{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EZRPWSXWCBNP5QWSB6NHKCZU6D","short_pith_number":"pith:EZRPWSXW","canonical_record":{"source":{"id":"1810.13118","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-31T06:20:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f635db15cadb63bebb0f453f236eb94cfd97c8249e1b0115f3cafbe1c8c3a2c8","abstract_canon_sha256":"9b3d6c149e7138dac82959e63b4d007280915f4b025617c4b9b08b623ab3e96e"},"schema_version":"1.0"},"canonical_sha256":"2662fb4af6105afec2d20f9a750b34f0d641a2f51593342e86a6201a75c15863","source":{"kind":"arxiv","id":"1810.13118","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.13118","created_at":"2026-05-18T00:01:52Z"},{"alias_kind":"arxiv_version","alias_value":"1810.13118v1","created_at":"2026-05-18T00:01:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.13118","created_at":"2026-05-18T00:01:52Z"},{"alias_kind":"pith_short_12","alias_value":"EZRPWSXWCBNP","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EZRPWSXWCBNP5QWS","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EZRPWSXW","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EZRPWSXWCBNP5QWSB6NHKCZU6D","target":"record","payload":{"canonical_record":{"source":{"id":"1810.13118","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-31T06:20:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f635db15cadb63bebb0f453f236eb94cfd97c8249e1b0115f3cafbe1c8c3a2c8","abstract_canon_sha256":"9b3d6c149e7138dac82959e63b4d007280915f4b025617c4b9b08b623ab3e96e"},"schema_version":"1.0"},"canonical_sha256":"2662fb4af6105afec2d20f9a750b34f0d641a2f51593342e86a6201a75c15863","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:52.242736Z","signature_b64":"w3j4/mVVECAjvQn/Lfn9iN5TCyZh2f34KsoA2PZoQTtS0YFj1sflgBDn57ziG9HT9ehaV67Jl5G/XMt2tXm3Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2662fb4af6105afec2d20f9a750b34f0d641a2f51593342e86a6201a75c15863","last_reissued_at":"2026-05-18T00:01:52.242215Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:52.242215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.13118","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":"2026-05-18T00:01:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+HRvL9URnk0HQ02SHEXhp/tME7FfU4bobxOAGar8IzBW7POvmxnrSlzpTf6QKWAodQ5EsLXITxn/KOutPBsLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T15:20:19.690235Z"},"content_sha256":"feaf18b77b471c260207b36b030923e3ee4dff82c017d10a2b468e8e008a7bcf","schema_version":"1.0","event_id":"sha256:feaf18b77b471c260207b36b030923e3ee4dff82c017d10a2b468e8e008a7bcf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EZRPWSXWCBNP5QWSB6NHKCZU6D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SplineNets: Continuous Neural Decision Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cem Keskin, Shahram Izadi","submitted_at":"2018-10-31T06:20:24Z","abstract_excerpt":"We present SplineNets, a practical and novel approach for using conditioning in convolutional neural networks (CNNs). SplineNets are continuous generalizations of neural decision graphs, and they can dramatically reduce runtime complexity and computation costs of CNNs, while maintaining or even increasing accuracy. Functions of SplineNets are both dynamic (i.e., conditioned on the input) and hierarchical (i.e., conditioned on the computational path). SplineNets employ a unified loss function with a desired level of smoothness over both the network and decision parameters, while allowing for sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.13118","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":"2026-05-18T00:01:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2OM6Y2m8/beJXmrdwR09bKdm9Da4hgfjajuBAEApuiaipkG4fddFPxX7YbYDx6IAT25omjfxHXDu31lAXh5LBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T15:20:19.690594Z"},"content_sha256":"35d2f5b69be85f1d2c6fee33db5b12258626229029463df0b00aa96d4f3d20e6","schema_version":"1.0","event_id":"sha256:35d2f5b69be85f1d2c6fee33db5b12258626229029463df0b00aa96d4f3d20e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EZRPWSXWCBNP5QWSB6NHKCZU6D/bundle.json","state_url":"https://