{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:Y4FMPITX7GI52RIQFVWGXF75LK","short_pith_number":"pith:Y4FMPITX","canonical_record":{"source":{"id":"1807.10251","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-26T17:22:29Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"6aae863bda97b8618d7ec4826e6647e86b0693884f00ff26bf69672d7747c289","abstract_canon_sha256":"a12e42799ce38363d73e25c3afe2e2bba25df6e56b961511a6f5fe06f04019a6"},"schema_version":"1.0"},"canonical_sha256":"c70ac7a277f991dd45102d6c6b97fd5a944d29f3a8381a1bcda9603699bafffe","source":{"kind":"arxiv","id":"1807.10251","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.10251","created_at":"2026-05-17T23:54:16Z"},{"alias_kind":"arxiv_version","alias_value":"1807.10251v3","created_at":"2026-05-17T23:54:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.10251","created_at":"2026-05-17T23:54:16Z"},{"alias_kind":"pith_short_12","alias_value":"Y4FMPITX7GI5","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Y4FMPITX7GI52RIQ","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Y4FMPITX","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:Y4FMPITX7GI52RIQFVWGXF75LK","target":"record","payload":{"canonical_record":{"source":{"id":"1807.10251","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-26T17:22:29Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"6aae863bda97b8618d7ec4826e6647e86b0693884f00ff26bf69672d7747c289","abstract_canon_sha256":"a12e42799ce38363d73e25c3afe2e2bba25df6e56b961511a6f5fe06f04019a6"},"schema_version":"1.0"},"canonical_sha256":"c70ac7a277f991dd45102d6c6b97fd5a944d29f3a8381a1bcda9603699bafffe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:16.299376Z","signature_b64":"i9q/xRRXhz8QZOh3gadFi3gN+/XELIhCxMr+MUrAuO86eLIxM1EMtvCsqN8g62baQ3yW7GZXCbBioY2KBcucDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c70ac7a277f991dd45102d6c6b97fd5a944d29f3a8381a1bcda9603699bafffe","last_reissued_at":"2026-05-17T23:54:16.298828Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:16.298828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.10251","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:54:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TIJlzlXawwSTifjMjCds65xTRrBqwuvJxXBklc9b0o4fZGLk+jnLthhW+SeXZA0ap9QbqqB7HjAsIcxpzKhKDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T10:21:56.339294Z"},"content_sha256":"7e67ccd3b76a18b09331169a365a7051acbcdc150eabf1755a3ece6713c55351","schema_version":"1.0","event_id":"sha256:7e67ccd3b76a18b09331169a365a7051acbcdc150eabf1755a3ece6713c55351"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:Y4FMPITX7GI52RIQFVWGXF75LK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aggregated Learning: A Deep Learning Framework Based on Information-Bottleneck Vector Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ali Al-Bashabsheh, Hongyu Guo, Richong Zhang, Yongyi Mao","submitted_at":"2018-07-26T17:22:29Z","abstract_excerpt":"Based on the notion of information bottleneck (IB), we formulate a quantization problem called \"IB quantization\". We show that IB quantization is equivalent to learning based on the IB principle. Under this equivalence, the standard neural network models can be viewed as scalar (single sample) IB quantizers. It is known, from conventional rate-distortion theory, that scalar quantizers are inferior to vector (multi-sample) quantizers. Such a deficiency then inspires us to develop a novel learning framework, AgrLearn, that corresponds to vector IB quantizers for learning with neural networks. Un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.10251","kind":"arxiv","version":3},"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":"2026-05-17T23:54:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/XBfMdQj9knynfk3EqC9CaXyzUqXpvgU7mJJLZZ0SzRN/eVEc1RKkieCAPcrkH2DPbP9LzVXOw3ocDI+ZM0jDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T10:21:56.340017Z"},"content_sha256":"98664f40209df3a77df4df964c1da4fb37db08ad309ede8e06c5598015f328e1","schema_version":"1.0","event_id":"sha256:98664f40209df3a77df4df964c1da4fb37db08ad309ede8e06c5598015f328e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y4FMPITX7GI52RIQFVWGXF75LK/bundle.json","state_url":"https://pith.science/pith/Y4FMPITX7GI52RIQFVWGXF75LK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y4FMPITX7GI52RIQFVWGXF75LK/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":"2026-05-25T10:21:56Z","links":{"resolver":"https://pith.science/pith/Y4FMPITX7GI52RIQFVWGXF75LK","bundle":"https://pith.science/pith/Y4FMPITX7GI52RIQFVWGXF75LK/bundle.json","state":"https://pith.science/pith/Y4FMPITX7GI52RIQFVWGXF75LK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y4FMPITX7GI52RIQFVWGXF75LK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Y4FMPITX7GI52RIQFVWGXF75LK","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":"a12e42799ce38363d73e25c3afe2e2bba25df6e56b961511a6f5fe06f04019a6","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-26T17:22:29Z","title_canon_sha256":"6aae863bda97b8618d7ec4826e6647e86b0693884f00ff26bf69672d7747c289"},"schema_version":"1.0","source":{"id":"1807.10251","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.10251","created_at":"2026-05-17T23:54:16Z"},{"alias_kind":"arxiv_version","alias_value":"1807.10251v3","created_at":"2026-05-17T23:54:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.10251","created_at":"2026-05-17T23:54:16Z"},{"alias_kind":"pith_short_12","alias_value":"Y4FMPITX7GI5","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Y4FMPITX7GI52RIQ","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Y4FMPITX","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:98664f40209df3a77df4df964c1da4fb37db08ad309ede8e06c5598015f328e1","target":"graph","created_at":"2026-05-17T23:54:16Z","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":"Based on the notion of information bottleneck (IB), we formulate a quantization problem called \"IB quantization\". We show that IB quantization is equivalent to learning based on the IB principle. Under this equivalence, the standard neural network models can be viewed as scalar (single sample) IB quantizers. It is known, from conventional rate-distortion theory, that scalar quantizers are inferior to vector (multi-sample) quantizers. Such a deficiency then inspires us to develop a novel learning framework, AgrLearn, that corresponds to vector IB quantizers for learning with neural networks. Un","authors_text":"Ali Al-Bashabsheh, Hongyu Guo, Richong Zhang, Yongyi Mao","cross_cats":["cs.AI","cs.IT","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-26T17:22:29Z","title":"Aggregated Learning: A Deep Learning Framework Based on Information-Bottleneck Vector Quantization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.10251","kind":"arxiv","version":3},"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":"sha256:7e67ccd3b76a18b09331169a365a7051acbcdc150eabf1755a3ece6713c55351","target":"record","created_at":"2026-05-17T23:54:16Z","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":"a12e42799ce38363d73e25c3afe2e2bba25df6e56b961511a6f5fe06f04019a6","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-26T17:22:29Z","title_canon_sha256":"6aae863bda97b8618d7ec4826e6647e86b0693884f00ff26bf69672d7747c289"},"schema_version":"1.0","source":{"id":"1807.10251","kind":"arxiv","version":3}},"canonical_sha256":"c70ac7a277f991dd45102d6c6b97fd5a944d29f3a8381a1bcda9603699bafffe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c70ac7a277f991dd45102d6c6b97fd5a944d29f3a8381a1bcda9603699bafffe","first_computed_at":"2026-05-17T23:54:16.298828Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:16.298828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i9q/xRRXhz8QZOh3gadFi3gN+/XELIhCxMr+MUrAuO86eLIxM1EMtvCsqN8g62baQ3yW7GZXCbBioY2KBcucDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:16.299376Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.10251","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e67ccd3b76a18b09331169a365a7051acbcdc150eabf1755a3ece6713c55351","sha256:98664f40209df3a77df4df964c1da4fb37db08ad309ede8e06c5598015f328e1"],"state_sha256":"a74c61b51d3d359a9871dde9fa7741845bbc9ab617fef72c81c8ef13f7a9535b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mW5OG1CX2jgXhl2pH0GCVH61a1WuAtvthrDLQaAdkieljsnHfdscJqusaix2xgnr0uPkMr8FXF6xKJTmkS/zAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T10:21:56.343775Z","bundle_sha256":"f90347cf702cf34446f0e75888aaa61aedea4b58147d2f7d31382dcd24e116a8"}}