{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3XCKCX75YHLNQEDAYBBQVC257V","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":"c6e6280b3afd06a7bfc97586dca381463660936d93e2ff124c2a005c7bf0e8c3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T09:14:05Z","title_canon_sha256":"4919499c3f803d4a011e7a86b24d5f340a0b04254d5e5ba8747c788cf0127e1c"},"schema_version":"1.0","source":{"id":"2605.10239","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10239","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10239v2","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10239","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"3XCKCX75YHLN","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"3XCKCX75YHLNQEDA","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"3XCKCX75","created_at":"2026-05-20T00:04:35Z"}],"graph_snapshots":[{"event_id":"sha256:034866d7dea0466b21c354d85e6ca392834d1ed3a557c182f75523aad158123c","target":"graph","created_at":"2026-05-20T00:04:35Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"introducing a single adapter of only 1.5M parameters into the generic architecture is sufficient to achieve superior performance."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That high-frequency structural priors extracted from shallow features of a vision foundation model backbone can be seamlessly integrated to compensate for low-pass filtering without requiring additional domain-specific fine-tuning or larger training data."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"AdaptSplat adds a lightweight Frequency-Preserving Adapter to vision foundation models that extracts direction-aware high-frequency priors and integrates them via positional encodings and residual modulation to improve feed-forward 3D Gaussian Splatting fidelity and cross-domain performance."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A single 1.5-million-parameter adapter added to vision foundation models enables superior feed-forward 3D Gaussian Splatting."}],"snapshot_sha256":"348351d973d84d6400925f37a7e9e5609f38d2d0a5204f2abf720f68d64c6cb8"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"69d6a262322efcbca748cfad2839f293b00834daccc562f6830a5271ece9d9d8"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T15:38:03.960704Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T11:31:19.712732Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T09:33:05.558837Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.10239/integrity.json","findings":[],"snapshot_sha256":"40fd28a32eb7a970c5ebf75602105a00cd1a317ebfbd9154fd03898a50ad6555","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work explores a simple yet powerful lightweight adapter design for feed-forward 3D Gaussian Splatting (3DGS). Existing methods typically apply complex, architecture-specific designs on top of the generic pipeline of image feature extraction $\\rightarrow$ multi-view interaction $\\rightarrow$ feature decoding. However, constrained by the scale bottleneck of 3D training data and the low-pass filtering effect of deep networks, these methods still fall short in cross-domain generalization and high-frequency geometric fidelity. To address these problems, we propose AdaptSplat, which demonstrate","authors_text":"Mingwei Xing, Xinliang Wang, Yifeng Shi","cross_cats":[],"headline":"A single 1.5-million-parameter adapter added to vision foundation models enables superior feed-forward 3D Gaussian Splatting.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T09:14:05Z","title":"AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.10239","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T03:25:46.238373Z","id":"8c551969-000e-4cf4-a58b-7df4ea1dbbc9","model_set":{"reader":"grok-4.3"},"one_line_summary":"AdaptSplat adds a lightweight Frequency-Preserving Adapter to vision foundation models that extracts direction-aware high-frequency priors and integrates them via positional encodings and residual modulation to improve feed-forward 3D Gaussian Splatting fidelity and cross-domain performance.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A single 1.5-million-parameter adapter added to vision foundation models enables superior feed-forward 3D Gaussian Splatting.","strongest_claim":"introducing a single adapter of only 1.5M parameters into the generic architecture is sufficient to achieve superior performance.","weakest_assumption":"That high-frequency structural priors extracted from shallow features of a vision foundation model backbone can be seamlessly integrated to compensate for low-pass filtering without requiring additional domain-specific fine-tuning or larger training data."}},"verdict_id":"8c551969-000e-4cf4-a58b-7df4ea1dbbc9"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bb7d317102e6199f93e96b2d980b3f087bda526b1a1cd07bdf9b14ba1bdd2e16","target":"record","created_at":"2026-05-20T00:04:35Z","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":"c6e6280b3afd06a7bfc97586dca381463660936d93e2ff124c2a005c7bf0e8c3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T09:14:05Z","title_canon_sha256":"4919499c3f803d4a011e7a86b24d5f340a0b04254d5e5ba8747c788cf0127e1c"},"schema_version":"1.0","source":{"id":"2605.10239","kind":"arxiv","version":2}},"canonical_sha256":"ddc4a15ffdc1d6d81060c0430a8b5dfd51e1390c5a5d3764c8717067bfb4f021","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddc4a15ffdc1d6d81060c0430a8b5dfd51e1390c5a5d3764c8717067bfb4f021","first_computed_at":"2026-05-20T00:04:35.718146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:35.718146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HqwS43GnbMlutqtqdEWc2ufe0DvNSU3K0dWF2MkjCHWVqP/59fiz8d3PbgnsHqTVMBNohe5jHxDJGuX65dBcCw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:35.719046Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.10239","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb7d317102e6199f93e96b2d980b3f087bda526b1a1cd07bdf9b14ba1bdd2e16","sha256:034866d7dea0466b21c354d85e6ca392834d1ed3a557c182f75523aad158123c"],"state_sha256":"c757b6a64edabc1701f66c87e55ad83e35f35cff0c86b7ade8208c65397ac585"}