{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:EHXMI57GXAY44NTSUVOV6N45NG","short_pith_number":"pith:EHXMI57G","canonical_record":{"source":{"id":"1511.06827","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-21T03:50:49Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"d65ae9b7362a9a0690c5ebc241936ded6fb8cd65cd5d9d6e134460a62ab01b8a","abstract_canon_sha256":"dd45dbbe41481b05d4afbc41b974a39b674d44f44ce2a5bb0caa5bef0eb68ab9"},"schema_version":"1.0"},"canonical_sha256":"21eec477e6b831ce3672a55d5f379d69b2b4b0259a545eb47bdc304deca84464","source":{"kind":"arxiv","id":"1511.06827","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.06827","created_at":"2026-05-18T01:26:17Z"},{"alias_kind":"arxiv_version","alias_value":"1511.06827v1","created_at":"2026-05-18T01:26:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06827","created_at":"2026-05-18T01:26:17Z"},{"alias_kind":"pith_short_12","alias_value":"EHXMI57GXAY4","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"EHXMI57GXAY44NTS","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"EHXMI57G","created_at":"2026-05-18T12:29:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:EHXMI57GXAY44NTSUVOV6N45NG","target":"record","payload":{"canonical_record":{"source":{"id":"1511.06827","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-21T03:50:49Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"d65ae9b7362a9a0690c5ebc241936ded6fb8cd65cd5d9d6e134460a62ab01b8a","abstract_canon_sha256":"dd45dbbe41481b05d4afbc41b974a39b674d44f44ce2a5bb0caa5bef0eb68ab9"},"schema_version":"1.0"},"canonical_sha256":"21eec477e6b831ce3672a55d5f379d69b2b4b0259a545eb47bdc304deca84464","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:26:17.424659Z","signature_b64":"F4pk8AigRUjGUUOkGdhU2YOymP4djOIVJpchV1Wa92X3AIy3tTWD3tehqDRh5amzqyqoCTKR1+qrbPrG0sBVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21eec477e6b831ce3672a55d5f379d69b2b4b0259a545eb47bdc304deca84464","last_reissued_at":"2026-05-18T01:26:17.424081Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:26:17.424081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.06827","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":"2026-05-18T01:26:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zZdV7opJwU3BrzxoSch0fRc4lIsZCDiTkjV+SkMqVwJAdRyfAGvhN1NwpcE3dkLm9iywKLgy/9QnBs+9ahMPCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T07:33:25.297868Z"},"content_sha256":"4867e816c1e9826996b80e83057518644851eb1d7169eed413c8c7cb5a7dfe6a","schema_version":"1.0","event_id":"sha256:4867e816c1e9826996b80e83057518644851eb1d7169eed413c8c7cb5a7dfe6a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:EHXMI57GXAY44NTSUVOV6N45NG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GradNets: Dynamic Interpolation Between Neural Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Diogo Almeida, Nate Sauder","submitted_at":"2015-11-21T03:50:49Z","abstract_excerpt":"In machine learning, there is a fundamental trade-off between ease of optimization and expressive power. Neural Networks, in particular, have enormous expressive power and yet are notoriously challenging to train. The nature of that optimization challenge changes over the course of learning. Traditionally in deep learning, one makes a static trade-off between the needs of early and late optimization. In this paper, we investigate a novel framework, GradNets, for dynamically adapting architectures during training to get the benefits of both. For example, we can gradually transition from linear "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06827","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":"2026-05-18T01:26:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iW1+4TqO7Xevrm3tcGn7iW6RntIUTCQTCi4oPbm4FVYHiWoZePDLleCf/dV92wg9xBFs99V1ARAwY4i3vQzvCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T07:33:25.298220Z"},"content_sha256":"45558cec78d7ca7b8f0e122ef356c555180415106d84c48d7d3e51c34937dd4d","schema_version":"1.0","event_id":"sha256:45558cec78d7ca7b8f0e122ef356c555180415106d84c48d7d3e51c34937dd4d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EHXMI57GXAY44NTSUVOV6N45NG/bundle.json","state_url":"https://pith.science/