{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:JRGM44QDAR7NHW3PVXXMOXLLAZ","short_pith_number":"pith:JRGM44QD","canonical_record":{"source":{"id":"1706.02815","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-09T02:56:54Z","cross_cats_sorted":[],"title_canon_sha256":"ccb859d7aaf0a9bbf4d9f80658d7e8dfe957bc2f082a49d0c3e8abfd0a85fcd5","abstract_canon_sha256":"771f0c1c7e3f0db57d038b96080d907afb2a6fa67ab780a882aa81c2e1f66db5"},"schema_version":"1.0"},"canonical_sha256":"4c4cce7203047ed3db6fadeec75d6b066e95d50ccf1a11b8d05a8bf0c350dc8c","source":{"kind":"arxiv","id":"1706.02815","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.02815","created_at":"2026-05-18T00:38:45Z"},{"alias_kind":"arxiv_version","alias_value":"1706.02815v2","created_at":"2026-05-18T00:38:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.02815","created_at":"2026-05-18T00:38:45Z"},{"alias_kind":"pith_short_12","alias_value":"JRGM44QDAR7N","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"JRGM44QDAR7NHW3P","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"JRGM44QD","created_at":"2026-05-18T12:31:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:JRGM44QDAR7NHW3PVXXMOXLLAZ","target":"record","payload":{"canonical_record":{"source":{"id":"1706.02815","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-09T02:56:54Z","cross_cats_sorted":[],"title_canon_sha256":"ccb859d7aaf0a9bbf4d9f80658d7e8dfe957bc2f082a49d0c3e8abfd0a85fcd5","abstract_canon_sha256":"771f0c1c7e3f0db57d038b96080d907afb2a6fa67ab780a882aa81c2e1f66db5"},"schema_version":"1.0"},"canonical_sha256":"4c4cce7203047ed3db6fadeec75d6b066e95d50ccf1a11b8d05a8bf0c350dc8c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:45.885691Z","signature_b64":"6IRLuc+vQNu8qToCL2VswaJMpXJ3Ek2XELX1xlWuhySabmScCZHS/jYVtFBxgVpAiLDUdYio0nQzAfjNlRXlAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c4cce7203047ed3db6fadeec75d6b066e95d50ccf1a11b8d05a8bf0c350dc8c","last_reissued_at":"2026-05-18T00:38:45.885058Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:45.885058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.02815","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:38:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kpa9wed65JmWRFmJ6z/RZOsSaYokexzVbMz5iPiz3PcERF61EJKhIYyh4E6pyNPXbyXVEp1Vz31VqPptoIohCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:31:13.160520Z"},"content_sha256":"74732df24718dcfdf7061352db85f63b7ff1089e8fbe6cdb89bcf5c788a6b577","schema_version":"1.0","event_id":"sha256:74732df24718dcfdf7061352db85f63b7ff1089e8fbe6cdb89bcf5c788a6b577"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:JRGM44QDAR7NHW3PVXXMOXLLAZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Bayesian Sparsity to Gated Recurrent Nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Xin, David Wipf, Hao He","submitted_at":"2017-06-09T02:56:54Z","abstract_excerpt":"The iterations of many first-order algorithms, when applied to minimizing common regularized regression functions, often resemble neural network layers with pre-specified weights. This observation has prompted the development of learning-based approaches that purport to replace these iterations with enhanced surrogates forged as DNN models from available training data. For example, important NP-hard sparse estimation problems have recently benefitted from this genre of upgrade, with simple feedforward or recurrent networks ousting proximal gradient-based iterations. Analogously, this paper dem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.02815","kind":"arxiv","version":2},"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":"2026-05-18T00:38:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bd2MBiiBx5//0Z/jxlZyPUTVlSHfbw313S/eo2NovIQRhSjHBxJFr7INFEk60AoG++mFfC6EReW5CEfPPE1CBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:31:13.160964Z"},"content_sha256":"d2fe1a0cfff7db9ef5677b1a7130ab7073b61e0b4785c2eb893237356e831d95","schema_version":"1.0","event_id":"sha256:d2fe1a0cfff7db9ef5677b1a7130ab7073b61e0b4785c2eb893237356e831d95"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JRGM44QDAR7NHW3PVXXMOXLLAZ/bundle.json","state_url":"https://pith.science/pith/JRGM44QDAR7NHW3PVXXMOXLLAZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JRGM44QDAR7NHW3PVXXMOXLLAZ/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":"2026-05-31T20:31:13Z","links":{"resolver":"https://pith.science/pith/JRGM44QDAR7NHW3PVXXMOXLLAZ","bundle":"https://pith.science/pith/JRGM44QDAR7NHW3PVXXMOXLLAZ/bundle.json","state":"https://pith.science/pith/JRGM44QDAR7NHW3PVXXMOXLLAZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JRGM44QDAR7NHW3PVXXMOXLLAZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:JRGM44QDAR7NHW3PVXXMOXLLAZ","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":"771f0c1c7e3f0db57d038b96080d907afb2a6fa67ab780a882aa81c2e1f66db5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-09T02:56:54Z","title_canon_sha256":"ccb859d7aaf0a9bbf4d9f80658d7e8dfe957bc2f082a49d0c3e8abfd0a85fcd5"},"schema_version":"1.0","source":{"id":"1706.02815","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.02815","created_at":"2026-05-18T00:38:45Z"},{"alias_kind":"arxiv_version","alias_value":"1706.02815v2","created_at":"2026-05-18T00:38:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.02815","created_at":"2026-05-18T00:38:45Z"},{"alias_kind":"pith_short_12","alias_value":"JRGM44QDAR7N","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"JRGM44QDAR7NHW3P","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"JRGM44QD","created_at":"2026-05-18T12:31:24Z"}],"graph_snapshots":[{"event_id":"sha256:d2fe1a0cfff7db9ef5677b1a7130ab7073b61e0b4785c2eb893237356e831d95","target":"graph","created_at":"2026-05-18T00:38:45Z","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":"The iterations of many first-order algorithms, when applied to minimizing common regularized regression functions, often resemble neural network layers with pre-specified weights. This observation has prompted the development of learning-based approaches that purport to replace these iterations with enhanced surrogates forged as DNN models from available training data. For example, important NP-hard sparse estimation problems have recently benefitted from this genre of upgrade, with simple feedforward or recurrent networks ousting proximal gradient-based iterations. Analogously, this paper dem","authors_text":"Bo Xin, David Wipf, Hao He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-09T02:56:54Z","title":"From Bayesian Sparsity to Gated Recurrent Nets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.02815","kind":"arxiv","version":2},"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":"sha256:74732df24718dcfdf7061352db85f63b7ff1089e8fbe6cdb89bcf5c788a6b577","target":"record","created_at":"2026-05-18T00:38:45Z","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":"771f0c1c7e3f0db57d038b96080d907afb2a6fa67ab780a882aa81c2e1f66db5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-09T02:56:54Z","title_canon_sha256":"ccb859d7aaf0a9bbf4d9f80658d7e8dfe957bc2f082a49d0c3e8abfd0a85fcd5"},"schema_version":"1.0","source":{"id":"1706.02815","kind":"arxiv","version":2}},"canonical_sha256":"4c4cce7203047ed3db6fadeec75d6b066e95d50ccf1a11b8d05a8bf0c350dc8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c4cce7203047ed3db6fadeec75d6b066e95d50ccf1a11b8d05a8bf0c350dc8c","first_computed_at":"2026-05-18T00:38:45.885058Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:45.885058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6IRLuc+vQNu8qToCL2VswaJMpXJ3Ek2XELX1xlWuhySabmScCZHS/jYVtFBxgVpAiLDUdYio0nQzAfjNlRXlAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:45.885691Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.02815","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74732df24718dcfdf7061352db85f63b7ff1089e8fbe6cdb89bcf5c788a6b577","sha256:d2fe1a0cfff7db9ef5677b1a7130ab7073b61e0b4785c2eb893237356e831d95"],"state_sha256":"7759d293fc59730ee240a465d832adf42e2e466cd838ea016f62c8a901402608"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5cGceMKo7NAwhcxU3PhdXWQMkrXbX1w1JDeukEarPVQUxeOQXkRXRnuMjsBTbxv9qh7QqqaXhpiUadg6Kk2wAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T20:31:13.164182Z","bundle_sha256":"76c1cad7209295d7493fa6c310205ca91aa6c5ee6a1bf4555aefbb0258fe457f"}}