{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N7ZODER4A23M625LE64VUW7DBS","short_pith_number":"pith:N7ZODER4","schema_version":"1.0","canonical_sha256":"6ff2e1923c06b6cf6bab27b95a5be30c829825c8f3dee8bffe6ab42e62ef73fb","source":{"kind":"arxiv","id":"2501.12255","version":4},"attestation_state":"computed","paper":{"title":"HAC++: Towards 100X Compression of 3D Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianfei Cai, Mehrtash Harandi, Qianyi Wu, Weiyao Lin, Yihang Chen","submitted_at":"2025-01-21T16:23:05Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity. However, the substantial Gaussians and their associated attributes necessitate effective compression techniques. Nevertheless, the sparse and unorganized nature of the point cloud of Gaussians (or anchors in our paper) presents challenges for compression. To achieve a compact size, we propose HAC++, which leverages the relationships between unorganized anchors and a structured hash grid, utilizing their mutual information for context modeling. Additiona"},"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":"2501.12255","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-21T16:23:05Z","cross_cats_sorted":[],"title_canon_sha256":"5a5a6b6e15e4268a71419505b3945bb101b65075ea5e5a72abaf45d6f340cf46","abstract_canon_sha256":"4f9e32dd601b3f0d61a2c0ea9132cb23318f08899604affb7ccaf2207770d8a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:25.454707Z","signature_b64":"OVJI3WPTW+K8/Nu0POWXVPMPhxzTIdzNpc04BI4ZyzkItOiwi6fiee5sPWge+VstvdL4uHlCPaUae0E0pVKRAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ff2e1923c06b6cf6bab27b95a5be30c829825c8f3dee8bffe6ab42e62ef73fb","last_reissued_at":"2026-07-05T10:12:25.454222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:25.454222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HAC++: Towards 100X Compression of 3D Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianfei Cai, Mehrtash Harandi, Qianyi Wu, Weiyao Lin, Yihang Chen","submitted_at":"2025-01-21T16:23:05Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity. However, the substantial Gaussians and their associated attributes necessitate effective compression techniques. Nevertheless, the sparse and unorganized nature of the point cloud of Gaussians (or anchors in our paper) presents challenges for compression. To achieve a compact size, we propose HAC++, which leverages the relationships between unorganized anchors and a structured hash grid, utilizing their mutual information for context modeling. Additiona"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12255","kind":"arxiv","version":4},"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/2501.12255/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":"2501.12255","created_at":"2026-07-05T10:12:25.454279+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12255v4","created_at":"2026-07-05T10:12:25.454279+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12255","created_at":"2026-07-05T10:12:25.454279+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7ZODER4A23M","created_at":"2026-07-05T10:12:25.454279+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7ZODER4A23M625L","created_at":"2026-07-05T10:12:25.454279+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7ZODER4","created_at":"2026-07-05T10:12:25.454279+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26880","citing_title":"GScomp-QA: A Subjective Dataset for Quality Assessment of Compressed Gaussian Splatting","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30017","citing_title":"Monte Carlo Energy Aggregation for Mobile 3D Gaussian Splatting","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2601.14821","citing_title":"POTR: Post-Training 3DGS Compression","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26799","citing_title":"MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09279","citing_title":"CAGS: Color-Adaptive Volumetric Video Streaming with Dynamic 3D Gaussian Splatting","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26799","citing_title":"MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02086","citing_title":"GETA-3DGS: Automatic Joint Structured Pruning and Quantization for 3D Gaussian Splatting","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N7ZODER4A23M625LE64VUW7DBS","json":"https://pith.science/pith/N7ZODER4A23M625LE64VUW7DBS.json","graph_json":"https://pith.science/api/pith-number/N7ZODER4A23M625LE64VUW7DBS/graph.json","events_json":"https://pith.science/api/pith-number/N7ZODER4A23M625LE64VUW7DBS/events.json","paper":"https://pith.science/paper/N7ZODER4"},"agent_actions":{"view_html":"https://pith.science/pith/N7ZODER4A23M625LE64VUW7DBS","download_json":"https://pith.science/pith/N7ZODER4A23M625LE64VUW7DBS.json","view_paper":"https://pith.science/paper/N7ZODER4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12255&json=true","fetch_graph":"https://pith.science/api/pith-number/N7ZODER4A23M625LE64VUW7DBS/graph.json","fetch_events":"https://pith.science/api/pith-number/N7ZODER4A23M625LE64VUW7DBS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7ZODER4A23M625LE64VUW7DBS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7ZODER4A23M625LE64VUW7DBS/action/storage_attestation","attest_author":"https://pith.science/pith/N7ZODER4A23M625LE64VUW7DBS/action/author_attestation","sign_citation":"https://pith.science/pith/N7ZODER4A23M625LE64VUW7DBS/action/citation_signature","submit_replication":"https://pith.science/pith/N7ZODER4A23M625LE64VUW7DBS/action/replication_record"}},"created_at":"2026-07-05T10:12:25.454279+00:00","updated_at":"2026-07-05T10:12:25.454279+00:00"}