pith.science/pith/EZRPWSXWCBNP5QWSB6NHKCZU6D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EZRPWSXWCBNP5QWSB6NHKCZU6D/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":"2026-05-20T15:20:19Z","links":{"resolver":"https://pith.science/pith/EZRPWSXWCBNP5QWSB6NHKCZU6D","bundle":"https://pith.science/pith/EZRPWSXWCBNP5QWSB6NHKCZU6D/bundle.json","state":"https://pith.science/pith/EZRPWSXWCBNP5QWSB6NHKCZU6D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EZRPWSXWCBNP5QWSB6NHKCZU6D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EZRPWSXWCBNP5QWSB6NHKCZU6D","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":"9b3d6c149e7138dac82959e63b4d007280915f4b025617c4b9b08b623ab3e96e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-31T06:20:24Z","title_canon_sha256":"f635db15cadb63bebb0f453f236eb94cfd97c8249e1b0115f3cafbe1c8c3a2c8"},"schema_version":"1.0","source":{"id":"1810.13118","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.13118","created_at":"2026-05-18T00:01:52Z"},{"alias_kind":"arxiv_version","alias_value":"1810.13118v1","created_at":"2026-05-18T00:01:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.13118","created_at":"2026-05-18T00:01:52Z"},{"alias_kind":"pith_short_12","alias_value":"EZRPWSXWCBNP","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EZRPWSXWCBNP5QWS","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EZRPWSXW","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:35d2f5b69be85f1d2c6fee33db5b12258626229029463df0b00aa96d4f3d20e6","target":"graph","created_at":"2026-05-18T00:01:52Z","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 SplineNets, a practical and novel approach for using conditioning in convolutional neural networks (CNNs). SplineNets are continuous generalizations of neural decision graphs, and they can dramatically reduce runtime complexity and computation costs of CNNs, while maintaining or even increasing accuracy. Functions of SplineNets are both dynamic (i.e., conditioned on the input) and hierarchical (i.e., conditioned on the computational path). SplineNets employ a unified loss function with a desired level of smoothness over both the network and decision parameters, while allowing for sp","authors_text":"Cem Keskin, Shahram Izadi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-31T06:20:24Z","title":"SplineNets: Continuous Neural Decision Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.13118","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:feaf18b77b471c260207b36b030923e3ee4dff82c017d10a2b468e8e008a7bcf","target":"record","created_at":"2026-05-18T00:01:52Z","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":"9b3d6c149e7138dac82959e63b4d007280915f4b025617c4b9b08b623ab3e96e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-31T06:20:24Z","title_canon_sha256":"f635db15cadb63bebb0f453f236eb94cfd97c8249e1b0115f3cafbe1c8c3a2c8"},"schema_version":"1.0","source":{"id":"1810.13118","kind":"arxiv","version":1}},"canonical_sha256":"2662fb4af6105afec2d20f9a750b34f0d641a2f51593342e86a6201a75c15863","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2662fb4af6105afec2d20f9a750b34f0d641a2f51593342e86a6201a75c15863","first_computed_at":"2026-05-18T00:01:52.242215Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:52.242215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w3j4/mVVECAjvQn/Lfn9iN5TCyZh2f34KsoA2PZoQTtS0YFj1sflgBDn57ziG9HT9ehaV67Jl5G/XMt2tXm3Ag==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:52.242736Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.13118","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:feaf18b77b471c260207b36b030923e3ee4dff82c017d10a2b468e8e008a7bcf","sha256:35d2f5b69be85f1d2c6fee33db5b12258626229029463df0b00aa96d4f3d20e6"],"state_sha256":"e2a88f854b0cd6299fefb142bee832d801814bffd76f21294f0f03a7afb78a2a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lcyx1di01ZgV+rrQFjFa4JUCGm7/bLoT74qVYvHpR9Y/fQBDNbVaVlJ6wHdpEvUuWcFZ7k62OdepytBGcIwoDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T15:20:19.692559Z","bundle_sha256":"11c0461055b6df66eb571bf5699c4f08a98379b9e4c58f65a083c68e9baa1735"}}