{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SJMEP67IARB7YEMVGMOXEJOATJ","short_pith_number":"pith:SJMEP67I","canonical_record":{"source":{"id":"2310.16695","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T15:06:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8aa432be920849338ba6f648d6bf7ea6cb39f39042b14ff8920bb1b4247b92d1","abstract_canon_sha256":"3e96fb976fce78cb588f5439a51e4eeddceb656e67737cb66eea575eb8ecff01"},"schema_version":"1.0"},"canonical_sha256":"925847fbe80443fc1195331d7225c09a546afde634f7f4a7baae549dc68a1bb7","source":{"kind":"arxiv","id":"2310.16695","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16695","created_at":"2026-07-05T07:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16695v1","created_at":"2026-07-05T07:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16695","created_at":"2026-07-05T07:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"SJMEP67IARB7","created_at":"2026-07-05T07:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"SJMEP67IARB7YEMV","created_at":"2026-07-05T07:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"SJMEP67I","created_at":"2026-07-05T07:05:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SJMEP67IARB7YEMVGMOXEJOATJ","target":"record","payload":{"canonical_record":{"source":{"id":"2310.16695","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T15:06:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8aa432be920849338ba6f648d6bf7ea6cb39f39042b14ff8920bb1b4247b92d1","abstract_canon_sha256":"3e96fb976fce78cb588f5439a51e4eeddceb656e67737cb66eea575eb8ecff01"},"schema_version":"1.0"},"canonical_sha256":"925847fbe80443fc1195331d7225c09a546afde634f7f4a7baae549dc68a1bb7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:01.731764Z","signature_b64":"fZgDjOs6MFtKepU++wUrlrFcKx+umNDwRRZKz1Qh7EnrEhSyyvt6mjeBXbwAm+Zj0AsHY+4MN/ztyu97xOhJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"925847fbe80443fc1195331d7225c09a546afde634f7f4a7baae549dc68a1bb7","last_reissued_at":"2026-07-05T07:05:01.731341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:01.731341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.16695","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":"2026-07-05T07:05:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GmRRVBMYUf5VrxW3HtIOkKEsrnF+7wxru7tUGOXMuTwSA6sal9MG8L6GeHMDjGyx1Fy+uxEZNf12mbeBUIEODA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T04:12:16.715262Z"},"content_sha256":"2a0962982fe3bd1b7c6e36f25355582b8b8a77b708ab20686705dcfbdf2c558e","schema_version":"1.0","event_id":"sha256:2a0962982fe3bd1b7c6e36f25355582b8b8a77b708ab20686705dcfbdf2c558e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SJMEP67IARB7YEMVGMOXEJOATJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Pointwise to Powerhouse: Initialising Neural Networks with Generative Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anirban Mukhopadhyay, Christian Harder, Moritz Fuchs, Yuri Tolkach","submitted_at":"2023-10-25T15:06:32Z","abstract_excerpt":"Traditional initialisation methods, e.g. He and Xavier, have been effective in avoiding the problem of vanishing or exploding gradients in neural networks. However, they only use simple pointwise distributions, which model one-dimensional variables. Moreover, they ignore most information about the architecture and disregard past training experiences. These limitations can be overcome by employing generative models for initialisation. In this paper, we introduce two groups of new initialisation methods. First, we locally initialise weight groups by employing variational autoencoders. Secondly, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16695","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.16695/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T07:05:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NKl/hxgk8mr4a7s30hgwyQuiJCUQ+1G6pNVhu1/zXz4UwyJRiHH1H80CpD9i+NBCLVdUbL6me3dTM8eG029mCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T04:12:16.715669Z"},"content_sha256":"12f9f1ed939111f6388d433043ce19a65023079f7d995256cadca97a095bd648","schema_version":"1.0","event_id":"sha256:12f9f1ed939111f6388d433043ce19a65023079f7d995256cadca97a095bd648"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SJMEP67IARB7YEMVGMOXEJOATJ/bundle.json","state_url":"https://pith