{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:6D2OKJW7BWESAW4MIFNFTXXGWI","short_pith_number":"pith:6D2OKJW7","canonical_record":{"source":{"id":"2004.05665","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-12T18:09:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e49acfff0794297a060601a8253cf38111f2029fb9ca6708a65f1a9663d598ca","abstract_canon_sha256":"11c9c1099fc1103fcee7963c25ce0871be17aa0cf599cff75e86e855a3b724e9"},"schema_version":"1.0"},"canonical_sha256":"f0f4e526df0d89205b8c415a59dee6b2169a3b77dd1325c0de5c1f20a71edee0","source":{"kind":"arxiv","id":"2004.05665","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.05665","created_at":"2026-07-05T00:54:39Z"},{"alias_kind":"arxiv_version","alias_value":"2004.05665v1","created_at":"2026-07-05T00:54:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05665","created_at":"2026-07-05T00:54:39Z"},{"alias_kind":"pith_short_12","alias_value":"6D2OKJW7BWES","created_at":"2026-07-05T00:54:39Z"},{"alias_kind":"pith_short_16","alias_value":"6D2OKJW7BWESAW4M","created_at":"2026-07-05T00:54:39Z"},{"alias_kind":"pith_short_8","alias_value":"6D2OKJW7","created_at":"2026-07-05T00:54:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:6D2OKJW7BWESAW4MIFNFTXXGWI","target":"record","payload":{"canonical_record":{"source":{"id":"2004.05665","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-12T18:09:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e49acfff0794297a060601a8253cf38111f2029fb9ca6708a65f1a9663d598ca","abstract_canon_sha256":"11c9c1099fc1103fcee7963c25ce0871be17aa0cf599cff75e86e855a3b724e9"},"schema_version":"1.0"},"canonical_sha256":"f0f4e526df0d89205b8c415a59dee6b2169a3b77dd1325c0de5c1f20a71edee0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:54:39.504217Z","signature_b64":"/qfkqhXJJ12xnXyGx5L/wYHBfdU95R5NdADew/qLgMk8Yk0NLnt42EiVC3pkubx7HcXRVWgv84a2nyPgo0uBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0f4e526df0d89205b8c415a59dee6b2169a3b77dd1325c0de5c1f20a71edee0","last_reissued_at":"2026-07-05T00:54:39.503805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:54:39.503805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.05665","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":"2026-07-05T00:54:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UoONdArRqhxLFHwJHsoJnEbBIoDyzAQ8OGUAADW6/W6YLW9FoblWxkswnND40SrWb6GUGilMqQPEZXS/TcuGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T20:00:58.767783Z"},"content_sha256":"a1db26be382babc5748ce56a35b4754d27bf6ec01efaf548316e5946aa185521","schema_version":"1.0","event_id":"sha256:a1db26be382babc5748ce56a35b4754d27bf6ec01efaf548316e5946aa185521"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:6D2OKJW7BWESAW4MIFNFTXXGWI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Minimizing FLOPs to Learn Efficient Sparse Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Barnab\\'as P\\'oczos, Biswajit Paria, Chih-Kuan Yeh, Ian E.H. Yen, Ning Xu, Pradeep Ravikumar","submitted_at":"2020-04-12T18:09:02Z","abstract_excerpt":"Deep representation learning has become one of the most widely adopted approaches for visual search, recommendation, and identification. Retrieval of such representations from a large database is however computationally challenging. Approximate methods based on learning compact representations, have been widely explored for this problem, such as locality sensitive hashing, product quantization, and PCA. In this work, in contrast to learning compact representations, we propose to learn high dimensional and sparse representations that have similar representational capacity as dense embeddings wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05665","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.05665/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:54:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9hUG52AencwRwOtV0Zl5jBm1Rh8fp+fLH1xXKdPPGVgWdcdILzxsCrroqtSssBj7ljlnJcGgO7HeDGmutSCtCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T20:00:58.768279Z"},"content_sha256":"0a9b806dfd41521a0b0bc6fc493d92a49c0ba87a5dbea5777cbd1b348bab745a","schema_version":"1.0","event_id":"sha256:0a9b806dfd41521a0b0bc6fc493d92a49c0ba87a5dbea5777cbd1b348bab745a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6D2OKJW7BWESAW4MIFNFTXXGWI/bundle.json","state_url":"https://pith