{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OHDA6KYHQWNTFOEV2RCEAKO4DJ","short_pith_number":"pith:OHDA6KYH","canonical_record":{"source":{"id":"1803.01834","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-03-05T18:54:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"86dd8b627dbcd4abad88fa43e36c0da5047b34380a2e17b778952bf086176ab7","abstract_canon_sha256":"464885221c9821cc682e83c1bc8861072be7087c1cd69f088db160f66bc53361"},"schema_version":"1.0"},"canonical_sha256":"71c60f2b07859b32b895d4444029dc1a681ca08a19dea75da331e7d24c6a3189","source":{"kind":"arxiv","id":"1803.01834","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.01834","created_at":"2026-05-18T00:10:51Z"},{"alias_kind":"arxiv_version","alias_value":"1803.01834v2","created_at":"2026-05-18T00:10:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01834","created_at":"2026-05-18T00:10:51Z"},{"alias_kind":"pith_short_12","alias_value":"OHDA6KYHQWNT","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OHDA6KYHQWNTFOEV","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OHDA6KYH","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OHDA6KYHQWNTFOEV2RCEAKO4DJ","target":"record","payload":{"canonical_record":{"source":{"id":"1803.01834","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-03-05T18:54:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"86dd8b627dbcd4abad88fa43e36c0da5047b34380a2e17b778952bf086176ab7","abstract_canon_sha256":"464885221c9821cc682e83c1bc8861072be7087c1cd69f088db160f66bc53361"},"schema_version":"1.0"},"canonical_sha256":"71c60f2b07859b32b895d4444029dc1a681ca08a19dea75da331e7d24c6a3189","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:51.942135Z","signature_b64":"5XS+EoRCkgeLNI8bOu3fPK5K16C5lLk7wDQYgfZxf7CJ8UtZaZCUQZQVhXWvUe/yXNyL9bTe6t2TvYkkHLlIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71c60f2b07859b32b895d4444029dc1a681ca08a19dea75da331e7d24c6a3189","last_reissued_at":"2026-05-18T00:10:51.941495Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:51.941495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.01834","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":"2026-05-18T00:10:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H1/Fe9xrys+8pixxG5gzQIu2pq8vWL6fTTjBs93Hn7svhMjO1m3fx+5fZnY7AA6mKIDebIzErWxlecQ/b7keCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:35:24.872072Z"},"content_sha256":"743da5437b58303de9d2b32d79c24aaa80443802027d5836b8ebe50b19dbacc7","schema_version":"1.0","event_id":"sha256:743da5437b58303de9d2b32d79c24aaa80443802027d5836b8ebe50b19dbacc7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OHDA6KYHQWNTFOEV2RCEAKO4DJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Conducting Credit Assignment by Aligning Local Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander G. Ororbia, Ankur Mali, C. Lee Giles, Daniel Kifer","submitted_at":"2018-03-05T18:54:02Z","abstract_excerpt":"Using back-propagation and its variants to train deep networks is often problematic for new users. Issues such as exploding gradients, vanishing gradients, and high sensitivity to weight initialization strategies often make networks difficult to train, especially when users are experimenting with new architectures. Here, we present Local Representation Alignment (LRA), a training procedure that is much less sensitive to bad initializations, does not require modifications to the network architecture, and can be adapted to networks with highly nonlinear and discrete-valued activation functions. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01834","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":"2026-05-18T00:10:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Etem6zOCxBfaOgIQsSVnuzh9YsANVRTpbaUFJWgSGLLsdwJPgmoJNhyXpPbq9iGI9EXO8iFDrWYs5p4Ua0WxDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:35:24.872826Z"},"content_sha256":"bb2062497a3fc4b95fc97c7bbed74a739719d938e84da7121d1c24b84e686990","schema_version":"1.0","event_id":"sha256:bb2062497a3fc4b95fc97c7bbed74a739719d938e84da7121d1c24b84e686990"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OHDA6KYHQWNTFOEV2RCEAKO4DJ/bundle.json","state_url":"https://pith.science/pith/