{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:IG4GIVS3TOMFB4PB4JBLMUEEKU","short_pith_number":"pith:IG4GIVS3","canonical_record":{"source":{"id":"1906.06033","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-14T05:53:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e0b69b247b1f74d68de591dcb6fec89954b531026663fee767bf076d8ca0fc2f","abstract_canon_sha256":"6388bd96c98e1ffd65fff4e713fc4cb42ca41109747113e478dbe49ce3133196"},"schema_version":"1.0"},"canonical_sha256":"41b864565b9b9850f1e1e242b650845539011322d6ad4d71cdca0c4ef95b85dd","source":{"kind":"arxiv","id":"1906.06033","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.06033","created_at":"2026-07-05T00:45:06Z"},{"alias_kind":"arxiv_version","alias_value":"1906.06033v4","created_at":"2026-07-05T00:45:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06033","created_at":"2026-07-05T00:45:06Z"},{"alias_kind":"pith_short_12","alias_value":"IG4GIVS3TOMF","created_at":"2026-07-05T00:45:06Z"},{"alias_kind":"pith_short_16","alias_value":"IG4GIVS3TOMFB4PB","created_at":"2026-07-05T00:45:06Z"},{"alias_kind":"pith_short_8","alias_value":"IG4GIVS3","created_at":"2026-07-05T00:45:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:IG4GIVS3TOMFB4PB4JBLMUEEKU","target":"record","payload":{"canonical_record":{"source":{"id":"1906.06033","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-14T05:53:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e0b69b247b1f74d68de591dcb6fec89954b531026663fee767bf076d8ca0fc2f","abstract_canon_sha256":"6388bd96c98e1ffd65fff4e713fc4cb42ca41109747113e478dbe49ce3133196"},"schema_version":"1.0"},"canonical_sha256":"41b864565b9b9850f1e1e242b650845539011322d6ad4d71cdca0c4ef95b85dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:45:06.245787Z","signature_b64":"rKwFINOsbsY/bDFtFxRbrQwHlLtpEflX++eqwwn990JLNxfnUIN9htrjJi+oXZzS3/+IwOE6I9/THJXCp6EzDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41b864565b9b9850f1e1e242b650845539011322d6ad4d71cdca0c4ef95b85dd","last_reissued_at":"2026-07-05T00:45:06.245374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:45:06.245374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.06033","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:45:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WfDkuE+2PHrqE39S++0uW49a1guRlDPIiS2w2AWsrP9OHktgG8tZYIkDth4eSI0l42rkD4yrIM+LYMOuMKp4Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:39:33.526478Z"},"content_sha256":"6daa24df73c085db98b7840405d9113eacc22c6c443d1e0034138123f5939b2b","schema_version":"1.0","event_id":"sha256:6daa24df73c085db98b7840405d9113eacc22c6c443d1e0034138123f5939b2b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:IG4GIVS3TOMFB4PB4JBLMUEEKU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Divide and Conquer: Leveraging Intermediate Feature Representations for Quantized Training of Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed T. Elthakeb, Alex Cloninger, Hadi Esmaeilzadeh, Prannoy Pilligundla","submitted_at":"2019-06-14T05:53:30Z","abstract_excerpt":"The deep layers of modern neural networks extract a rather rich set of features as an input propagates through the network. This paper sets out to harvest these rich intermediate representations for quantization with minimal accuracy loss while significantly reducing the memory footprint and compute intensity of the DNN. This paper utilizes knowledge distillation through teacher-student paradigm (Hinton et al., 2015) in a novel setting that exploits the feature extraction capability of DNNs for higher-accuracy quantization. As such, our algorithm logically divides a pretrained full-precision D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06033","kind":"arxiv","version":4},"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/1906.06033/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":"2026-07-05T00:45:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3V0emO6nKINi3KhKOuyt0Nu7KNsnbyGYf40pqz4pbPq7cjoucEdhbTU7mlAPAXBmVYStw4o/pimmHbKQ5Bi7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:39:33.526859Z"},"content_sha256":"be5d1e1c340bd604e5689c320958d514e0b5238a3ca1c6b6e3dc75fda1948a07","schema_version":"1.0","event_id":"sha256:be5d1e1c340bd604e5689c320958d514e0b5238a3ca1c6b6e3dc75fda1948a07"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IG4GIVS3TOMFB4PB4JBLMUEEKU/bundle.json","state_url":"https://pith.science/pith