{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OFQW3NBIL3FKIII3AQNGXAF4C6","short_pith_number":"pith:OFQW3NBI","canonical_record":{"source":{"id":"1801.01609","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-05T01:52:35Z","cross_cats_sorted":[],"title_canon_sha256":"717a66aec13e822825c67b640c10cf2f8194f912a9bd98ce9e1df8309042265d","abstract_canon_sha256":"0f392885e6a2a43a9535df2e48116100ccdf56bec352e378e811048541bbeb1b"},"schema_version":"1.0"},"canonical_sha256":"71616db4285ecaa4211b041a6b80bc17a733edec53395287006ed935638c858a","source":{"kind":"arxiv","id":"1801.01609","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.01609","created_at":"2026-05-18T00:26:41Z"},{"alias_kind":"arxiv_version","alias_value":"1801.01609v1","created_at":"2026-05-18T00:26:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.01609","created_at":"2026-05-18T00:26:41Z"},{"alias_kind":"pith_short_12","alias_value":"OFQW3NBIL3FK","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OFQW3NBIL3FKIII3","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OFQW3NBI","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OFQW3NBIL3FKIII3AQNGXAF4C6","target":"record","payload":{"canonical_record":{"source":{"id":"1801.01609","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-05T01:52:35Z","cross_cats_sorted":[],"title_canon_sha256":"717a66aec13e822825c67b640c10cf2f8194f912a9bd98ce9e1df8309042265d","abstract_canon_sha256":"0f392885e6a2a43a9535df2e48116100ccdf56bec352e378e811048541bbeb1b"},"schema_version":"1.0"},"canonical_sha256":"71616db4285ecaa4211b041a6b80bc17a733edec53395287006ed935638c858a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:41.642075Z","signature_b64":"KDdvE3YOsStVDYcN64lhtauoDkHQzUBCTlejT2RvmxSsQkYn7au3ud6Znrq1sApyciLjog5hvFt4iFk4g44pAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71616db4285ecaa4211b041a6b80bc17a733edec53395287006ed935638c858a","last_reissued_at":"2026-05-18T00:26:41.641529Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:41.641529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.01609","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":"2026-05-18T00:26:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y4gyYlnoHT+4LL+hnlPJ+MJno3LrJdvVKJanmTIfXRgKjTeEwMWuBi9jSJ+Gsbdgz06Co7CIqdo/Q446jpwLDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T04:57:41.015940Z"},"content_sha256":"d1fa5488755047e8fcd64514adffcdec787f864bff4af3a0264a9d26e1c891f2","schema_version":"1.0","event_id":"sha256:d1fa5488755047e8fcd64514adffcdec787f864bff4af3a0264a9d26e1c891f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OFQW3NBIL3FKIII3AQNGXAF4C6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning $3$D-FilterMap for Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jianchao Yang, Ning Xu, Wei Han, Yingzhen Yang","submitted_at":"2018-01-05T01:52:35Z","abstract_excerpt":"We present a novel and compact architecture for deep Convolutional Neural Networks (CNNs) in this paper, termed $3$D-FilterMap Convolutional Neural Networks ($3$D-FM-CNNs). The convolution layer of $3$D-FM-CNN learns a compact representation of the filters, named $3$D-FilterMap, instead of a set of independent filters in the conventional convolution layer. The filters are extracted from the $3$D-FilterMap as overlapping $3$D submatrics with weight sharing among nearby filters, and these filters are convolved with the input to generate the output of the convolution layer for $3$D-FM-CNN. Due to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.01609","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":"2026-05-18T00:26:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SClofVX8m0BXIHW8J/Y1jI883WBu9g4LSGgGXuVP0TCzFxC7D/9dBGFhvG16XdtfsXxiSGU7QwmCLH6pPvw3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T04:57:41.016653Z"},"content_sha256":"6992bbdd6838a811e5e8ef5ffa5351bdfb8f6b1522a153637c4a91e50d969349","schema_version":"1.0","event_id":"sha256:6992bbdd6838a811e5e8ef5ffa5351bdfb8f6b1522a153637c4a91e50d969349"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OFQW3NBIL3FKIII3AQNGXAF4C6/bundle.json","state_url":"https://pith.science