OHDA6KYHQWNTFOEV2RCEAKO4DJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OHDA6KYHQWNTFOEV2RCEAKO4DJ/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":"2026-05-30T11:35:24Z","links":{"resolver":"https://pith.science/pith/OHDA6KYHQWNTFOEV2RCEAKO4DJ","bundle":"https://pith.science/pith/OHDA6KYHQWNTFOEV2RCEAKO4DJ/bundle.json","state":"https://pith.science/pith/OHDA6KYHQWNTFOEV2RCEAKO4DJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OHDA6KYHQWNTFOEV2RCEAKO4DJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OHDA6KYHQWNTFOEV2RCEAKO4DJ","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":"464885221c9821cc682e83c1bc8861072be7087c1cd69f088db160f66bc53361","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-03-05T18:54:02Z","title_canon_sha256":"86dd8b627dbcd4abad88fa43e36c0da5047b34380a2e17b778952bf086176ab7"},"schema_version":"1.0","source":{"id":"1803.01834","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.01834","created_at":"2026-05-18T00:10:51Z"},{"alias_kind":"arxiv_version","alias_value":"1803.01834v2","created_at":"2026-05-18T00:10:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01834","created_at":"2026-05-18T00:10:51Z"},{"alias_kind":"pith_short_12","alias_value":"OHDA6KYHQWNT","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OHDA6KYHQWNTFOEV","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OHDA6KYH","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:bb2062497a3fc4b95fc97c7bbed74a739719d938e84da7121d1c24b84e686990","target":"graph","created_at":"2026-05-18T00:10:51Z","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":"Using back-propagation and its variants to train deep networks is often problematic for new users. Issues such as exploding gradients, vanishing gradients, and high sensitivity to weight initialization strategies often make networks difficult to train, especially when users are experimenting with new architectures. Here, we present Local Representation Alignment (LRA), a training procedure that is much less sensitive to bad initializations, does not require modifications to the network architecture, and can be adapted to networks with highly nonlinear and discrete-valued activation functions. ","authors_text":"Alexander G. Ororbia, Ankur Mali, C. Lee Giles, Daniel Kifer","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-03-05T18:54:02Z","title":"Conducting Credit Assignment by Aligning Local Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01834","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":"sha256:743da5437b58303de9d2b32d79c24aaa80443802027d5836b8ebe50b19dbacc7","target":"record","created_at":"2026-05-18T00:10:51Z","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":"464885221c9821cc682e83c1bc8861072be7087c1cd69f088db160f66bc53361","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-03-05T18:54:02Z","title_canon_sha256":"86dd8b627dbcd4abad88fa43e36c0da5047b34380a2e17b778952bf086176ab7"},"schema_version":"1.0","source":{"id":"1803.01834","kind":"arxiv","version":2}},"canonical_sha256":"71c60f2b07859b32b895d4444029dc1a681ca08a19dea75da331e7d24c6a3189","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71c60f2b07859b32b895d4444029dc1a681ca08a19dea75da331e7d24c6a3189","first_computed_at":"2026-05-18T00:10:51.941495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:51.941495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5XS+EoRCkgeLNI8bOu3fPK5K16C5lLk7wDQYgfZxf7CJ8UtZaZCUQZQVhXWvUe/yXNyL9bTe6t2TvYkkHLlIDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:51.942135Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.01834","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:743da5437b58303de9d2b32d79c24aaa80443802027d5836b8ebe50b19dbacc7","sha256:bb2062497a3fc4b95fc97c7bbed74a739719d938e84da7121d1c24b84e686990"],"state_sha256":"9b1d1bffa1358e7c3db5bc9f78e80489a5044375f476f6b4a397717094ff5626"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XLmNpQ/WUtE9iPutHMv2nD8312pYisooS7SNPcfrNr02yqb/NZj9yhtyFuHspoDOI0TucUt8krZt7HgmpCKGDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T11:35:24.877853Z","bundle_sha256":"085e45b16bf7c132e27fdf71843f23f353d47fe5a92a3be583b8c78078364fe3"}}