{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ADBFLA4ZSDABF5EBQI75V42KJI","short_pith_number":"pith:ADBFLA4Z","canonical_record":{"source":{"id":"1804.02941","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-04-09T12:31:07Z","cross_cats_sorted":[],"title_canon_sha256":"ba315e7890a3a21e184fc1ceb893b65914cd3842ad46fa89626ea437e63672a0","abstract_canon_sha256":"a0a2fca721c17219d03777fb2ff314473b1e1e2f4ed7d72945e46659bc7ea492"},"schema_version":"1.0"},"canonical_sha256":"00c255839990c012f481823fdaf34a4a30f0693b41b67b6f0abfca32e5c37bea","source":{"kind":"arxiv","id":"1804.02941","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.02941","created_at":"2026-05-18T00:18:57Z"},{"alias_kind":"arxiv_version","alias_value":"1804.02941v1","created_at":"2026-05-18T00:18:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02941","created_at":"2026-05-18T00:18:57Z"},{"alias_kind":"pith_short_12","alias_value":"ADBFLA4ZSDAB","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"ADBFLA4ZSDABF5EB","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"ADBFLA4Z","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ADBFLA4ZSDABF5EBQI75V42KJI","target":"record","payload":{"canonical_record":{"source":{"id":"1804.02941","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-04-09T12:31:07Z","cross_cats_sorted":[],"title_canon_sha256":"ba315e7890a3a21e184fc1ceb893b65914cd3842ad46fa89626ea437e63672a0","abstract_canon_sha256":"a0a2fca721c17219d03777fb2ff314473b1e1e2f4ed7d72945e46659bc7ea492"},"schema_version":"1.0"},"canonical_sha256":"00c255839990c012f481823fdaf34a4a30f0693b41b67b6f0abfca32e5c37bea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:57.898136Z","signature_b64":"Fv07O1piNZrqkzSPT9F8kLsbIL0S3TaFLrIEYchBqxNwb+Sn7wz1gjuL2aGpR/u30u8HApwcehWPEErLk6EMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00c255839990c012f481823fdaf34a4a30f0693b41b67b6f0abfca32e5c37bea","last_reissued_at":"2026-05-18T00:18:57.897410Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:57.897410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.02941","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":"2026-05-18T00:18:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EhnSepem7/2vkZ2KelzWr82+IhlZvx+WgKJE95CKhCr39BDF7E+3XLZU2Nyc7gwp/7J4370CNQYGNYwID7SZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T03:54:34.854348Z"},"content_sha256":"b0ed1c381bf3955b6be17319dae506067af7aeb45078cbe944e92d176a8c62e9","schema_version":"1.0","event_id":"sha256:b0ed1c381bf3955b6be17319dae506067af7aeb45078cbe944e92d176a8c62e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ADBFLA4ZSDABF5EBQI75V42KJI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distribution-Aware Binarization of Neural Networks for Sketch Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ameya Prabhu, Anoop Namboodiri, Rohit Gajawada, Sri Aurobindo Munagala, Vishal Batchu","submitted_at":"2018-04-09T12:31:07Z","abstract_excerpt":"Deep neural networks are highly effective at a range of computational tasks. However, they tend to be computationally expensive, especially in vision-related problems, and also have large memory requirements. One of the most effective methods to achieve significant improvements in computational/spatial efficiency is to binarize the weights and activations in a network. However, naive binarization results in accuracy drops when applied to networks for most tasks. In this work, we present a highly generalized, distribution-aware approach to binarizing deep networks that allows us to retain the a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02941","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":"2026-05-18T00:18:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DRaS48By1OItUdH7nUM5kg9SFQdyfRUC73f2TIDo7wtStIqgZ26NRtbLXdoszHkbeDd+PL8Mq5Ipev3bMdDBDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T03:54:34.854990Z"},"content_sha256":"1ec620b12ba812c08d65a15ce9d8211cdc734a24a90eb7107ab9a879285a0b0d","schema_version":"1.0","event_id":"sha256:1ec620b12ba812c08d65a15ce9d8211cdc734a24a90eb7107ab9a879285a0b0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ADBFLA4ZSDABF5EBQI75V42KJI/bundle.json","state_url":"https://pith.science