{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UDOGGNPV7B5CXXZEKB2OFECPUJ","short_pith_number":"pith:UDOGGNPV","canonical_record":{"source":{"id":"2505.12470","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-18T15:48:10Z","cross_cats_sorted":[],"title_canon_sha256":"8429cc53c4e3c5359ec754ceaf3fc19b4832b0cbc0aa6f1554e2bbac3888525b","abstract_canon_sha256":"d5c48e1babcd7b39e6728a211d936f84be77036893b000b464d150404d32fa54"},"schema_version":"1.0"},"canonical_sha256":"a0dc6335f5f87a2bdf245074e2904fa2627c822d431b214599d8ab622ff458fc","source":{"kind":"arxiv","id":"2505.12470","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12470","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12470v2","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12470","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"pith_short_12","alias_value":"UDOGGNPV7B5C","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"pith_short_16","alias_value":"UDOGGNPV7B5CXXZE","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"pith_short_8","alias_value":"UDOGGNPV","created_at":"2026-07-05T11:08:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UDOGGNPV7B5CXXZEKB2OFECPUJ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.12470","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-18T15:48:10Z","cross_cats_sorted":[],"title_canon_sha256":"8429cc53c4e3c5359ec754ceaf3fc19b4832b0cbc0aa6f1554e2bbac3888525b","abstract_canon_sha256":"d5c48e1babcd7b39e6728a211d936f84be77036893b000b464d150404d32fa54"},"schema_version":"1.0"},"canonical_sha256":"a0dc6335f5f87a2bdf245074e2904fa2627c822d431b214599d8ab622ff458fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:20.833424Z","signature_b64":"xDMfZK0FpqpmawOy0bdVvAR5y8Lgk7SjPrycG92wLqGglDVFS2R1KkMQvdVx3ecG3WR8Fo0PShQxfIhEq3Y8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0dc6335f5f87a2bdf245074e2904fa2627c822d431b214599d8ab622ff458fc","last_reissued_at":"2026-07-05T11:08:20.832763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:20.832763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.12470","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":"2026-07-05T11:08:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LZPgrHgQbJROIXEtoH5gCK/YH8VI3eSda46AlWHeRlsa2EMffe9ca4hF2s/5bGe5zA92LLG/ULfZygnyB7XaDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T18:12:22.658075Z"},"content_sha256":"898c934a89a16df83c8afa37410e92b30c433e8e39af4d66b3a91e8fa6998c5b","schema_version":"1.0","event_id":"sha256:898c934a89a16df83c8afa37410e92b30c433e8e39af4d66b3a91e8fa6998c5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UDOGGNPV7B5CXXZEKB2OFECPUJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NeuroGen: Neural Network Parameter Generation via Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiaqi Wang, Xi Li, Yusen Zhang","submitted_at":"2025-05-18T15:48:10Z","abstract_excerpt":"Acquiring the parameters of neural networks (NNs) has been one of the most important problems in machine learning since the inception of NNs. Traditional approaches, such as backpropagation and forward-only optimization, acquire parameters via iterative data fitting to gradually optimize them. This paper aims to explore the feasibility of a new direction: acquiring NN parameters via large language model generation. We propose NeuroGen, a generalized and easy-to-implement two-stage approach for NN parameter generation conditioned on descriptions of the data, task, and network architecture. Stag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12470","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.12470/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":"2026-07-05T11:08:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/MhAdIE+sD0jAl85/gISKICg+SPFSlZxEpZT2mkdL14P3akkYB5npz7fb4nFwXxrMo/oFfJ5vEbgq/4RfPL0Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T18:12:22.658570Z"},"content_sha256":"db6321dac3d6966a172bb023b8f2d6e0ad0d4a1ee24315280d2ad3a1b046fa5c","schema_version":"1.0","event_id":"sha256:db6321dac3d6966a172bb023b8f2d6e0ad0d4a1ee24315280d2ad3a1b046fa5c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UDOGGNPV7B5CXXZEKB2OFECPUJ/bundle.json","state_url":"https://pith.science/pith/