wwYN9nKwsUcgBQ1qVTGFoDkZtlLvDmXXL1CJ/06WuZTeK8yKWOaFVRVEHEUc6yNDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:35:50.441021Z"},"content_sha256":"11f3aa39e22a65a13d57a5614cd271d3e81b56e0a08f0e3ac1011e39c1d695b9","schema_version":"1.0","event_id":"sha256:11f3aa39e22a65a13d57a5614cd271d3e81b56e0a08f0e3ac1011e39c1d695b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A66RZ2TCA5ER6VFTIF72EWEDPR/bundle.json","state_url":"https://pith.science/pith/A66RZ2TCA5ER6VFTIF72EWEDPR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A66RZ2TCA5ER6VFTIF72EWEDPR/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":"2026-08-06T02:35:50Z","links":{"resolver":"https://pith.science/pith/A66RZ2TCA5ER6VFTIF72EWEDPR","bundle":"https://pith.science/pith/A66RZ2TCA5ER6VFTIF72EWEDPR/bundle.json","state":"https://pith.science/pith/A66RZ2TCA5ER6VFTIF72EWEDPR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A66RZ2TCA5ER6VFTIF72EWEDPR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:A66RZ2TCA5ER6VFTIF72EWEDPR","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":"d3f2ff90bd846e35a730bb744056f61eb9db3fca89949f3b2558548c2a48ec42","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T16:20:20Z","title_canon_sha256":"99b8a4a61d4aca2b99e2ebc7efacb0dbdb5ca1f0258e7d7781bd5f677e615614"},"schema_version":"1.0","source":{"id":"2509.02466","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02466","created_at":"2026-07-05T12:04:19Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02466v1","created_at":"2026-07-05T12:04:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02466","created_at":"2026-07-05T12:04:19Z"},{"alias_kind":"pith_short_12","alias_value":"A66RZ2TCA5ER","created_at":"2026-07-05T12:04:19Z"},{"alias_kind":"pith_short_16","alias_value":"A66RZ2TCA5ER6VFT","created_at":"2026-07-05T12:04:19Z"},{"alias_kind":"pith_short_8","alias_value":"A66RZ2TC","created_at":"2026-07-05T12:04:19Z"}],"graph_snapshots":[{"event_id":"sha256:11f3aa39e22a65a13d57a5614cd271d3e81b56e0a08f0e3ac1011e39c1d695b9","target":"graph","created_at":"2026-07-05T12:04:19Z","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/2509.02466/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we rethink text-to-avatar generative models by proposing TeRA, a more efficient and effective framework than the previous SDS-based models and general large 3D generative models. Our approach employs a two-stage training strategy for learning a native 3D avatar generative model. Initially, we distill a decoder to derive a structured latent space from a large human reconstruction model. Subsequently, a text-controlled latent diffusion model is trained to generate photorealistic 3D human avatars within this latent space. TeRA enhances the model performance by eliminating slow iter","authors_text":"Hao Zhu, Jiawei Zhang, Li Wang, Xinxin Zuo, Xun Cao, Yanwen Wang, Yifei Zeng, Yiyu Zhuang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T16:20:20Z","title":"TeRA: Rethinking Text-guided Realistic 3D Avatar Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02466","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":"sha256:74748574e3e3c7ed9ba13890009ba409901b44c4a44997149088f66293d3f9b7","target":"record","created_at":"2026-07-05T12:04:19Z","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":"d3f2ff90bd846e35a730bb744056f61eb9db3fca89949f3b2558548c2a48ec42","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T16:20:20Z","title_canon_sha256":"99b8a4a61d4aca2b99e2ebc7efacb0dbdb5ca1f0258e7d7781bd5f677e615614"},"schema_version":"1.0","source":{"id":"2509.02466","kind":"arxiv","version":1}},"canonical_sha256":"07bd1cea6207491f54b3417fa258837c74e6d384617fb9fecdb78d2cdf783189","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07bd1cea6207491f54b3417fa258837c74e6d384617fb9fecdb78d2cdf783189","first_computed_at":"2026-07-05T12:04:19.301529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:19.301529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+jh1264DNatFVUNHYu+BS5MnmloABQCsFl//GeWh6uuzSXWFGVxfEUOZirNf6fT6s+XAYTaDUQA07qlREiXbCA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:19.302027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02466","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74748574e3e3c7ed9ba13890009ba409901b44c4a44997149088f66293d3f9b7","sha256:11f3aa39e22a65a13d57a5614cd271d3e81b56e0a08f0e3ac1011e39c1d695b9"],"state_sha256":"ed877c7fe977caad5aff9c7af0087b9713b9ddbf20654a6761549bd0554b6dea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9xR+3wctqyf1O7nl7jZPiFO6q5/+F7FjQb9UX6eZZIsJO73GtOCRvdSKwL7rxWFS662uttQRDPAv/76uF8h5Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:35:50.444794Z","bundle_sha256":"f49d028e4d0af3fb9c89cd9a111c8f34e274cf6b015253593f27e9c061fa48f9"}}