.science/pith/6D2OKJW7BWESAW4MIFNFTXXGWI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6D2OKJW7BWESAW4MIFNFTXXGWI/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":"2026-08-23T20:00:58Z","links":{"resolver":"https://pith.science/pith/6D2OKJW7BWESAW4MIFNFTXXGWI","bundle":"https://pith.science/pith/6D2OKJW7BWESAW4MIFNFTXXGWI/bundle.json","state":"https://pith.science/pith/6D2OKJW7BWESAW4MIFNFTXXGWI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6D2OKJW7BWESAW4MIFNFTXXGWI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6D2OKJW7BWESAW4MIFNFTXXGWI","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":"11c9c1099fc1103fcee7963c25ce0871be17aa0cf599cff75e86e855a3b724e9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-12T18:09:02Z","title_canon_sha256":"e49acfff0794297a060601a8253cf38111f2029fb9ca6708a65f1a9663d598ca"},"schema_version":"1.0","source":{"id":"2004.05665","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.05665","created_at":"2026-07-05T00:54:39Z"},{"alias_kind":"arxiv_version","alias_value":"2004.05665v1","created_at":"2026-07-05T00:54:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05665","created_at":"2026-07-05T00:54:39Z"},{"alias_kind":"pith_short_12","alias_value":"6D2OKJW7BWES","created_at":"2026-07-05T00:54:39Z"},{"alias_kind":"pith_short_16","alias_value":"6D2OKJW7BWESAW4M","created_at":"2026-07-05T00:54:39Z"},{"alias_kind":"pith_short_8","alias_value":"6D2OKJW7","created_at":"2026-07-05T00:54:39Z"}],"graph_snapshots":[{"event_id":"sha256:0a9b806dfd41521a0b0bc6fc493d92a49c0ba87a5dbea5777cbd1b348bab745a","target":"graph","created_at":"2026-07-05T00:54:39Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2004.05665/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep representation learning has become one of the most widely adopted approaches for visual search, recommendation, and identification. Retrieval of such representations from a large database is however computationally challenging. Approximate methods based on learning compact representations, have been widely explored for this problem, such as locality sensitive hashing, product quantization, and PCA. In this work, in contrast to learning compact representations, we propose to learn high dimensional and sparse representations that have similar representational capacity as dense embeddings wh","authors_text":"Barnab\\'as P\\'oczos, Biswajit Paria, Chih-Kuan Yeh, Ian E.H. Yen, Ning Xu, Pradeep Ravikumar","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-12T18:09:02Z","title":"Minimizing FLOPs to Learn Efficient Sparse Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05665","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:a1db26be382babc5748ce56a35b4754d27bf6ec01efaf548316e5946aa185521","target":"record","created_at":"2026-07-05T00:54:39Z","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":"11c9c1099fc1103fcee7963c25ce0871be17aa0cf599cff75e86e855a3b724e9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-12T18:09:02Z","title_canon_sha256":"e49acfff0794297a060601a8253cf38111f2029fb9ca6708a65f1a9663d598ca"},"schema_version":"1.0","source":{"id":"2004.05665","kind":"arxiv","version":1}},"canonical_sha256":"f0f4e526df0d89205b8c415a59dee6b2169a3b77dd1325c0de5c1f20a71edee0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0f4e526df0d89205b8c415a59dee6b2169a3b77dd1325c0de5c1f20a71edee0","first_computed_at":"2026-07-05T00:54:39.503805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:54:39.503805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/qfkqhXJJ12xnXyGx5L/wYHBfdU95R5NdADew/qLgMk8Yk0NLnt42EiVC3pkubx7HcXRVWgv84a2nyPgo0uBBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:54:39.504217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.05665","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1db26be382babc5748ce56a35b4754d27bf6ec01efaf548316e5946aa185521","sha256:0a9b806dfd41521a0b0bc6fc493d92a49c0ba87a5dbea5777cbd1b348bab745a"],"state_sha256":"4af95a14a8dae0e548b3c17c01dd13f63879dad9776b30c778e0e4d9946620dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rTfuJtbZoXWlY+/yO8KCqPT3qDKJfpfgcxdWO4xnoY81/cebENg7/vhekoNsDmrUy26JOvBWCezzx1BqDwWWBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T20:00:58.772846Z","bundle_sha256":"0a6edc2834f3976dd631275f2416b667163f6f9c3124be78020cdcf01eec3e51"}}