{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:UV337HB7VAJZSRDQGDYFQQIER4","short_pith_number":"pith:UV337HB7","canonical_record":{"source":{"id":"1707.09068","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-07-27T22:56:13Z","cross_cats_sorted":[],"title_canon_sha256":"8783c11feb705791255c65444e7f004c567dd86f1599552f1ef63bda0ccfd181","abstract_canon_sha256":"ccf172605a22445d185b3e5913f31c114a631dfb4828495cbaf3ecf76c2b5677"},"schema_version":"1.0"},"canonical_sha256":"a577bf9c3fa81399447030f05841048f03e60ac89d24850a72299849ca6b19b1","source":{"kind":"arxiv","id":"1707.09068","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.09068","created_at":"2026-05-18T00:39:17Z"},{"alias_kind":"arxiv_version","alias_value":"1707.09068v1","created_at":"2026-05-18T00:39:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09068","created_at":"2026-05-18T00:39:17Z"},{"alias_kind":"pith_short_12","alias_value":"UV337HB7VAJZ","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"UV337HB7VAJZSRDQ","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"UV337HB7","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:UV337HB7VAJZSRDQGDYFQQIER4","target":"record","payload":{"canonical_record":{"source":{"id":"1707.09068","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-07-27T22:56:13Z","cross_cats_sorted":[],"title_canon_sha256":"8783c11feb705791255c65444e7f004c567dd86f1599552f1ef63bda0ccfd181","abstract_canon_sha256":"ccf172605a22445d185b3e5913f31c114a631dfb4828495cbaf3ecf76c2b5677"},"schema_version":"1.0"},"canonical_sha256":"a577bf9c3fa81399447030f05841048f03e60ac89d24850a72299849ca6b19b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:17.194969Z","signature_b64":"VRu3jW4zGEo9cSsF37/LrCXRJixzSDaN8mI9b0lsFvIVQXGCLerbgNd2JTv8cVM0NR5tAvkJj7tqnZ2YmU1NDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a577bf9c3fa81399447030f05841048f03e60ac89d24850a72299849ca6b19b1","last_reissued_at":"2026-05-18T00:39:17.194364Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:17.194364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.09068","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":"2026-05-18T00:39:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B2IRT4Oqh282RuH9TB1UykTkLuJ+0YrmQ5iAAxGPlL8DuUSACmXPNMm4+nQCxJsQwPtFDnh4wFomp0QrHKmsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:17:52.514265Z"},"content_sha256":"cb406ba828f81fa964657e0b59af3865bcf54eb420577235e02fc352c4e6a158","schema_version":"1.0","event_id":"sha256:cb406ba828f81fa964657e0b59af3865bcf54eb420577235e02fc352c4e6a158"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:UV337HB7VAJZSRDQGDYFQQIER4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tartan: Accelerating Fully-Connected and Convolutional Layers in Deep Learning Networks by Exploiting Numerical Precision Variability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Alberto Delmas, Andreas Moshovos, Patrick Judd, Sayeh Sharify","submitted_at":"2017-07-27T22:56:13Z","abstract_excerpt":"Tartan (TRT), a hardware accelerator for inference with Deep Neural Networks (DNNs), is presented and evaluated on Convolutional Neural Networks. TRT exploits the variable per layer precision requirements of DNNs to deliver execution time that is proportional to the precision p in bits used per layer for convolutional and fully-connected layers. Prior art has demonstrated an accelerator with the same execution performance only for convolutional layers. Experiments on image classification CNNs show that on average across all networks studied, TRT outperforms a state-of-the-art bit-parallel acce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09068","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":"2026-05-18T00:39:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gvFCplvqXzjL+KMlffY6f/w9mAIF3orQFmLaxjWz3+52h8iTkGNSqqvMSHkZDC5h1IJ9Y0n38cpj3Kq9wwUoDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:17:52.514645Z"},"content_sha256":"d6695959df1162a45b2329988f59c96f9cd00e567cc54769e4986e7e2c5786c7","schema_version":"1.0","event_id":"sha256:d6695959df1162a45b2329988f59c96f9cd00e567cc54769e4986e7e2c5786c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UV337HB7VAJZSRDQGDYFQQIER4/bundle.json","state_url":"https://pith.science/pith/UV337HB7VAJZSRDQGDYFQQIER4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UV337HB7VAJZSRDQGDYFQQIER4/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":"2026-06-03T20:17:52Z","links":{"resolver":"https://pith.science/pith/UV337HB7VAJZSRDQGDYFQQIER4","bundle":"https://pith.science/pith/UV337HB7VAJZSRDQGDYFQQIER4/bundle.json","state":"https://pith.science/pith/UV337HB7VAJZSRDQGDYFQQIER4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UV337HB7VAJZSRDQGDYFQQIER4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:UV337HB7VAJZSRDQGDYFQQIER4","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":"ccf172605a22445d185b3e5913f31c114a631dfb4828495cbaf3ecf76c2b5677","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-07-27T22:56:13Z","title_canon_sha256":"8783c11feb705791255c65444e7f004c567dd86f1599552f1ef63bda0ccfd181"},"schema_version":"1.0","source":{"id":"1707.09068","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.09068","created_at":"2026-05-18T00:39:17Z"},{"alias_kind":"arxiv_version","alias_value":"1707.09068v1","created_at":"2026-05-18T00:39:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09068","created_at":"2026-05-18T00:39:17Z"},{"alias_kind":"pith_short_12","alias_value":"UV337HB7VAJZ","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"UV337HB7VAJZSRDQ","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"UV337HB7","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:d6695959df1162a45b2329988f59c96f9cd00e567cc54769e4986e7e2c5786c7","target":"graph","created_at":"2026-05-18T00:39:17Z","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":"Tartan (TRT), a hardware accelerator for inference with Deep Neural Networks (DNNs), is presented and evaluated on Convolutional Neural Networks. TRT exploits the variable per layer precision requirements of DNNs to deliver execution time that is proportional to the precision p in bits used per layer for convolutional and fully-connected layers. Prior art has demonstrated an accelerator with the same execution performance only for convolutional layers. Experiments on image classification CNNs show that on average across all networks studied, TRT outperforms a state-of-the-art bit-parallel acce","authors_text":"Alberto Delmas, Andreas Moshovos, Patrick Judd, Sayeh Sharify","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-07-27T22:56:13Z","title":"Tartan: Accelerating Fully-Connected and Convolutional Layers in Deep Learning Networks by Exploiting Numerical Precision Variability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09068","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:cb406ba828f81fa964657e0b59af3865bcf54eb420577235e02fc352c4e6a158","target":"record","created_at":"2026-05-18T00:39:17Z","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":"ccf172605a22445d185b3e5913f31c114a631dfb4828495cbaf3ecf76c2b5677","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-07-27T22:56:13Z","title_canon_sha256":"8783c11feb705791255c65444e7f004c567dd86f1599552f1ef63bda0ccfd181"},"schema_version":"1.0","source":{"id":"1707.09068","kind":"arxiv","version":1}},"canonical_sha256":"a577bf9c3fa81399447030f05841048f03e60ac89d24850a72299849ca6b19b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a577bf9c3fa81399447030f05841048f03e60ac89d24850a72299849ca6b19b1","first_computed_at":"2026-05-18T00:39:17.194364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:17.194364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VRu3jW4zGEo9cSsF37/LrCXRJixzSDaN8mI9b0lsFvIVQXGCLerbgNd2JTv8cVM0NR5tAvkJj7tqnZ2YmU1NDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:17.194969Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.09068","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb406ba828f81fa964657e0b59af3865bcf54eb420577235e02fc352c4e6a158","sha256:d6695959df1162a45b2329988f59c96f9cd00e567cc54769e4986e7e2c5786c7"],"state_sha256":"6c056fcb85fd273eaba453a68d84eafa6e304bb95dde801e30907d81b8e74797"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YZGILA7BP8sw7qKsKkSg/e6Qr/mc/NeQUm/BbV583bQn1FurSm1IBMGLqngaFZ6XgHruX2eIikeb99hMBb+uBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T20:17:52.516632Z","bundle_sha256":"39452f8ba442345d6ccaefa99005b64b18369e20f9572bc65b7c5add91b32661"}}