{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:YDI2NVBIFXMAMTG3PVCCFR3VOI","short_pith_number":"pith:YDI2NVBI","canonical_record":{"source":{"id":"1407.5155","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-07-19T06:50:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d34c4870af4f0dd6da550f39c182ad131fd23c862ed026bfd3c62112b9762985","abstract_canon_sha256":"182eee33f02ba18d1423ee1ea91ba300d6ff59d78aa874db05e876c7eb6cbf86"},"schema_version":"1.0"},"canonical_sha256":"c0d1a6d4282dd8064cdb7d4422c77572372deab8e9c28353625db695bfff326b","source":{"kind":"arxiv","id":"1407.5155","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1407.5155","created_at":"2026-05-18T01:34:55Z"},{"alias_kind":"arxiv_version","alias_value":"1407.5155v4","created_at":"2026-05-18T01:34:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1407.5155","created_at":"2026-05-18T01:34:55Z"},{"alias_kind":"pith_short_12","alias_value":"YDI2NVBIFXMA","created_at":"2026-05-18T12:28:57Z"},{"alias_kind":"pith_short_16","alias_value":"YDI2NVBIFXMAMTG3","created_at":"2026-05-18T12:28:57Z"},{"alias_kind":"pith_short_8","alias_value":"YDI2NVBI","created_at":"2026-05-18T12:28:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:YDI2NVBIFXMAMTG3PVCCFR3VOI","target":"record","payload":{"canonical_record":{"source":{"id":"1407.5155","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-07-19T06:50:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d34c4870af4f0dd6da550f39c182ad131fd23c862ed026bfd3c62112b9762985","abstract_canon_sha256":"182eee33f02ba18d1423ee1ea91ba300d6ff59d78aa874db05e876c7eb6cbf86"},"schema_version":"1.0"},"canonical_sha256":"c0d1a6d4282dd8064cdb7d4422c77572372deab8e9c28353625db695bfff326b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:34:55.412037Z","signature_b64":"F/PjUWol0DIbN3Ob2sbeh1K4gyVw+XXAEXuJT4sDlLGK/OcXTgZHDCDf2sm5VGFKdX18ENLg+ysYbVacsIrADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0d1a6d4282dd8064cdb7d4422c77572372deab8e9c28353625db695bfff326b","last_reissued_at":"2026-05-18T01:34:55.411564Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:34:55.411564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1407.5155","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:34:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U+sOj+SAhiSmXJdWbqW+aMOi7WiBjHuh90+3zNhIiHGXp5y/6TaO8j0mFWy5Vt7zMvacG55t8v5JICkqHwRfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T08:42:02.994021Z"},"content_sha256":"de4e731612ff07fce9d22e67933c2eaf6a1dc0b259f96872244eaddd6ac65a2b","schema_version":"1.0","event_id":"sha256:de4e731612ff07fce9d22e67933c2eaf6a1dc0b259f96872244eaddd6ac65a2b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:YDI2NVBIFXMAMTG3PVCCFR3VOI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sparse and spurious: dictionary learning with noise and outliers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Francis Bach (SIERRA, LIENS), R\\'emi Gribonval (PANAMA), Rodolphe Jenatton (CMAP)","submitted_at":"2014-07-19T06:50:19Z","abstract_excerpt":"A popular approach within the signal processing and machine learning communities consists in modelling signals as sparse linear combinations of atoms selected from a learned dictionary. While this paradigm has led to numerous empirical successes in various fields ranging from image to audio processing, there have only been a few theoretical arguments supporting these evidences. In particular, sparse coding, or sparse dictionary learning, relies on a non-convex procedure whose local minima have not been fully analyzed yet. In this paper, we consider a probabilistic model of sparse signals, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1407.5155","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":""},"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":"2026-05-18T01:34:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4PvzLQ2ztmp5HfmG22H4o63lqaPjBOIRiM54eg2muVhET/nBEeOYkWPU/SsFVHOe4B+O05+Z+n6Kw/G+5DqtCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T08:42:02.994390Z"},"content_sha256":"628df19aae86c5e5f726559ae88baae59ca7b25463f26185882e5a1eb3dcd2dc","schema_version":"1.0","event_id":"sha256:628df19aae86c5e5f726559ae88baae59ca7b25463f26185882e5a1eb3dcd2dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YDI2NVBIFXMAMTG3PVCCFR3VOI/bundle.json","state_url":"https://pith