{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OU7GU65CCIF72QVT2M2XJQC75G","short_pith_number":"pith:OU7GU65C","canonical_record":{"source":{"id":"2411.05845","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-06T16:02:55Z","cross_cats_sorted":[],"title_canon_sha256":"687d3a71009c23a1158c5f287fbaebd047fa6f188f0fe92123a123dba2a8af21","abstract_canon_sha256":"11d4d0bd733151d5b22937a9dbb6e1769dcc3d6f8d127caff9d7ca91e815ef58"},"schema_version":"1.0"},"canonical_sha256":"753e6a7ba2120bfd42b3d33574c05fe9a96f35cb205c2d877c7467156e028037","source":{"kind":"arxiv","id":"2411.05845","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05845","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05845v1","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05845","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"pith_short_12","alias_value":"OU7GU65CCIF7","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"OU7GU65CCIF72QVT","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"OU7GU65C","created_at":"2026-07-05T09:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OU7GU65CCIF72QVT2M2XJQC75G","target":"record","payload":{"canonical_record":{"source":{"id":"2411.05845","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-06T16:02:55Z","cross_cats_sorted":[],"title_canon_sha256":"687d3a71009c23a1158c5f287fbaebd047fa6f188f0fe92123a123dba2a8af21","abstract_canon_sha256":"11d4d0bd733151d5b22937a9dbb6e1769dcc3d6f8d127caff9d7ca91e815ef58"},"schema_version":"1.0"},"canonical_sha256":"753e6a7ba2120bfd42b3d33574c05fe9a96f35cb205c2d877c7467156e028037","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:12.050631Z","signature_b64":"JFiLe4BnfopsN2IJclcyfH/DJ+5mTv1mfUIIvVzBFUvIdaVB2oAUNHUOxRj+iwUsa+BtMD9jmDJ0KWmpY48oDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"753e6a7ba2120bfd42b3d33574c05fe9a96f35cb205c2d877c7467156e028037","last_reissued_at":"2026-07-05T09:33:12.050110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:12.050110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.05845","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":"2026-07-05T09:33:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hTb/4Oe3euW4xR0781A/EsGOzKNndJiKnJ0DIJ/+9mz3JxAoL8OliNqA8aujxK27b3czJ0R5ZsFiEdad5vfFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:52:45.731966Z"},"content_sha256":"f8bccb3132130f0da632c1c55c10fcb9ff8b6eae04055c49c9a37c7e0fa09633","schema_version":"1.0","event_id":"sha256:f8bccb3132130f0da632c1c55c10fcb9ff8b6eae04055c49c9a37c7e0fa09633"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OU7GU65CCIF72QVT2M2XJQC75G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Precision Polarization: Simplifying Neural Network Inference with Dual-Level Precision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amit Ranjan Trivedi, Dinithi Jayasuriya, Maeesha Binte Hashem, Nastaran Darabi","submitted_at":"2024-11-06T16:02:55Z","abstract_excerpt":"We introduce a precision polarization scheme for DNN inference that utilizes only very low and very high precision levels, assigning low precision to the majority of network weights and activations while reserving high precision paths for targeted error compensation. This separation allows for distinct optimization of each precision level, thereby reducing memory and computation demands without compromising model accuracy. In the discussed approach, a floating-point model can be trained in the cloud and then downloaded to an edge device, where network weights and activations are directly quant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05845","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/2411.05845/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":"2026-07-05T09:33:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jaPTQzH4nxZS+9gvfyb6rLqvdr8pfOY+QF8llE70FgPBONVl8PKkCGGYPDM53j2imqS8gYa+cuH3MNLlhNggDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:52:45.732347Z"},"content_sha256":"2e2933230d60f890095fed7f3d0725d702a7c97a94ea45f9e19ebd6c8e10e5f8","schema_version":"1.0","event_id":"sha256:2e2933230d60f890095fed7f3d0725d702a7c97a94ea45f9e19ebd6c8e10e5f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OU7GU65CCIF72QVT2M2XJQC75G/bundle.json","state_url":"https://pith.science