/pith/OFQW3NBIL3FKIII3AQNGXAF4C6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OFQW3NBIL3FKIII3AQNGXAF4C6/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":"2026-06-09T04:57:41Z","links":{"resolver":"https://pith.science/pith/OFQW3NBIL3FKIII3AQNGXAF4C6","bundle":"https://pith.science/pith/OFQW3NBIL3FKIII3AQNGXAF4C6/bundle.json","state":"https://pith.science/pith/OFQW3NBIL3FKIII3AQNGXAF4C6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OFQW3NBIL3FKIII3AQNGXAF4C6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OFQW3NBIL3FKIII3AQNGXAF4C6","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":"0f392885e6a2a43a9535df2e48116100ccdf56bec352e378e811048541bbeb1b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-05T01:52:35Z","title_canon_sha256":"717a66aec13e822825c67b640c10cf2f8194f912a9bd98ce9e1df8309042265d"},"schema_version":"1.0","source":{"id":"1801.01609","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.01609","created_at":"2026-05-18T00:26:41Z"},{"alias_kind":"arxiv_version","alias_value":"1801.01609v1","created_at":"2026-05-18T00:26:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.01609","created_at":"2026-05-18T00:26:41Z"},{"alias_kind":"pith_short_12","alias_value":"OFQW3NBIL3FK","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OFQW3NBIL3FKIII3","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OFQW3NBI","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:6992bbdd6838a811e5e8ef5ffa5351bdfb8f6b1522a153637c4a91e50d969349","target":"graph","created_at":"2026-05-18T00:26:41Z","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":"We present a novel and compact architecture for deep Convolutional Neural Networks (CNNs) in this paper, termed $3$D-FilterMap Convolutional Neural Networks ($3$D-FM-CNNs). The convolution layer of $3$D-FM-CNN learns a compact representation of the filters, named $3$D-FilterMap, instead of a set of independent filters in the conventional convolution layer. The filters are extracted from the $3$D-FilterMap as overlapping $3$D submatrics with weight sharing among nearby filters, and these filters are convolved with the input to generate the output of the convolution layer for $3$D-FM-CNN. Due to","authors_text":"Jianchao Yang, Ning Xu, Wei Han, Yingzhen Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-05T01:52:35Z","title":"Learning $3$D-FilterMap for Deep Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.01609","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:d1fa5488755047e8fcd64514adffcdec787f864bff4af3a0264a9d26e1c891f2","target":"record","created_at":"2026-05-18T00:26:41Z","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":"0f392885e6a2a43a9535df2e48116100ccdf56bec352e378e811048541bbeb1b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-05T01:52:35Z","title_canon_sha256":"717a66aec13e822825c67b640c10cf2f8194f912a9bd98ce9e1df8309042265d"},"schema_version":"1.0","source":{"id":"1801.01609","kind":"arxiv","version":1}},"canonical_sha256":"71616db4285ecaa4211b041a6b80bc17a733edec53395287006ed935638c858a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71616db4285ecaa4211b041a6b80bc17a733edec53395287006ed935638c858a","first_computed_at":"2026-05-18T00:26:41.641529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:26:41.641529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KDdvE3YOsStVDYcN64lhtauoDkHQzUBCTlejT2RvmxSsQkYn7au3ud6Znrq1sApyciLjog5hvFt4iFk4g44pAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:26:41.642075Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.01609","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1fa5488755047e8fcd64514adffcdec787f864bff4af3a0264a9d26e1c891f2","sha256:6992bbdd6838a811e5e8ef5ffa5351bdfb8f6b1522a153637c4a91e50d969349"],"state_sha256":"1c959704020d63e880739eb20584e1f9e13144bfd3add12a4363ec2fc75bd3d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EUuKlVYKZC+WDoZQg0dji+ZF+Om6BSPe8qmbc8xfbzlLdEOqold7ltGXoOJKrCGh7EW4om5yHyN+MdJ7c7rQDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T04:57:41.020328Z","bundle_sha256":"420846bee1eb4f98fed16f8198fc4eab5a50604ed7ea533fb980fa2d622f5476"}}