{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:OPY7RFJFWG3L7SX7OQIVL6GBH3","short_pith_number":"pith:OPY7RFJF","canonical_record":{"source":{"id":"1612.00694","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-01T13:16:00Z","cross_cats_sorted":[],"title_canon_sha256":"b3b89e2018c7b5bc1cc1bb329c711a3c656d8f8d230a7e5c4a6f424d52e1b212","abstract_canon_sha256":"f14ff19c6a13ac86506b782e5823e7f78570a6773add6dfc36ad34c49ec2bb3d"},"schema_version":"1.0"},"canonical_sha256":"73f1f89525b1b6bfcaff741155f8c13ee19d546380fb8f5a6ed764ab7ba12250","source":{"kind":"arxiv","id":"1612.00694","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.00694","created_at":"2026-05-18T00:50:28Z"},{"alias_kind":"arxiv_version","alias_value":"1612.00694v2","created_at":"2026-05-18T00:50:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.00694","created_at":"2026-05-18T00:50:28Z"},{"alias_kind":"pith_short_12","alias_value":"OPY7RFJFWG3L","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OPY7RFJFWG3L7SX7","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OPY7RFJF","created_at":"2026-05-18T12:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:OPY7RFJFWG3L7SX7OQIVL6GBH3","target":"record","payload":{"canonical_record":{"source":{"id":"1612.00694","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-01T13:16:00Z","cross_cats_sorted":[],"title_canon_sha256":"b3b89e2018c7b5bc1cc1bb329c711a3c656d8f8d230a7e5c4a6f424d52e1b212","abstract_canon_sha256":"f14ff19c6a13ac86506b782e5823e7f78570a6773add6dfc36ad34c49ec2bb3d"},"schema_version":"1.0"},"canonical_sha256":"73f1f89525b1b6bfcaff741155f8c13ee19d546380fb8f5a6ed764ab7ba12250","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:28.856741Z","signature_b64":"moOUfMTiu1SZOipnfif+4X5TEMtMvJU3OqCGCiw1BRfq5Z6Ja4o92y8ozub3KK7KqUy1MoNHW88h6yPTY9t3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73f1f89525b1b6bfcaff741155f8c13ee19d546380fb8f5a6ed764ab7ba12250","last_reissued_at":"2026-05-18T00:50:28.856003Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:28.856003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.00694","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":"2026-05-18T00:50:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xk9ZojOmerrRVV2Tajy4sCDabLHfBoKqri8ZlPI39QuSDxQOCdcdDb3LCxpr5prq0iG5q3uwm0eeWbb92xN+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T01:06:09.387702Z"},"content_sha256":"9a7fcc105c6f6d7902ca0d5dfad6780d65c537b8e09a552cfcb780d0d23de419","schema_version":"1.0","event_id":"sha256:9a7fcc105c6f6d7902ca0d5dfad6780d65c537b8e09a552cfcb780d0d23de419"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:OPY7RFJFWG3L7SX7OQIVL6GBH3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongliang Xie, Hong Luo, Huazhong Yang, Huizi Mao, Junlong Kang, Song Han, Song Yao, William J. Dally, Xin Li, Yiming Hu, Yubin Li, Yu Wang","submitted_at":"2016-12-01T13:16:00Z","abstract_excerpt":"Long Short-Term Memory (LSTM) is widely used in speech recognition. In order to achieve higher prediction accuracy, machine learning scientists have built larger and larger models. Such large model is both computation intensive and memory intensive. Deploying such bulky model results in high power consumption and leads to high total cost of ownership (TCO) of a data center. In order to speedup the prediction and make it energy efficient, we first propose a load-balance-aware pruning method that can compress the LSTM model size by 20x (10x from pruning and 2x from quantization) with negligible "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.00694","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":"2026-05-18T00:50:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Ghi3lg+caJC0JIXMCeM3DyCDFFjH68SpyqB7Sy6FXTI5hEOxSjsI4iVN/J8R+829Pxbry8A5XFnfPjvm3UHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T01:06:09.388335Z"},"content_sha256":"c785d6c9038995d2671082739a5ff8b33279078423420e772fc81f8c35c34119","schema_version":"1.0","event_id":"sha256:c785d6c9038995d2671082739a5ff8b33279078423420e772fc81f8c35c34119"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OPY7RFJFWG3L7SX7OQIVL6GBH3/bundle.json","state_url":"https://pith.science/pith/OPY7RFJFWG3L7SX7OQIVL6GBH3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OPY7RFJFWG3L7SX7OQIVL6GBH3/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":"2026-06-05T01:06:09Z","links":{"resolver":"https://pith.science/pith/OPY7RFJFWG3L7SX7OQIVL6GBH3","bundle":"https://pith.science/pith/OPY7RFJFWG3L7SX7OQIVL6GBH3/bundle.json","state":"https://pith.science/pith/OPY7RFJFWG3L7SX7OQIVL6GBH3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OPY7RFJFWG3L7SX7OQIVL6GBH3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:OPY7RFJFWG3L7SX7OQIVL6GBH3","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":"f14ff19c6a13ac86506b782e5823e7f78570a6773add6dfc36ad34c49ec2bb3d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-01T13:16:00Z","title_canon_sha256":"b3b89e2018c7b5bc1cc1bb329c711a3c656d8f8d230a7e5c4a6f424d52e1b212"},"schema_version":"1.0","source":{"id":"1612.00694","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.00694","created_at":"2026-05-18T00:50:28Z"},{"alias_kind":"arxiv_version","alias_value":"1612.00694v2","created_at":"2026-05-18T00:50:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.00694","created_at":"2026-05-18T00:50:28Z"},{"alias_kind":"pith_short_12","alias_value":"OPY7RFJFWG3L","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OPY7RFJFWG3L7SX7","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OPY7RFJF","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:c785d6c9038995d2671082739a5ff8b33279078423420e772fc81f8c35c34119","target":"graph","created_at":"2026-05-18T00:50:28Z","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":"Long Short-Term Memory (LSTM) is widely used in speech recognition. In order to achieve higher prediction accuracy, machine learning scientists have built larger and larger models. Such large model is both computation intensive and memory intensive. Deploying such bulky model results in high power consumption and leads to high total cost of ownership (TCO) of a data center. In order to speedup the prediction and make it energy efficient, we first propose a load-balance-aware pruning method that can compress the LSTM model size by 20x (10x from pruning and 2x from quantization) with negligible ","authors_text":"Dongliang Xie, Hong Luo, Huazhong Yang, Huizi Mao, Junlong Kang, Song Han, Song Yao, William J. Dally, Xin Li, Yiming Hu, Yubin Li, Yu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-01T13:16:00Z","title":"ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.00694","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":"sha256:9a7fcc105c6f6d7902ca0d5dfad6780d65c537b8e09a552cfcb780d0d23de419","target":"record","created_at":"2026-05-18T00:50:28Z","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":"f14ff19c6a13ac86506b782e5823e7f78570a6773add6dfc36ad34c49ec2bb3d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-01T13:16:00Z","title_canon_sha256":"b3b89e2018c7b5bc1cc1bb329c711a3c656d8f8d230a7e5c4a6f424d52e1b212"},"schema_version":"1.0","source":{"id":"1612.00694","kind":"arxiv","version":2}},"canonical_sha256":"73f1f89525b1b6bfcaff741155f8c13ee19d546380fb8f5a6ed764ab7ba12250","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73f1f89525b1b6bfcaff741155f8c13ee19d546380fb8f5a6ed764ab7ba12250","first_computed_at":"2026-05-18T00:50:28.856003Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:28.856003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"moOUfMTiu1SZOipnfif+4X5TEMtMvJU3OqCGCiw1BRfq5Z6Ja4o92y8ozub3KK7KqUy1MoNHW88h6yPTY9t3Cw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:28.856741Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.00694","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a7fcc105c6f6d7902ca0d5dfad6780d65c537b8e09a552cfcb780d0d23de419","sha256:c785d6c9038995d2671082739a5ff8b33279078423420e772fc81f8c35c34119"],"state_sha256":"47a2278824b2de554e562feff50c23e5483627543fcb5bdb75ba4da0cf095509"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tBjQekr5ii0p8vMU93npESqmdWJ8XzSnH1sLuVeI0p4CwiSAjJ3KWjeoXDiCDv/qwNVnQmivxXFIclr8Q8n0Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T01:06:09.394512Z","bundle_sha256":"164e8599346070bd61e12d0375db4c351fbee3acfa2cd6ddbd8ce0be52fb8c77"}}