{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QS7OSYOGB4WPSBHRETJ7WEW7GP","short_pith_number":"pith:QS7OSYOG","schema_version":"1.0","canonical_sha256":"84bee961c60f2cf904f124d3fb12df33ce470e3ebe68accce1fe1db8c8a4d79f","source":{"kind":"arxiv","id":"2201.12904","version":3},"attestation_state":"computed","paper":{"title":"COIN++: Neural Compression Across Modalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.IV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Goli\\'nski, Arnaud Doucet, Emilien Dupont, Hrushikesh Loya, Milad Alizadeh, Yee Whye Teh","submitted_at":"2022-01-30T20:12:04Z","abstract_excerpt":"Neural compression algorithms are typically based on autoencoders that require specialized encoder and decoder architectures for different data modalities. In this paper, we propose COIN++, a neural compression framework that seamlessly handles a wide range of data modalities. Our approach is based on converting data to implicit neural representations, i.e. neural functions that map coordinates (such as pixel locations) to features (such as RGB values). Then, instead of storing the weights of the implicit neural representation directly, we store modulations applied to a meta-learned base netwo"},"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":"2201.12904","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-30T20:12:04Z","cross_cats_sorted":["cs.CV","eess.IV","stat.ML"],"title_canon_sha256":"0496e40eca3c9c122939247db392f5688c4c47db9fbc30e645d7203f22c2b855","abstract_canon_sha256":"05679bdf83a9677682913292b286ca5eb026981938d787456e2f98de5c116de2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:29.568438Z","signature_b64":"fK1tFkXr8NtWBz9UWdHQpoLBEjJ5/SsUgTnXMv4kdP76eQZaqVIxVH+qVaD9/mNU/WUojOyeMEg5MTRZ3NI5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84bee961c60f2cf904f124d3fb12df33ce470e3ebe68accce1fe1db8c8a4d79f","last_reissued_at":"2026-07-05T05:23:29.567940Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:29.567940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COIN++: Neural Compression Across Modalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.IV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Goli\\'nski, Arnaud Doucet, Emilien Dupont, Hrushikesh Loya, Milad Alizadeh, Yee Whye Teh","submitted_at":"2022-01-30T20:12:04Z","abstract_excerpt":"Neural compression algorithms are typically based on autoencoders that require specialized encoder and decoder architectures for different data modalities. In this paper, we propose COIN++, a neural compression framework that seamlessly handles a wide range of data modalities. Our approach is based on converting data to implicit neural representations, i.e. neural functions that map coordinates (such as pixel locations) to features (such as RGB values). Then, instead of storing the weights of the implicit neural representation directly, we store modulations applied to a meta-learned base netwo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.12904","kind":"arxiv","version":3},"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/2201.12904/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":"2201.12904","created_at":"2026-07-05T05:23:29.568009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.12904v3","created_at":"2026-07-05T05:23:29.568009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.12904","created_at":"2026-07-05T05:23:29.568009+00:00"},{"alias_kind":"pith_short_12","alias_value":"QS7OSYOGB4WP","created_at":"2026-07-05T05:23:29.568009+00:00"},{"alias_kind":"pith_short_16","alias_value":"QS7OSYOGB4WPSBHR","created_at":"2026-07-05T05:23:29.568009+00:00"},{"alias_kind":"pith_short_8","alias_value":"QS7OSYOG","created_at":"2026-07-05T05:23:29.568009+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.10433","citing_title":"Implicit Neural Compression of Point Clouds","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22556","citing_title":"ImplicitTerrainV2: Wavelet-Guided Spatially Adaptive Neural Terrain Representation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20672","citing_title":"LANCE: Locally Adaptive Neural Context Estimation for Overfitted Image Compression","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21984","citing_title":"Soft Anisotropic Diagrams for Differentiable Image Representation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15047","citing_title":"Implicit Neural Representations: A Signal Processing Perspective","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QS7OSYOGB4WPSBHRETJ7WEW7GP","json":"https://pith.science/pith/QS7OSYOGB4WPSBHRETJ7WEW7GP.json","graph_json":"https://pith.science/api/pith-number/QS7OSYOGB4WPSBHRETJ7WEW7GP/graph.json","events_json":"https://pith.science/api/pith-number/QS7OSYOGB4WPSBHRETJ7WEW7GP/events.json","paper":"https://pith.science/paper/QS7OSYOG"},"agent_actions":{"view_html":"https://pith.science/pith/QS7OSYOGB4WPSBHRETJ7WEW7GP","download_json":"https://pith.science/pith/QS7OSYOGB4WPSBHRETJ7WEW7GP.json","view_paper":"https://pith.science/paper/QS7OSYOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.12904&json=true","fetch_graph":"https://pith.science/api/pith-number/QS7OSYOGB4WPSBHRETJ7WEW7GP/graph.json","fetch_events":"https://pith.science/api/pith-number/QS7OSYOGB4WPSBHRETJ7WEW7GP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QS7OSYOGB4WPSBHRETJ7WEW7GP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QS7OSYOGB4WPSBHRETJ7WEW7GP/action/storage_attestation","attest_author":"https://pith.science/pith/QS7OSYOGB4WPSBHRETJ7WEW7GP/action/author_attestation","sign_citation":"https://pith.science/pith/QS7OSYOGB4WPSBHRETJ7WEW7GP/action/citation_signature","submit_replication":"https://pith.science/pith/QS7OSYOGB4WPSBHRETJ7WEW7GP/action/replication_record"}},"created_at":"2026-07-05T05:23:29.568009+00:00","updated_at":"2026-07-05T05:23:29.568009+00:00"}