/pith/OU7GU65CCIF72QVT2M2XJQC75G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OU7GU65CCIF72QVT2M2XJQC75G/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":"2026-07-09T03:52:45Z","links":{"resolver":"https://pith.science/pith/OU7GU65CCIF72QVT2M2XJQC75G","bundle":"https://pith.science/pith/OU7GU65CCIF72QVT2M2XJQC75G/bundle.json","state":"https://pith.science/pith/OU7GU65CCIF72QVT2M2XJQC75G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OU7GU65CCIF72QVT2M2XJQC75G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OU7GU65CCIF72QVT2M2XJQC75G","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":"11d4d0bd733151d5b22937a9dbb6e1769dcc3d6f8d127caff9d7ca91e815ef58","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-06T16:02:55Z","title_canon_sha256":"687d3a71009c23a1158c5f287fbaebd047fa6f188f0fe92123a123dba2a8af21"},"schema_version":"1.0","source":{"id":"2411.05845","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05845","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05845v1","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05845","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"pith_short_12","alias_value":"OU7GU65CCIF7","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"OU7GU65CCIF72QVT","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"OU7GU65C","created_at":"2026-07-05T09:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:2e2933230d60f890095fed7f3d0725d702a7c97a94ea45f9e19ebd6c8e10e5f8","target":"graph","created_at":"2026-07-05T09:33:12Z","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/2411.05845/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a precision polarization scheme for DNN inference that utilizes only very low and very high precision levels, assigning low precision to the majority of network weights and activations while reserving high precision paths for targeted error compensation. This separation allows for distinct optimization of each precision level, thereby reducing memory and computation demands without compromising model accuracy. In the discussed approach, a floating-point model can be trained in the cloud and then downloaded to an edge device, where network weights and activations are directly quant","authors_text":"Amit Ranjan Trivedi, Dinithi Jayasuriya, Maeesha Binte Hashem, Nastaran Darabi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-06T16:02:55Z","title":"Neural Precision Polarization: Simplifying Neural Network Inference with Dual-Level Precision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05845","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:f8bccb3132130f0da632c1c55c10fcb9ff8b6eae04055c49c9a37c7e0fa09633","target":"record","created_at":"2026-07-05T09:33:12Z","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":"11d4d0bd733151d5b22937a9dbb6e1769dcc3d6f8d127caff9d7ca91e815ef58","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-06T16:02:55Z","title_canon_sha256":"687d3a71009c23a1158c5f287fbaebd047fa6f188f0fe92123a123dba2a8af21"},"schema_version":"1.0","source":{"id":"2411.05845","kind":"arxiv","version":1}},"canonical_sha256":"753e6a7ba2120bfd42b3d33574c05fe9a96f35cb205c2d877c7467156e028037","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"753e6a7ba2120bfd42b3d33574c05fe9a96f35cb205c2d877c7467156e028037","first_computed_at":"2026-07-05T09:33:12.050110Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:12.050110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JFiLe4BnfopsN2IJclcyfH/DJ+5mTv1mfUIIvVzBFUvIdaVB2oAUNHUOxRj+iwUsa+BtMD9jmDJ0KWmpY48oDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:12.050631Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.05845","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8bccb3132130f0da632c1c55c10fcb9ff8b6eae04055c49c9a37c7e0fa09633","sha256:2e2933230d60f890095fed7f3d0725d702a7c97a94ea45f9e19ebd6c8e10e5f8"],"state_sha256":"517e2627451d1b22fdf90083382f6b4ff7d45e82575ef8bbc1bd1cadb15de9a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TGmjz+dNCidYQMR4PRtp4JMdSXl3zUzM1JX3mKOwL8a5QguBTg4FWbd+NttaQ/v54bjep1RE5qc33bk/KH8VAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T03:52:45.734309Z","bundle_sha256":"4c530d1786dfb5661b99dd40a4a72c1bab9a18d2f4ac87d5f80b62d2518ff49d"}}