{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HWPU3CDTUIPFQYCHOFPL3OG32S","short_pith_number":"pith:HWPU3CDT","schema_version":"1.0","canonical_sha256":"3d9f4d8873a21e586047715ebdb8dbd48ec7ab1df54092ae6efc576c2a6f3438","source":{"kind":"arxiv","id":"2508.16917","version":1},"attestation_state":"computed","paper":{"title":"Structural Energy-Guided Sampling for View-Consistent Text-to-3D","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Hong, Jinguang Tong, Jing Zhang, Qing Zhang, Xuesong Li","submitted_at":"2025-08-23T06:26:04Z","abstract_excerpt":"Text-to-3D generation often suffers from the Janus problem, where objects look correct from the front but collapse into duplicated or distorted geometry from other angles. We attribute this failure to viewpoint bias in 2D diffusion priors, which propagates into 3D optimization. To address this, we propose Structural Energy-Guided Sampling (SEGS), a training-free, plug-and-play framework that enforces multi-view consistency entirely at sampling time. SEGS defines a structural energy in a PCA subspace of intermediate U-Net features and injects its gradients into the denoising trajectory, steerin"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.16917","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-23T06:26:04Z","cross_cats_sorted":[],"title_canon_sha256":"99022b3c671fd3ff795b99d640164ac1097d0d1256a8c0f749814c3592bbfe7e","abstract_canon_sha256":"1472887eaf348602465584fe89987f35ce602cbf54a25d6eb3fd09813a3f01fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:06.388852Z","signature_b64":"gwHCiggrWINRzsELONijk0HyDaiBuzekJPAaHQo27mihmAWIV2h5IrDGUlAhz6XOV+PmSAEqTGJscPl+URcWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d9f4d8873a21e586047715ebdb8dbd48ec7ab1df54092ae6efc576c2a6f3438","last_reissued_at":"2026-07-05T11:58:06.388413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:06.388413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structural Energy-Guided Sampling for View-Consistent Text-to-3D","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Hong, Jinguang Tong, Jing Zhang, Qing Zhang, Xuesong Li","submitted_at":"2025-08-23T06:26:04Z","abstract_excerpt":"Text-to-3D generation often suffers from the Janus problem, where objects look correct from the front but collapse into duplicated or distorted geometry from other angles. We attribute this failure to viewpoint bias in 2D diffusion priors, which propagates into 3D optimization. To address this, we propose Structural Energy-Guided Sampling (SEGS), a training-free, plug-and-play framework that enforces multi-view consistency entirely at sampling time. SEGS defines a structural energy in a PCA subspace of intermediate U-Net features and injects its gradients into the denoising trajectory, steerin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16917","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/2508.16917/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.16917","created_at":"2026-07-05T11:58:06.388471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.16917v1","created_at":"2026-07-05T11:58:06.388471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16917","created_at":"2026-07-05T11:58:06.388471+00:00"},{"alias_kind":"pith_short_12","alias_value":"HWPU3CDTUIPF","created_at":"2026-07-05T11:58:06.388471+00:00"},{"alias_kind":"pith_short_16","alias_value":"HWPU3CDTUIPFQYCH","created_at":"2026-07-05T11:58:06.388471+00:00"},{"alias_kind":"pith_short_8","alias_value":"HWPU3CDT","created_at":"2026-07-05T11:58:06.388471+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20872","citing_title":"CAdam: Context-Adaptive Moment Estimation for 3D Gaussian Densification in Generative Distillation","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HWPU3CDTUIPFQYCHOFPL3OG32S","json":"https://pith.science/pith/HWPU3CDTUIPFQYCHOFPL3OG32S.json","graph_json":"https://pith.science/api/pith-number/HWPU3CDTUIPFQYCHOFPL3OG32S/graph.json","events_json":"https://pith.science/api/pith-number/HWPU3CDTUIPFQYCHOFPL3OG32S/events.json","paper":"https://pith.science/paper/HWPU3CDT"},"agent_actions":{"view_html":"https://pith.science/pith/HWPU3CDTUIPFQYCHOFPL3OG32S","download_json":"https://pith.science/pith/HWPU3CDTUIPFQYCHOFPL3OG32S.json","view_paper":"https://pith.science/paper/HWPU3CDT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.16917&json=true","fetch_graph":"https://pith.science/api/pith-number/HWPU3CDTUIPFQYCHOFPL3OG32S/graph.json","fetch_events":"https://pith.science/api/pith-number/HWPU3CDTUIPFQYCHOFPL3OG32S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HWPU3CDTUIPFQYCHOFPL3OG32S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HWPU3CDTUIPFQYCHOFPL3OG32S/action/storage_attestation","attest_author":"https://pith.science/pith/HWPU3CDTUIPFQYCHOFPL3OG32S/action/author_attestation","sign_citation":"https://pith.science/pith/HWPU3CDTUIPFQYCHOFPL3OG32S/action/citation_signature","submit_replication":"https://pith.science/pith/HWPU3CDTUIPFQYCHOFPL3OG32S/action/replication_record"}},"created_at":"2026-07-05T11:58:06.388471+00:00","updated_at":"2026-07-05T11:58:06.388471+00:00"}