UDOGGNPV7B5CXXZEKB2OFECPUJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UDOGGNPV7B5CXXZEKB2OFECPUJ/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":"2026-08-19T18:12:22Z","links":{"resolver":"https://pith.science/pith/UDOGGNPV7B5CXXZEKB2OFECPUJ","bundle":"https://pith.science/pith/UDOGGNPV7B5CXXZEKB2OFECPUJ/bundle.json","state":"https://pith.science/pith/UDOGGNPV7B5CXXZEKB2OFECPUJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UDOGGNPV7B5CXXZEKB2OFECPUJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UDOGGNPV7B5CXXZEKB2OFECPUJ","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":"d5c48e1babcd7b39e6728a211d936f84be77036893b000b464d150404d32fa54","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-18T15:48:10Z","title_canon_sha256":"8429cc53c4e3c5359ec754ceaf3fc19b4832b0cbc0aa6f1554e2bbac3888525b"},"schema_version":"1.0","source":{"id":"2505.12470","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12470","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12470v2","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12470","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"pith_short_12","alias_value":"UDOGGNPV7B5C","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"pith_short_16","alias_value":"UDOGGNPV7B5CXXZE","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"pith_short_8","alias_value":"UDOGGNPV","created_at":"2026-07-05T11:08:20Z"}],"graph_snapshots":[{"event_id":"sha256:db6321dac3d6966a172bb023b8f2d6e0ad0d4a1ee24315280d2ad3a1b046fa5c","target":"graph","created_at":"2026-07-05T11:08:20Z","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/2505.12470/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Acquiring the parameters of neural networks (NNs) has been one of the most important problems in machine learning since the inception of NNs. Traditional approaches, such as backpropagation and forward-only optimization, acquire parameters via iterative data fitting to gradually optimize them. This paper aims to explore the feasibility of a new direction: acquiring NN parameters via large language model generation. We propose NeuroGen, a generalized and easy-to-implement two-stage approach for NN parameter generation conditioned on descriptions of the data, task, and network architecture. Stag","authors_text":"Jiaqi Wang, Xi Li, Yusen Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-18T15:48:10Z","title":"NeuroGen: Neural Network Parameter Generation via Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12470","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":"sha256:898c934a89a16df83c8afa37410e92b30c433e8e39af4d66b3a91e8fa6998c5b","target":"record","created_at":"2026-07-05T11:08:20Z","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":"d5c48e1babcd7b39e6728a211d936f84be77036893b000b464d150404d32fa54","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-18T15:48:10Z","title_canon_sha256":"8429cc53c4e3c5359ec754ceaf3fc19b4832b0cbc0aa6f1554e2bbac3888525b"},"schema_version":"1.0","source":{"id":"2505.12470","kind":"arxiv","version":2}},"canonical_sha256":"a0dc6335f5f87a2bdf245074e2904fa2627c822d431b214599d8ab622ff458fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0dc6335f5f87a2bdf245074e2904fa2627c822d431b214599d8ab622ff458fc","first_computed_at":"2026-07-05T11:08:20.832763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:20.832763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xDMfZK0FpqpmawOy0bdVvAR5y8Lgk7SjPrycG92wLqGglDVFS2R1KkMQvdVx3ecG3WR8Fo0PShQxfIhEq3Y8Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:20.833424Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12470","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:898c934a89a16df83c8afa37410e92b30c433e8e39af4d66b3a91e8fa6998c5b","sha256:db6321dac3d6966a172bb023b8f2d6e0ad0d4a1ee24315280d2ad3a1b046fa5c"],"state_sha256":"b1f990849ff9682c081c602ac9ebb8670f538e8113925308dd26f201f9500991"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HnbmTri1zuJvS4YAJG6ZqkzjFNnr6wGytOwZAPZC7eTMA2WRJIxwtJ3eVlVSYK5JzKNUmxvLhqBafJ1ICJhrAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T18:12:22.662224Z","bundle_sha256":"0b2eec9ff2f6a2a0d9f7bec1428b6e961dc0ab3c452d2412de262cd77ef4ccc1"}}