.science/pith/YDI2NVBIFXMAMTG3PVCCFR3VOI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YDI2NVBIFXMAMTG3PVCCFR3VOI/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":"2026-06-05T08:42:02Z","links":{"resolver":"https://pith.science/pith/YDI2NVBIFXMAMTG3PVCCFR3VOI","bundle":"https://pith.science/pith/YDI2NVBIFXMAMTG3PVCCFR3VOI/bundle.json","state":"https://pith.science/pith/YDI2NVBIFXMAMTG3PVCCFR3VOI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YDI2NVBIFXMAMTG3PVCCFR3VOI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:YDI2NVBIFXMAMTG3PVCCFR3VOI","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":"182eee33f02ba18d1423ee1ea91ba300d6ff59d78aa874db05e876c7eb6cbf86","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-07-19T06:50:19Z","title_canon_sha256":"d34c4870af4f0dd6da550f39c182ad131fd23c862ed026bfd3c62112b9762985"},"schema_version":"1.0","source":{"id":"1407.5155","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1407.5155","created_at":"2026-05-18T01:34:55Z"},{"alias_kind":"arxiv_version","alias_value":"1407.5155v4","created_at":"2026-05-18T01:34:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1407.5155","created_at":"2026-05-18T01:34:55Z"},{"alias_kind":"pith_short_12","alias_value":"YDI2NVBIFXMA","created_at":"2026-05-18T12:28:57Z"},{"alias_kind":"pith_short_16","alias_value":"YDI2NVBIFXMAMTG3","created_at":"2026-05-18T12:28:57Z"},{"alias_kind":"pith_short_8","alias_value":"YDI2NVBI","created_at":"2026-05-18T12:28:57Z"}],"graph_snapshots":[{"event_id":"sha256:628df19aae86c5e5f726559ae88baae59ca7b25463f26185882e5a1eb3dcd2dc","target":"graph","created_at":"2026-05-18T01:34:55Z","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":"A popular approach within the signal processing and machine learning communities consists in modelling signals as sparse linear combinations of atoms selected from a learned dictionary. While this paradigm has led to numerous empirical successes in various fields ranging from image to audio processing, there have only been a few theoretical arguments supporting these evidences. In particular, sparse coding, or sparse dictionary learning, relies on a non-convex procedure whose local minima have not been fully analyzed yet. In this paper, we consider a probabilistic model of sparse signals, and ","authors_text":"Francis Bach (SIERRA, LIENS), R\\'emi Gribonval (PANAMA), Rodolphe Jenatton (CMAP)","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-07-19T06:50:19Z","title":"Sparse and spurious: dictionary learning with noise and outliers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1407.5155","kind":"arxiv","version":4},"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:de4e731612ff07fce9d22e67933c2eaf6a1dc0b259f96872244eaddd6ac65a2b","target":"record","created_at":"2026-05-18T01:34:55Z","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":"182eee33f02ba18d1423ee1ea91ba300d6ff59d78aa874db05e876c7eb6cbf86","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-07-19T06:50:19Z","title_canon_sha256":"d34c4870af4f0dd6da550f39c182ad131fd23c862ed026bfd3c62112b9762985"},"schema_version":"1.0","source":{"id":"1407.5155","kind":"arxiv","version":4}},"canonical_sha256":"c0d1a6d4282dd8064cdb7d4422c77572372deab8e9c28353625db695bfff326b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0d1a6d4282dd8064cdb7d4422c77572372deab8e9c28353625db695bfff326b","first_computed_at":"2026-05-18T01:34:55.411564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:34:55.411564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F/PjUWol0DIbN3Ob2sbeh1K4gyVw+XXAEXuJT4sDlLGK/OcXTgZHDCDf2sm5VGFKdX18ENLg+ysYbVacsIrADw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:34:55.412037Z","signed_message":"canonical_sha256_bytes"},"source_id":"1407.5155","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de4e731612ff07fce9d22e67933c2eaf6a1dc0b259f96872244eaddd6ac65a2b","sha256:628df19aae86c5e5f726559ae88baae59ca7b25463f26185882e5a1eb3dcd2dc"],"state_sha256":"d0150bded82f5ba3f6ecf91fd9b5727454b2459b98547a1f3b5a7a6e2b60fab0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qe4+y6VPhyaCGZ2DN4LqJaI7TZxQNmjaEZ80uI0DXYhwYehoTww4KDh/SZTsdGwA7otdvxRW+qyyYvNMA/hTDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T08:42:02.996611Z","bundle_sha256":"ef33109f8243fa2b526edfebc684b8921456202eabc041c650be7677b4af9a07"}}