.science/pith/SJMEP67IARB7YEMVGMOXEJOATJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SJMEP67IARB7YEMVGMOXEJOATJ/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":"2026-07-13T04:12:16Z","links":{"resolver":"https://pith.science/pith/SJMEP67IARB7YEMVGMOXEJOATJ","bundle":"https://pith.science/pith/SJMEP67IARB7YEMVGMOXEJOATJ/bundle.json","state":"https://pith.science/pith/SJMEP67IARB7YEMVGMOXEJOATJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SJMEP67IARB7YEMVGMOXEJOATJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SJMEP67IARB7YEMVGMOXEJOATJ","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":"3e96fb976fce78cb588f5439a51e4eeddceb656e67737cb66eea575eb8ecff01","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T15:06:32Z","title_canon_sha256":"8aa432be920849338ba6f648d6bf7ea6cb39f39042b14ff8920bb1b4247b92d1"},"schema_version":"1.0","source":{"id":"2310.16695","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16695","created_at":"2026-07-05T07:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16695v1","created_at":"2026-07-05T07:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16695","created_at":"2026-07-05T07:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"SJMEP67IARB7","created_at":"2026-07-05T07:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"SJMEP67IARB7YEMV","created_at":"2026-07-05T07:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"SJMEP67I","created_at":"2026-07-05T07:05:01Z"}],"graph_snapshots":[{"event_id":"sha256:12f9f1ed939111f6388d433043ce19a65023079f7d995256cadca97a095bd648","target":"graph","created_at":"2026-07-05T07:05:01Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.16695/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional initialisation methods, e.g. He and Xavier, have been effective in avoiding the problem of vanishing or exploding gradients in neural networks. However, they only use simple pointwise distributions, which model one-dimensional variables. Moreover, they ignore most information about the architecture and disregard past training experiences. These limitations can be overcome by employing generative models for initialisation. In this paper, we introduce two groups of new initialisation methods. First, we locally initialise weight groups by employing variational autoencoders. Secondly, ","authors_text":"Anirban Mukhopadhyay, Christian Harder, Moritz Fuchs, Yuri Tolkach","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T15:06:32Z","title":"From Pointwise to Powerhouse: Initialising Neural Networks with Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16695","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":"sha256:2a0962982fe3bd1b7c6e36f25355582b8b8a77b708ab20686705dcfbdf2c558e","target":"record","created_at":"2026-07-05T07:05:01Z","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":"3e96fb976fce78cb588f5439a51e4eeddceb656e67737cb66eea575eb8ecff01","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T15:06:32Z","title_canon_sha256":"8aa432be920849338ba6f648d6bf7ea6cb39f39042b14ff8920bb1b4247b92d1"},"schema_version":"1.0","source":{"id":"2310.16695","kind":"arxiv","version":1}},"canonical_sha256":"925847fbe80443fc1195331d7225c09a546afde634f7f4a7baae549dc68a1bb7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"925847fbe80443fc1195331d7225c09a546afde634f7f4a7baae549dc68a1bb7","first_computed_at":"2026-07-05T07:05:01.731341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:01.731341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fZgDjOs6MFtKepU++wUrlrFcKx+umNDwRRZKz1Qh7EnrEhSyyvt6mjeBXbwAm+Zj0AsHY+4MN/ztyu97xOhJCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:01.731764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16695","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a0962982fe3bd1b7c6e36f25355582b8b8a77b708ab20686705dcfbdf2c558e","sha256:12f9f1ed939111f6388d433043ce19a65023079f7d995256cadca97a095bd648"],"state_sha256":"8a4b8e84d05b6ee9a9c204c44e07189894719c95a2318f1e90bb89b8904fbc57"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bzPzU8q0H5X/Lh17FdF3GFUSSwepYb74rnZB+rGHLvqr3fi+z9CloLPaq5R2CVnYQF+MYKe/bZ/6Rzl6fWUgCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T04:12:16.717839Z","bundle_sha256":"ff1e9f38d8c0d1a0e9c4622eaa840d108c740d6b8f0c6759d21ec3506d7b0354"}}