pith/EHXMI57GXAY44NTSUVOV6N45NG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EHXMI57GXAY44NTSUVOV6N45NG/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":"2026-06-12T07:33:25Z","links":{"resolver":"https://pith.science/pith/EHXMI57GXAY44NTSUVOV6N45NG","bundle":"https://pith.science/pith/EHXMI57GXAY44NTSUVOV6N45NG/bundle.json","state":"https://pith.science/pith/EHXMI57GXAY44NTSUVOV6N45NG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EHXMI57GXAY44NTSUVOV6N45NG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:EHXMI57GXAY44NTSUVOV6N45NG","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":"dd45dbbe41481b05d4afbc41b974a39b674d44f44ce2a5bb0caa5bef0eb68ab9","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-21T03:50:49Z","title_canon_sha256":"d65ae9b7362a9a0690c5ebc241936ded6fb8cd65cd5d9d6e134460a62ab01b8a"},"schema_version":"1.0","source":{"id":"1511.06827","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.06827","created_at":"2026-05-18T01:26:17Z"},{"alias_kind":"arxiv_version","alias_value":"1511.06827v1","created_at":"2026-05-18T01:26:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06827","created_at":"2026-05-18T01:26:17Z"},{"alias_kind":"pith_short_12","alias_value":"EHXMI57GXAY4","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"EHXMI57GXAY44NTS","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"EHXMI57G","created_at":"2026-05-18T12:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:45558cec78d7ca7b8f0e122ef356c555180415106d84c48d7d3e51c34937dd4d","target":"graph","created_at":"2026-05-18T01:26:17Z","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":"In machine learning, there is a fundamental trade-off between ease of optimization and expressive power. Neural Networks, in particular, have enormous expressive power and yet are notoriously challenging to train. The nature of that optimization challenge changes over the course of learning. Traditionally in deep learning, one makes a static trade-off between the needs of early and late optimization. In this paper, we investigate a novel framework, GradNets, for dynamically adapting architectures during training to get the benefits of both. For example, we can gradually transition from linear ","authors_text":"Diogo Almeida, Nate Sauder","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-21T03:50:49Z","title":"GradNets: Dynamic Interpolation Between Neural Architectures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06827","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":"sha256:4867e816c1e9826996b80e83057518644851eb1d7169eed413c8c7cb5a7dfe6a","target":"record","created_at":"2026-05-18T01:26:17Z","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":"dd45dbbe41481b05d4afbc41b974a39b674d44f44ce2a5bb0caa5bef0eb68ab9","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-21T03:50:49Z","title_canon_sha256":"d65ae9b7362a9a0690c5ebc241936ded6fb8cd65cd5d9d6e134460a62ab01b8a"},"schema_version":"1.0","source":{"id":"1511.06827","kind":"arxiv","version":1}},"canonical_sha256":"21eec477e6b831ce3672a55d5f379d69b2b4b0259a545eb47bdc304deca84464","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21eec477e6b831ce3672a55d5f379d69b2b4b0259a545eb47bdc304deca84464","first_computed_at":"2026-05-18T01:26:17.424081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:26:17.424081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F4pk8AigRUjGUUOkGdhU2YOymP4djOIVJpchV1Wa92X3AIy3tTWD3tehqDRh5amzqyqoCTKR1+qrbPrG0sBVCg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:26:17.424659Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.06827","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4867e816c1e9826996b80e83057518644851eb1d7169eed413c8c7cb5a7dfe6a","sha256:45558cec78d7ca7b8f0e122ef356c555180415106d84c48d7d3e51c34937dd4d"],"state_sha256":"a6ff5e4b5c784e16db0eb1d7e53db42d2f268a5e68cddefef5eed17d40ec8247"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vTcB2hfLNBSxxeJsgc28lS+3gZu/caJZ5QIfl8eVoT0BN3Pxx/ROCX1gQichlkUOWkZBD41znG7z10tAorspCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T07:33:25.300347Z","bundle_sha256":"85f75ecfab5e56892dd46abdc6e3fcaf2744b3255e0cc1b8b918759a88ba8a7d"}}