{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:KNH4VFXROMBZ6DB7CZVO6L35NE","short_pith_number":"pith:KNH4VFXR","canonical_record":{"source":{"id":"1609.00222","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-01T13:08:47Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"b94b4c7c9cc4532f7316cd9d72a088831e2dad20303f75ef4b8ed528ca1db015","abstract_canon_sha256":"8c2f2cd5267afdd4e46ec8b88321d2f9ea8bdacf011a5f1067a3d87ec2390396"},"schema_version":"1.0"},"canonical_sha256":"534fca96f173039f0c3f166aef2f7d691d4fa28144f51e8e416918c549c6d722","source":{"kind":"arxiv","id":"1609.00222","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.00222","created_at":"2026-05-18T00:49:58Z"},{"alias_kind":"arxiv_version","alias_value":"1609.00222v2","created_at":"2026-05-18T00:49:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.00222","created_at":"2026-05-18T00:49:58Z"},{"alias_kind":"pith_short_12","alias_value":"KNH4VFXROMBZ","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"KNH4VFXROMBZ6DB7","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"KNH4VFXR","created_at":"2026-05-18T12:30:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:KNH4VFXROMBZ6DB7CZVO6L35NE","target":"record","payload":{"canonical_record":{"source":{"id":"1609.00222","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-01T13:08:47Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"b94b4c7c9cc4532f7316cd9d72a088831e2dad20303f75ef4b8ed528ca1db015","abstract_canon_sha256":"8c2f2cd5267afdd4e46ec8b88321d2f9ea8bdacf011a5f1067a3d87ec2390396"},"schema_version":"1.0"},"canonical_sha256":"534fca96f173039f0c3f166aef2f7d691d4fa28144f51e8e416918c549c6d722","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:58.547692Z","signature_b64":"QxRLrTe80xOgVeL+v5lfQuqgkLT0qvwT4Ikz9u8afaVKRCeses0XfP2D6j7ESW2HEuz50F38jIlp5RzGZKR9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"534fca96f173039f0c3f166aef2f7d691d4fa28144f51e8e416918c549c6d722","last_reissued_at":"2026-05-18T00:49:58.547061Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:58.547061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.00222","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":"2026-05-18T00:49:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XgLoV0CQylS+k/FKjnT28KHQ/mjKgxRACpFxo233QjA+2yIo5tfqZ//EOtUYDVYZP0Y6G6WMf6nTEJ7pFZgiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T15:08:16.570472Z"},"content_sha256":"4db634a55ba949990811c7b5787f6b86935b1bfbdc3f90cd3ef9fbb78f5e5f82","schema_version":"1.0","event_id":"sha256:4db634a55ba949990811c7b5787f6b86935b1bfbdc3f90cd3ef9fbb78f5e5f82"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:KNH4VFXROMBZ6DB7CZVO6L35NE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ternary Neural Networks for Resource-Efficient AI Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Adrien Prost-Boucle, Fr\\'ed\\'eric P\\'etrot, Hande Alemdar, Vincent Leroy","submitted_at":"2016-09-01T13:08:47Z","abstract_excerpt":"The computation and storage requirements for Deep Neural Networks (DNNs) are usually high. This issue limits their deployability on ubiquitous computing devices such as smart phones, wearables and autonomous drones. In this paper, we propose ternary neural networks (TNNs) in order to make deep learning more resource-efficient. We train these TNNs using a teacher-student approach based on a novel, layer-wise greedy methodology. Thanks to our two-stage training procedure, the teacher network is still able to use state-of-the-art methods such as dropout and batch normalization to increase accurac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.00222","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":"2026-05-18T00:49:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Nni2xGfsu+agWY/G4J/7GHNmyifYUZ307IC9BaUItBhPKmGak3oVezwEL8w3iXLKhzkIHH7eyau4JCvr4I4BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T15:08:16.570821Z"},"content_sha256":"69e2cfb670f776950253371fa32a638e950009916b479b47a7bb519321b1e461","schema_version":"1.0","event_id":"sha256:69e2cfb670f776950253371fa32a638e950009916b479b47a7bb519321b1e461"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KNH4VFXROMBZ6DB7CZVO6L35NE/bundle.json","state_url":"https://pith.science