{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OLSHSZXQDNU5KMFJSKCFQA26WU","short_pith_number":"pith:OLSHSZXQ","schema_version":"1.0","canonical_sha256":"72e47966f01b69d530a9928458035eb506d34c066da858e6ba1832c2dd8d09a1","source":{"kind":"arxiv","id":"2607.11500","version":1},"attestation_state":"computed","paper":{"title":"HyperGS: Fast and Generalizable Gaussian Video Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernard Ghanem, Chen Zhao, Fatimah Zohra, Shuming Liu, Yahya Al Malallah","submitted_at":"2026-07-13T12:53:02Z","abstract_excerpt":"Gaussian Splatting has emerged as an effective representation for video, but existing methods rely on per-video optimization. This leads to slow encoding and limits generalization across videos. To amortize this optimization, we propose HyperGS, a feedforward, optimization-free approach that directly predicts Gaussian representations from any video in a single forward pass, speeding up encoding and decoding by orders of magnitude while generalizing to out-of-distribution videos at higher resolutions. In HyperGS, we design a factorized spatiotemporal Transformer to extract tokens from video, an"},"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":"2607.11500","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-13T12:53:02Z","cross_cats_sorted":[],"title_canon_sha256":"b4e6d9dafe3ac427a25aa61d0c9aa6d1c5683b4bcc7aa98584f73ece01b6401a","abstract_canon_sha256":"f7428ef9e06c71044856dc0246b13e6e44603f4321cb04e2ac62c7d2ea644832"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T02:22:07.305772Z","signature_b64":"y4oZOK2/F1gr3W9i5YWDSyvvZjy6l93d5qwQz1+DE0sthSPWEbHhG2bA6CNFImEAmsskwKbWU7RXjEw3D4nTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72e47966f01b69d530a9928458035eb506d34c066da858e6ba1832c2dd8d09a1","last_reissued_at":"2026-07-14T02:22:07.304948Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T02:22:07.304948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HyperGS: Fast and Generalizable Gaussian Video Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernard Ghanem, Chen Zhao, Fatimah Zohra, Shuming Liu, Yahya Al Malallah","submitted_at":"2026-07-13T12:53:02Z","abstract_excerpt":"Gaussian Splatting has emerged as an effective representation for video, but existing methods rely on per-video optimization. This leads to slow encoding and limits generalization across videos. To amortize this optimization, we propose HyperGS, a feedforward, optimization-free approach that directly predicts Gaussian representations from any video in a single forward pass, speeding up encoding and decoding by orders of magnitude while generalizing to out-of-distribution videos at higher resolutions. In HyperGS, we design a factorized spatiotemporal Transformer to extract tokens from video, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11500","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/2607.11500/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":"2607.11500","created_at":"2026-07-14T02:22:07.305364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.11500v1","created_at":"2026-07-14T02:22:07.305364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11500","created_at":"2026-07-14T02:22:07.305364+00:00"},{"alias_kind":"pith_short_12","alias_value":"OLSHSZXQDNU5","created_at":"2026-07-14T02:22:07.305364+00:00"},{"alias_kind":"pith_short_16","alias_value":"OLSHSZXQDNU5KMFJ","created_at":"2026-07-14T02:22:07.305364+00:00"},{"alias_kind":"pith_short_8","alias_value":"OLSHSZXQ","created_at":"2026-07-14T02:22:07.305364+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OLSHSZXQDNU5KMFJSKCFQA26WU","json":"https://pith.science/pith/OLSHSZXQDNU5KMFJSKCFQA26WU.json","graph_json":"https://pith.science/api/pith-number/OLSHSZXQDNU5KMFJSKCFQA26WU/graph.json","events_json":"https://pith.science/api/pith-number/OLSHSZXQDNU5KMFJSKCFQA26WU/events.json","paper":"https://pith.science/paper/OLSHSZXQ"},"agent_actions":{"view_html":"https://pith.science/pith/OLSHSZXQDNU5KMFJSKCFQA26WU","download_json":"https://pith.science/pith/OLSHSZXQDNU5KMFJSKCFQA26WU.json","view_paper":"https://pith.science/paper/OLSHSZXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.11500&json=true","fetch_graph":"https://pith.science/api/pith-number/OLSHSZXQDNU5KMFJSKCFQA26WU/graph.json","fetch_events":"https://pith.science/api/pith-number/OLSHSZXQDNU5KMFJSKCFQA26WU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OLSHSZXQDNU5KMFJSKCFQA26WU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OLSHSZXQDNU5KMFJSKCFQA26WU/action/storage_attestation","attest_author":"https://pith.science/pith/OLSHSZXQDNU5KMFJSKCFQA26WU/action/author_attestation","sign_citation":"https://pith.science/pith/OLSHSZXQDNU5KMFJSKCFQA26WU/action/citation_signature","submit_replication":"https://pith.science/pith/OLSHSZXQDNU5KMFJSKCFQA26WU/action/replication_record"}},"created_at":"2026-07-14T02:22:07.305364+00:00","updated_at":"2026-07-14T02:22:07.305364+00:00"}