{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T22753O62YY4OTNJLCNUDPI7O5","short_pith_number":"pith:T22753O6","schema_version":"1.0","canonical_sha256":"9eb5feedded631c74da9589b41bd1f7742a89ab871c1004a6fa454d413a5fc1d","source":{"kind":"arxiv","id":"2412.17184","version":1},"attestation_state":"computed","paper":{"title":"Foundation Model for Lossy Compression of Spatiotemporal Scientific Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anand Rangarajan, Jaemoon Lee, Sanjay Ranka, Xiao Li","submitted_at":"2024-12-22T22:57:08Z","abstract_excerpt":"We present a foundation model (FM) for lossy scientific data compression, combining a variational autoencoder (VAE) with a hyper-prior structure and a super-resolution (SR) module. The VAE framework uses hyper-priors to model latent space dependencies, enhancing compression efficiency. The SR module refines low-resolution representations into high-resolution outputs, improving reconstruction quality. By alternating between 2D and 3D convolutions, the model efficiently captures spatiotemporal correlations in scientific data while maintaining low computational cost. Experimental results demonstr"},"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":"2412.17184","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-22T22:57:08Z","cross_cats_sorted":[],"title_canon_sha256":"3fcf354b570aa9bcbd77817c28b2d14c87689bb2364a2a82423e6845efc81541","abstract_canon_sha256":"93ccc6d6f943ffc9bcc88230fe7a7f585434980b0851cbc101d77ae79c193ffc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:18.605640Z","signature_b64":"oIshaJ9fgn61vfYuZ0U59RRJ0/Ef4U61w4XI3kZvEEpEG9QR0wy54hua7mCj15Rpp9c7+nqnF/mZY9oKzIUHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9eb5feedded631c74da9589b41bd1f7742a89ab871c1004a6fa454d413a5fc1d","last_reissued_at":"2026-07-05T09:53:18.605198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:18.605198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Foundation Model for Lossy Compression of Spatiotemporal Scientific Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anand Rangarajan, Jaemoon Lee, Sanjay Ranka, Xiao Li","submitted_at":"2024-12-22T22:57:08Z","abstract_excerpt":"We present a foundation model (FM) for lossy scientific data compression, combining a variational autoencoder (VAE) with a hyper-prior structure and a super-resolution (SR) module. The VAE framework uses hyper-priors to model latent space dependencies, enhancing compression efficiency. The SR module refines low-resolution representations into high-resolution outputs, improving reconstruction quality. By alternating between 2D and 3D convolutions, the model efficiently captures spatiotemporal correlations in scientific data while maintaining low computational cost. Experimental results demonstr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17184","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/2412.17184/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":"2412.17184","created_at":"2026-07-05T09:53:18.605256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17184v1","created_at":"2026-07-05T09:53:18.605256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17184","created_at":"2026-07-05T09:53:18.605256+00:00"},{"alias_kind":"pith_short_12","alias_value":"T22753O62YY4","created_at":"2026-07-05T09:53:18.605256+00:00"},{"alias_kind":"pith_short_16","alias_value":"T22753O62YY4OTNJ","created_at":"2026-07-05T09:53:18.605256+00:00"},{"alias_kind":"pith_short_8","alias_value":"T22753O6","created_at":"2026-07-05T09:53:18.605256+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02129","citing_title":"Generative Latent Diffusion for Efficient Spatiotemporal Data Reduction","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T22753O62YY4OTNJLCNUDPI7O5","json":"https://pith.science/pith/T22753O62YY4OTNJLCNUDPI7O5.json","graph_json":"https://pith.science/api/pith-number/T22753O62YY4OTNJLCNUDPI7O5/graph.json","events_json":"https://pith.science/api/pith-number/T22753O62YY4OTNJLCNUDPI7O5/events.json","paper":"https://pith.science/paper/T22753O6"},"agent_actions":{"view_html":"https://pith.science/pith/T22753O62YY4OTNJLCNUDPI7O5","download_json":"https://pith.science/pith/T22753O62YY4OTNJLCNUDPI7O5.json","view_paper":"https://pith.science/paper/T22753O6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17184&json=true","fetch_graph":"https://pith.science/api/pith-number/T22753O62YY4OTNJLCNUDPI7O5/graph.json","fetch_events":"https://pith.science/api/pith-number/T22753O62YY4OTNJLCNUDPI7O5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T22753O62YY4OTNJLCNUDPI7O5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T22753O62YY4OTNJLCNUDPI7O5/action/storage_attestation","attest_author":"https://pith.science/pith/T22753O62YY4OTNJLCNUDPI7O5/action/author_attestation","sign_citation":"https://pith.science/pith/T22753O62YY4OTNJLCNUDPI7O5/action/citation_signature","submit_replication":"https://pith.science/pith/T22753O62YY4OTNJLCNUDPI7O5/action/replication_record"}},"created_at":"2026-07-05T09:53:18.605256+00:00","updated_at":"2026-07-05T09:53:18.605256+00:00"}