/pith/KNH4VFXROMBZ6DB7CZVO6L35NE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KNH4VFXROMBZ6DB7CZVO6L35NE/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":"2026-06-23T15:08:16Z","links":{"resolver":"https://pith.science/pith/KNH4VFXROMBZ6DB7CZVO6L35NE","bundle":"https://pith.science/pith/KNH4VFXROMBZ6DB7CZVO6L35NE/bundle.json","state":"https://pith.science/pith/KNH4VFXROMBZ6DB7CZVO6L35NE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KNH4VFXROMBZ6DB7CZVO6L35NE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:KNH4VFXROMBZ6DB7CZVO6L35NE","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":"8c2f2cd5267afdd4e46ec8b88321d2f9ea8bdacf011a5f1067a3d87ec2390396","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-01T13:08:47Z","title_canon_sha256":"b94b4c7c9cc4532f7316cd9d72a088831e2dad20303f75ef4b8ed528ca1db015"},"schema_version":"1.0","source":{"id":"1609.00222","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.00222","created_at":"2026-05-18T00:49:58Z"},{"alias_kind":"arxiv_version","alias_value":"1609.00222v2","created_at":"2026-05-18T00:49:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.00222","created_at":"2026-05-18T00:49:58Z"},{"alias_kind":"pith_short_12","alias_value":"KNH4VFXROMBZ","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"KNH4VFXROMBZ6DB7","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"KNH4VFXR","created_at":"2026-05-18T12:30:25Z"}],"graph_snapshots":[{"event_id":"sha256:69e2cfb670f776950253371fa32a638e950009916b479b47a7bb519321b1e461","target":"graph","created_at":"2026-05-18T00:49:58Z","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":"The computation and storage requirements for Deep Neural Networks (DNNs) are usually high. This issue limits their deployability on ubiquitous computing devices such as smart phones, wearables and autonomous drones. In this paper, we propose ternary neural networks (TNNs) in order to make deep learning more resource-efficient. We train these TNNs using a teacher-student approach based on a novel, layer-wise greedy methodology. Thanks to our two-stage training procedure, the teacher network is still able to use state-of-the-art methods such as dropout and batch normalization to increase accurac","authors_text":"Adrien Prost-Boucle, Fr\\'ed\\'eric P\\'etrot, Hande Alemdar, Vincent Leroy","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-01T13:08:47Z","title":"Ternary Neural Networks for Resource-Efficient AI Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.00222","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":"sha256:4db634a55ba949990811c7b5787f6b86935b1bfbdc3f90cd3ef9fbb78f5e5f82","target":"record","created_at":"2026-05-18T00:49:58Z","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":"8c2f2cd5267afdd4e46ec8b88321d2f9ea8bdacf011a5f1067a3d87ec2390396","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-01T13:08:47Z","title_canon_sha256":"b94b4c7c9cc4532f7316cd9d72a088831e2dad20303f75ef4b8ed528ca1db015"},"schema_version":"1.0","source":{"id":"1609.00222","kind":"arxiv","version":2}},"canonical_sha256":"534fca96f173039f0c3f166aef2f7d691d4fa28144f51e8e416918c549c6d722","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"534fca96f173039f0c3f166aef2f7d691d4fa28144f51e8e416918c549c6d722","first_computed_at":"2026-05-18T00:49:58.547061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:49:58.547061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QxRLrTe80xOgVeL+v5lfQuqgkLT0qvwT4Ikz9u8afaVKRCeses0XfP2D6j7ESW2HEuz50F38jIlp5RzGZKR9BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:49:58.547692Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.00222","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4db634a55ba949990811c7b5787f6b86935b1bfbdc3f90cd3ef9fbb78f5e5f82","sha256:69e2cfb670f776950253371fa32a638e950009916b479b47a7bb519321b1e461"],"state_sha256":"9da69831c9c9fe7d883d27377d341b5925e082555888836343b926be684dec10"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"on+XAXFZrGKH5jNNHuyBj2CuRRfh7NE8xDcdQPdKfnScjbhpeIE7oaQRCZ+y0qavMnM7Jx9b4g4Rv90obTBMCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-23T15:08:16.572774Z","bundle_sha256":"fd7bae9bc50df7e84ac3a668d21dcb3106f0d8e0e27089899bfe8c499f1937f1"}}