/IG4GIVS3TOMFB4PB4JBLMUEEKU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IG4GIVS3TOMFB4PB4JBLMUEEKU/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":"2026-07-06T18:39:33Z","links":{"resolver":"https://pith.science/pith/IG4GIVS3TOMFB4PB4JBLMUEEKU","bundle":"https://pith.science/pith/IG4GIVS3TOMFB4PB4JBLMUEEKU/bundle.json","state":"https://pith.science/pith/IG4GIVS3TOMFB4PB4JBLMUEEKU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IG4GIVS3TOMFB4PB4JBLMUEEKU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:IG4GIVS3TOMFB4PB4JBLMUEEKU","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":"6388bd96c98e1ffd65fff4e713fc4cb42ca41109747113e478dbe49ce3133196","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-14T05:53:30Z","title_canon_sha256":"e0b69b247b1f74d68de591dcb6fec89954b531026663fee767bf076d8ca0fc2f"},"schema_version":"1.0","source":{"id":"1906.06033","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.06033","created_at":"2026-07-05T00:45:06Z"},{"alias_kind":"arxiv_version","alias_value":"1906.06033v4","created_at":"2026-07-05T00:45:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06033","created_at":"2026-07-05T00:45:06Z"},{"alias_kind":"pith_short_12","alias_value":"IG4GIVS3TOMF","created_at":"2026-07-05T00:45:06Z"},{"alias_kind":"pith_short_16","alias_value":"IG4GIVS3TOMFB4PB","created_at":"2026-07-05T00:45:06Z"},{"alias_kind":"pith_short_8","alias_value":"IG4GIVS3","created_at":"2026-07-05T00:45:06Z"}],"graph_snapshots":[{"event_id":"sha256:be5d1e1c340bd604e5689c320958d514e0b5238a3ca1c6b6e3dc75fda1948a07","target":"graph","created_at":"2026-07-05T00:45:06Z","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/1906.06033/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The deep layers of modern neural networks extract a rather rich set of features as an input propagates through the network. This paper sets out to harvest these rich intermediate representations for quantization with minimal accuracy loss while significantly reducing the memory footprint and compute intensity of the DNN. This paper utilizes knowledge distillation through teacher-student paradigm (Hinton et al., 2015) in a novel setting that exploits the feature extraction capability of DNNs for higher-accuracy quantization. As such, our algorithm logically divides a pretrained full-precision D","authors_text":"Ahmed T. Elthakeb, Alex Cloninger, Hadi Esmaeilzadeh, Prannoy Pilligundla","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-14T05:53:30Z","title":"Divide and Conquer: Leveraging Intermediate Feature Representations for Quantized Training of Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06033","kind":"arxiv","version":4},"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":"sha256:6daa24df73c085db98b7840405d9113eacc22c6c443d1e0034138123f5939b2b","target":"record","created_at":"2026-07-05T00:45:06Z","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":"6388bd96c98e1ffd65fff4e713fc4cb42ca41109747113e478dbe49ce3133196","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-14T05:53:30Z","title_canon_sha256":"e0b69b247b1f74d68de591dcb6fec89954b531026663fee767bf076d8ca0fc2f"},"schema_version":"1.0","source":{"id":"1906.06033","kind":"arxiv","version":4}},"canonical_sha256":"41b864565b9b9850f1e1e242b650845539011322d6ad4d71cdca0c4ef95b85dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41b864565b9b9850f1e1e242b650845539011322d6ad4d71cdca0c4ef95b85dd","first_computed_at":"2026-07-05T00:45:06.245374Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:45:06.245374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rKwFINOsbsY/bDFtFxRbrQwHlLtpEflX++eqwwn990JLNxfnUIN9htrjJi+oXZzS3/+IwOE6I9/THJXCp6EzDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:45:06.245787Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.06033","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6daa24df73c085db98b7840405d9113eacc22c6c443d1e0034138123f5939b2b","sha256:be5d1e1c340bd604e5689c320958d514e0b5238a3ca1c6b6e3dc75fda1948a07"],"state_sha256":"18aa9bb832dcbe05705753c45bcb8c55198ce1c9982e4f9509c7f29b3b40a2d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CWZn4RqplUyXYeMne23VzIXaRwEpSgedq5zMTK1zqJNus5aFmQq/ilM8pA3SZavvvQ2SKOsuWhXX8W6QWZytBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:39:33.528810Z","bundle_sha256":"94916002fb2f239c2708c8dfcf9ac8451b24fa84c5571a96a545a90092efda76"}}