{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:VFCSD34E474X2W7TXZKSPU6XDX","short_pith_number":"pith:VFCSD34E","canonical_record":{"source":{"id":"1503.04949","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-03-17T08:43:57Z","cross_cats_sorted":[],"title_canon_sha256":"ee81e8a1f9eccb12ca23b3a693c2d2156400d9992cade7c66016983bbf8b2300","abstract_canon_sha256":"7f01451fb26652e3f93366ff8a92d1b804b766b5ee63db78f25e1f6857257197"},"schema_version":"1.0"},"canonical_sha256":"a94521ef84e7f97d5bf3be5527d3d71de677266a681199e7ca10c29c088bd248","source":{"kind":"arxiv","id":"1503.04949","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.04949","created_at":"2026-05-18T01:25:56Z"},{"alias_kind":"arxiv_version","alias_value":"1503.04949v3","created_at":"2026-05-18T01:25:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.04949","created_at":"2026-05-18T01:25:56Z"},{"alias_kind":"pith_short_12","alias_value":"VFCSD34E474X","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_16","alias_value":"VFCSD34E474X2W7T","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_8","alias_value":"VFCSD34E","created_at":"2026-05-18T12:29:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:VFCSD34E474X2W7TXZKSPU6XDX","target":"record","payload":{"canonical_record":{"source":{"id":"1503.04949","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-03-17T08:43:57Z","cross_cats_sorted":[],"title_canon_sha256":"ee81e8a1f9eccb12ca23b3a693c2d2156400d9992cade7c66016983bbf8b2300","abstract_canon_sha256":"7f01451fb26652e3f93366ff8a92d1b804b766b5ee63db78f25e1f6857257197"},"schema_version":"1.0"},"canonical_sha256":"a94521ef84e7f97d5bf3be5527d3d71de677266a681199e7ca10c29c088bd248","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:25:56.526884Z","signature_b64":"SbKZD5C5DjwDABSrDJki9kCVPt1m0ylOO6g7Lvwu4dqmvB0VAuZVkT3bqhVQyWuoSoAX65G2cjemFDh+JNzwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a94521ef84e7f97d5bf3be5527d3d71de677266a681199e7ca10c29c088bd248","last_reissued_at":"2026-05-18T01:25:56.526198Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:25:56.526198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1503.04949","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:25:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5IicpF4CztjSnUPdYY1hfZiNty8QBgZ88bc8buOwJOAVRZkf8nOP15zwpt4DlkvTCETh4+y/mHSEz+IU6KO8BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:52:29.851047Z"},"content_sha256":"bfcc7f6e1717f67168c674b6a2b2e0b3ace9216ff45ff7264a030695031113b8","schema_version":"1.0","event_id":"sha256:bfcc7f6e1717f67168c674b6a2b2e0b3ace9216ff45ff7264a030695031113b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:VFCSD34E474X2W7TXZKSPU6XDX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Martin Kiefel, Peter V. Gehler, Varun Jampani","submitted_at":"2015-03-17T08:43:57Z","abstract_excerpt":"Bilateral filters have wide spread use due to their edge-preserving properties. The common use case is to manually choose a parametric filter type, usually a Gaussian filter. In this paper, we will generalize the parametrization and in particular derive a gradient descent algorithm so the filter parameters can be learned from data. This derivation allows to learn high dimensional linear filters that operate in sparsely populated feature spaces. We build on the permutohedral lattice construction for efficient filtering. The ability to learn more general forms of high-dimensional filters can be "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.04949","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:25:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"trIqBjqy64uayATTTw+LVe1rok+TL062MpcqBSPMaCWDvbfz1q3vgRqkGXCS6mGFMvIbiW9KAUv3J4CsE0p7CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:52:29.851781Z"},"content_sha256":"883e8bcce246dc67b3cc9d19e03e7ba8be95501fdbc7b2d3d627d2d42731eb83","schema_version":"1.0","event_id":"sha256:883e8bcce246dc67b3cc9d19e03e7ba8be95501fdbc7b2d3d627d2d42731eb83"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VFCSD34E474X2W7TXZKSPU6XDX/bundle.json","state_url":"https://pith.science/pith/VFCSD34E474X2W7TXZKSPU6XDX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VFCSD34E474X2W7TXZKSPU6XDX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T22:52:29Z","links":{"resolver":"https://pith.science/pith/VFCSD34E474X2W7TXZKSPU6XDX","bundle":"https://pith.science/pith/VFCSD34E474X2W7TXZKSPU6XDX/bundle.json","state":"https://pith.science/pith/VFCSD34E474X2W7TXZKSPU6XDX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VFCSD34E474X2W7TXZKSPU6XDX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:VFCSD34E474X2W7TXZKSPU6XDX","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":"7f01451fb26652e3f93366ff8a92d1b804b766b5ee63db78f25e1f6857257197","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-03-17T08:43:57Z","title_canon_sha256":"ee81e8a1f9eccb12ca23b3a693c2d2156400d9992cade7c66016983bbf8b2300"},"schema_version":"1.0","source":{"id":"1503.04949","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.04949","created_at":"2026-05-18T01:25:56Z"},{"alias_kind":"arxiv_version","alias_value":"1503.04949v3","created_at":"2026-05-18T01:25:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.04949","created_at":"2026-05-18T01:25:56Z"},{"alias_kind":"pith_short_12","alias_value":"VFCSD34E474X","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_16","alias_value":"VFCSD34E474X2W7T","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_8","alias_value":"VFCSD34E","created_at":"2026-05-18T12:29:44Z"}],"graph_snapshots":[{"event_id":"sha256:883e8bcce246dc67b3cc9d19e03e7ba8be95501fdbc7b2d3d627d2d42731eb83","target":"graph","created_at":"2026-05-18T01:25:56Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Bilateral filters have wide spread use due to their edge-preserving properties. The common use case is to manually choose a parametric filter type, usually a Gaussian filter. In this paper, we will generalize the parametrization and in particular derive a gradient descent algorithm so the filter parameters can be learned from data. This derivation allows to learn high dimensional linear filters that operate in sparsely populated feature spaces. We build on the permutohedral lattice construction for efficient filtering. The ability to learn more general forms of high-dimensional filters can be ","authors_text":"Martin Kiefel, Peter V. Gehler, Varun Jampani","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-03-17T08:43:57Z","title":"Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.04949","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bfcc7f6e1717f67168c674b6a2b2e0b3ace9216ff45ff7264a030695031113b8","target":"record","created_at":"2026-05-18T01:25:56Z","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":"7f01451fb26652e3f93366ff8a92d1b804b766b5ee63db78f25e1f6857257197","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-03-17T08:43:57Z","title_canon_sha256":"ee81e8a1f9eccb12ca23b3a693c2d2156400d9992cade7c66016983bbf8b2300"},"schema_version":"1.0","source":{"id":"1503.04949","kind":"arxiv","version":3}},"canonical_sha256":"a94521ef84e7f97d5bf3be5527d3d71de677266a681199e7ca10c29c088bd248","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a94521ef84e7f97d5bf3be5527d3d71de677266a681199e7ca10c29c088bd248","first_computed_at":"2026-05-18T01:25:56.526198Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:25:56.526198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SbKZD5C5DjwDABSrDJki9kCVPt1m0ylOO6g7Lvwu4dqmvB0VAuZVkT3bqhVQyWuoSoAX65G2cjemFDh+JNzwBg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:25:56.526884Z","signed_message":"canonical_sha256_bytes"},"source_id":"1503.04949","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfcc7f6e1717f67168c674b6a2b2e0b3ace9216ff45ff7264a030695031113b8","sha256:883e8bcce246dc67b3cc9d19e03e7ba8be95501fdbc7b2d3d627d2d42731eb83"],"state_sha256":"f5cd42b1670285cca29850b0b4f4e82d36f76556aec34c6d22a165d156744ab6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a32UgWN+yiyyEu2q71ZiNI+JBSOVrhkr6g+ouPrwvicc2PL/DTMDuyhF46KdhMNlyeBEc2lVrRhf0wr3VH3kAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T22:52:29.855765Z","bundle_sha256":"4bd6dae67ce7b034ac9540128ad97663baf4ba8fc47d4ac1c44fd8f4af7ef807"}}