/pith/ADBFLA4ZSDABF5EBQI75V42KJI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ADBFLA4ZSDABF5EBQI75V42KJI/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":"2026-05-26T03:54:34Z","links":{"resolver":"https://pith.science/pith/ADBFLA4ZSDABF5EBQI75V42KJI","bundle":"https://pith.science/pith/ADBFLA4ZSDABF5EBQI75V42KJI/bundle.json","state":"https://pith.science/pith/ADBFLA4ZSDABF5EBQI75V42KJI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ADBFLA4ZSDABF5EBQI75V42KJI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ADBFLA4ZSDABF5EBQI75V42KJI","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":"a0a2fca721c17219d03777fb2ff314473b1e1e2f4ed7d72945e46659bc7ea492","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-04-09T12:31:07Z","title_canon_sha256":"ba315e7890a3a21e184fc1ceb893b65914cd3842ad46fa89626ea437e63672a0"},"schema_version":"1.0","source":{"id":"1804.02941","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.02941","created_at":"2026-05-18T00:18:57Z"},{"alias_kind":"arxiv_version","alias_value":"1804.02941v1","created_at":"2026-05-18T00:18:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02941","created_at":"2026-05-18T00:18:57Z"},{"alias_kind":"pith_short_12","alias_value":"ADBFLA4ZSDAB","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"ADBFLA4ZSDABF5EB","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"ADBFLA4Z","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:1ec620b12ba812c08d65a15ce9d8211cdc734a24a90eb7107ab9a879285a0b0d","target":"graph","created_at":"2026-05-18T00:18:57Z","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":"Deep neural networks are highly effective at a range of computational tasks. However, they tend to be computationally expensive, especially in vision-related problems, and also have large memory requirements. One of the most effective methods to achieve significant improvements in computational/spatial efficiency is to binarize the weights and activations in a network. However, naive binarization results in accuracy drops when applied to networks for most tasks. In this work, we present a highly generalized, distribution-aware approach to binarizing deep networks that allows us to retain the a","authors_text":"Ameya Prabhu, Anoop Namboodiri, Rohit Gajawada, Sri Aurobindo Munagala, Vishal Batchu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-04-09T12:31:07Z","title":"Distribution-Aware Binarization of Neural Networks for Sketch Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02941","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:b0ed1c381bf3955b6be17319dae506067af7aeb45078cbe944e92d176a8c62e9","target":"record","created_at":"2026-05-18T00:18:57Z","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":"a0a2fca721c17219d03777fb2ff314473b1e1e2f4ed7d72945e46659bc7ea492","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-04-09T12:31:07Z","title_canon_sha256":"ba315e7890a3a21e184fc1ceb893b65914cd3842ad46fa89626ea437e63672a0"},"schema_version":"1.0","source":{"id":"1804.02941","kind":"arxiv","version":1}},"canonical_sha256":"00c255839990c012f481823fdaf34a4a30f0693b41b67b6f0abfca32e5c37bea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00c255839990c012f481823fdaf34a4a30f0693b41b67b6f0abfca32e5c37bea","first_computed_at":"2026-05-18T00:18:57.897410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:57.897410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fv07O1piNZrqkzSPT9F8kLsbIL0S3TaFLrIEYchBqxNwb+Sn7wz1gjuL2aGpR/u30u8HApwcehWPEErLk6EMBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:57.898136Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.02941","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0ed1c381bf3955b6be17319dae506067af7aeb45078cbe944e92d176a8c62e9","sha256:1ec620b12ba812c08d65a15ce9d8211cdc734a24a90eb7107ab9a879285a0b0d"],"state_sha256":"84cdd4a7c2b9ef3c43e362ea99bb4bc5344075dff22ab2f45ddba660bb593efe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YSB49g9xSXj4AwRB1FrniIFPUOxIvif223bfkEwPlqXCH05xqrUD6jzTGjfTrQS2sICgOgA4sGKfQL2qmq/nCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T03:54:34.857931Z","bundle_sha256":"79e013f360cad3a5ff56850ed41a5eaca757f24d1af37232218442b48f274d46"}}