{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:R7FD7Z6BSOFSLVLI26G6GHBALO","short_pith_number":"pith:R7FD7Z6B","canonical_record":{"source":{"id":"1707.03372","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-11T17:23:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b1177138e3cc068d797eefad928595a70563976dfa2c0d6803b7d415eef07a55","abstract_canon_sha256":"2dc8068670be068dde7552afc3210a0bc789a54c7fc043cd94706117ef8eb0f7"},"schema_version":"1.0"},"canonical_sha256":"8fca3fe7c1938b25d568d78de31c205b95f89ba95e3f32baf4ab9e0e783d5377","source":{"kind":"arxiv","id":"1707.03372","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.03372","created_at":"2026-05-18T00:40:29Z"},{"alias_kind":"arxiv_version","alias_value":"1707.03372v1","created_at":"2026-05-18T00:40:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.03372","created_at":"2026-05-18T00:40:29Z"},{"alias_kind":"pith_short_12","alias_value":"R7FD7Z6BSOFS","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"R7FD7Z6BSOFSLVLI","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"R7FD7Z6B","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:R7FD7Z6BSOFSLVLI26G6GHBALO","target":"record","payload":{"canonical_record":{"source":{"id":"1707.03372","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-11T17:23:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b1177138e3cc068d797eefad928595a70563976dfa2c0d6803b7d415eef07a55","abstract_canon_sha256":"2dc8068670be068dde7552afc3210a0bc789a54c7fc043cd94706117ef8eb0f7"},"schema_version":"1.0"},"canonical_sha256":"8fca3fe7c1938b25d568d78de31c205b95f89ba95e3f32baf4ab9e0e783d5377","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:29.215679Z","signature_b64":"op/k2G3kpq059WsNEe4hMNHzp7Q822SYfXXdZT6/3cWsEcXMVkPVMV4qrbYY/O2R/emSYOFfs9RXMY81gf8hAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fca3fe7c1938b25d568d78de31c205b95f89ba95e3f32baf4ab9e0e783d5377","last_reissued_at":"2026-05-18T00:40:29.215218Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:29.215218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.03372","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:40:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0qHyFupjM7AL6fh6otdU9YhJxauMlvjvNJO6DuK1eqHqUa7AZyPhzJuNQApGWhj/wNoRb74FIVnV5KW259lMCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:29:17.668007Z"},"content_sha256":"f8702c2b7b228e2a27473bee5c5b4936989123af6ad8861d78be4ceab811ca6e","schema_version":"1.0","event_id":"sha256:f8702c2b7b228e2a27473bee5c5b4936989123af6ad8861d78be4ceab811ca6e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:R7FD7Z6BSOFSLVLI26G6GHBALO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast Amortized Inference and Learning in Log-linear Models with Randomly Perturbed Nearest Neighbor Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Levy, Stefano Ermon, Stephen Mussmann","submitted_at":"2017-07-11T17:23:10Z","abstract_excerpt":"Inference in log-linear models scales linearly in the size of output space in the worst-case. This is often a bottleneck in natural language processing and computer vision tasks when the output space is feasibly enumerable but very large. We propose a method to perform inference in log-linear models with sublinear amortized cost. Our idea hinges on using Gumbel random variable perturbations and a pre-computed Maximum Inner Product Search data structure to access the most-likely elements in sublinear amortized time. Our method yields provable runtime and accuracy guarantees. Further, we present"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.03372","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":""},"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":"2026-05-18T00:40:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YvzEhT+xXN906vdGdDsxSMwGyXEO0gWJ6FJq01SyqNNMbZYN9zd8tKPFf46HOEHOcQpX/IDOp8rXXkkpxBJ9Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:29:17.668382Z"},"content_sha256":"f6a02d4200ce34b822285ed1923cf2e7234c617bbaa86c300b54950469c8f268","schema_version":"1.0","event_id":"sha256:f6a02d4200ce34b822285ed1923cf2e7234c617bbaa86c300b54950469c8f268"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R7FD7Z6BSOFSLVLI26G6GHBALO/bundle.json","state_url":"https://pith.science/pith/R7FD7Z6BSOFSLVLI26G6GHBALO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R7FD7Z6BSOFSLVLI26G6GHBALO/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":"2026-06-03T07:29:17Z","links":{"resolver":"https://pith.science/pith/R7FD7Z6BSOFSLVLI26G6GHBALO","bundle":"https://pith.science/pith/R7FD7Z6BSOFSLVLI26G6GHBALO/bundle.json","state":"https://pith.science/pith/R7FD7Z6BSOFSLVLI26G6GHBALO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R7FD7Z6BSOFSLVLI26G6GHBALO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:R7FD7Z6BSOFSLVLI26G6GHBALO","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":"2dc8068670be068dde7552afc3210a0bc789a54c7fc043cd94706117ef8eb0f7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-11T17:23:10Z","title_canon_sha256":"b1177138e3cc068d797eefad928595a70563976dfa2c0d6803b7d415eef07a55"},"schema_version":"1.0","source":{"id":"1707.03372","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.03372","created_at":"2026-05-18T00:40:29Z"},{"alias_kind":"arxiv_version","alias_value":"1707.03372v1","created_at":"2026-05-18T00:40:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.03372","created_at":"2026-05-18T00:40:29Z"},{"alias_kind":"pith_short_12","alias_value":"R7FD7Z6BSOFS","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"R7FD7Z6BSOFSLVLI","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"R7FD7Z6B","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:f6a02d4200ce34b822285ed1923cf2e7234c617bbaa86c300b54950469c8f268","target":"graph","created_at":"2026-05-18T00:40:29Z","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":"Inference in log-linear models scales linearly in the size of output space in the worst-case. This is often a bottleneck in natural language processing and computer vision tasks when the output space is feasibly enumerable but very large. We propose a method to perform inference in log-linear models with sublinear amortized cost. Our idea hinges on using Gumbel random variable perturbations and a pre-computed Maximum Inner Product Search data structure to access the most-likely elements in sublinear amortized time. Our method yields provable runtime and accuracy guarantees. Further, we present","authors_text":"Daniel Levy, Stefano Ermon, Stephen Mussmann","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-11T17:23:10Z","title":"Fast Amortized Inference and Learning in Log-linear Models with Randomly Perturbed Nearest Neighbor Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.03372","kind":"arxiv","version":1},"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:f8702c2b7b228e2a27473bee5c5b4936989123af6ad8861d78be4ceab811ca6e","target":"record","created_at":"2026-05-18T00:40:29Z","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":"2dc8068670be068dde7552afc3210a0bc789a54c7fc043cd94706117ef8eb0f7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-11T17:23:10Z","title_canon_sha256":"b1177138e3cc068d797eefad928595a70563976dfa2c0d6803b7d415eef07a55"},"schema_version":"1.0","source":{"id":"1707.03372","kind":"arxiv","version":1}},"canonical_sha256":"8fca3fe7c1938b25d568d78de31c205b95f89ba95e3f32baf4ab9e0e783d5377","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fca3fe7c1938b25d568d78de31c205b95f89ba95e3f32baf4ab9e0e783d5377","first_computed_at":"2026-05-18T00:40:29.215218Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:29.215218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"op/k2G3kpq059WsNEe4hMNHzp7Q822SYfXXdZT6/3cWsEcXMVkPVMV4qrbYY/O2R/emSYOFfs9RXMY81gf8hAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:29.215679Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.03372","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8702c2b7b228e2a27473bee5c5b4936989123af6ad8861d78be4ceab811ca6e","sha256:f6a02d4200ce34b822285ed1923cf2e7234c617bbaa86c300b54950469c8f268"],"state_sha256":"b3d520d5b6bcc6624d4afa46dd11a9150da28c5ce29a479df9ea204d7d9d035f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fNXRIjZO17mOx165NZKGubSVcdUwqEmfhV82FQrn01BfO0ap+8XRGlCAAZPueJzT7wcxbZDdc+uHO1wnkxLPAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T07:29:17.670260Z","bundle_sha256":"dea7e40434b50d72a6600f0211cf6af1b9a50d02940f5d449042736e3a66bf78"}}