{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KBMSTO4EVBTKYQF2ZBK2ODEL44","short_pith_number":"pith:KBMSTO4E","canonical_record":{"source":{"id":"2402.10339","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T21:57:43Z","cross_cats_sorted":[],"title_canon_sha256":"357e0db12d88625118450c2147a0a00fa16c2ec9554b6a18e34609dc662782f2","abstract_canon_sha256":"abac333e930cc6de9bf3b4979ccc8bd4aa5db39ec3106209284affd5fa2b8c4e"},"schema_version":"1.0"},"canonical_sha256":"505929bb84a866ac40bac855a70c8be70b78316f49727c8b7be7fdabb21356fd","source":{"kind":"arxiv","id":"2402.10339","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10339","created_at":"2026-07-05T07:45:54Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10339v1","created_at":"2026-07-05T07:45:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10339","created_at":"2026-07-05T07:45:54Z"},{"alias_kind":"pith_short_12","alias_value":"KBMSTO4EVBTK","created_at":"2026-07-05T07:45:54Z"},{"alias_kind":"pith_short_16","alias_value":"KBMSTO4EVBTKYQF2","created_at":"2026-07-05T07:45:54Z"},{"alias_kind":"pith_short_8","alias_value":"KBMSTO4E","created_at":"2026-07-05T07:45:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KBMSTO4EVBTKYQF2ZBK2ODEL44","target":"record","payload":{"canonical_record":{"source":{"id":"2402.10339","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T21:57:43Z","cross_cats_sorted":[],"title_canon_sha256":"357e0db12d88625118450c2147a0a00fa16c2ec9554b6a18e34609dc662782f2","abstract_canon_sha256":"abac333e930cc6de9bf3b4979ccc8bd4aa5db39ec3106209284affd5fa2b8c4e"},"schema_version":"1.0"},"canonical_sha256":"505929bb84a866ac40bac855a70c8be70b78316f49727c8b7be7fdabb21356fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:54.862152Z","signature_b64":"1h1JrBCaDO2uuNGRpCwTFcYt0WZ0xEAJiWHP3IMDe/lZPFPc6qpibZ6MUGiEEwxbGkcEtek9wo/h1do7D53IDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"505929bb84a866ac40bac855a70c8be70b78316f49727c8b7be7fdabb21356fd","last_reissued_at":"2026-07-05T07:45:54.861716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:54.861716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.10339","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":"2026-07-05T07:45:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gfbj9XKaEjuBvpw3QzIuWBl5PpijPZxkmPGdt19FjOPluvfd+LqpbSTzuBYOAmr+fgcJNk6FhEJL5XzdXegBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:46:16.870412Z"},"content_sha256":"e00813630ff5dfb16ed5b1ce1738255d902b84e042960045b95363640c989ed3","schema_version":"1.0","event_id":"sha256:e00813630ff5dfb16ed5b1ce1738255d902b84e042960045b95363640c989ed3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KBMSTO4EVBTKYQF2ZBK2ODEL44","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What to Do When Your Discrete Optimization Is the Size of a Neural Network?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hugo Silva, Martha White","submitted_at":"2024-02-15T21:57:43Z","abstract_excerpt":"Oftentimes, machine learning applications using neural networks involve solving discrete optimization problems, such as in pruning, parameter-isolation-based continual learning and training of binary networks. Still, these discrete problems are combinatorial in nature and are also not amenable to gradient-based optimization. Additionally, classical approaches used in discrete settings do not scale well to large neural networks, forcing scientists and empiricists to rely on alternative methods. Among these, two main distinct sources of top-down information can be used to lead the model to good "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10339","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/2402.10339/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":"2026-07-05T07:45:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/tYmIbFi4y89eVuVOJ20J8vZfBRq7iWvDpni3SFeQcpfKgKWHKpS2vl9tLmsQ0Dc5TL559cY1yETEp4zEQmVAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:46:16.870799Z"},"content_sha256":"97ea6be1a42e3b331163a7ad91f6136f02d0b1012506ae69965a976862f92f6d","schema_version":"1.0","event_id":"sha256:97ea6be1a42e3b331163a7ad91f6136f02d0b1012506ae69965a976862f92f6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KBMSTO4EVBTKYQF2ZBK2ODEL44/bundle.json","state_url":"https://pith.science/pith/KBMSTO4EVBTKYQF2ZBK2ODEL44/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KBMSTO4EVBTKYQF2ZBK2ODEL44/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":"2026-08-07T04:46:16Z","links":{"resolver":"https://pith.science/pith/KBMSTO4EVBTKYQF2ZBK2ODEL44","bundle":"https://pith.science/pith/KBMSTO4EVBTKYQF2ZBK2ODEL44/bundle.json","state":"https://pith.science/pith/KBMSTO4EVBTKYQF2ZBK2ODEL44/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KBMSTO4EVBTKYQF2ZBK2ODEL44/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KBMSTO4EVBTKYQF2ZBK2ODEL44","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":"abac333e930cc6de9bf3b4979ccc8bd4aa5db39ec3106209284affd5fa2b8c4e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T21:57:43Z","title_canon_sha256":"357e0db12d88625118450c2147a0a00fa16c2ec9554b6a18e34609dc662782f2"},"schema_version":"1.0","source":{"id":"2402.10339","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10339","created_at":"2026-07-05T07:45:54Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10339v1","created_at":"2026-07-05T07:45:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10339","created_at":"2026-07-05T07:45:54Z"},{"alias_kind":"pith_short_12","alias_value":"KBMSTO4EVBTK","created_at":"2026-07-05T07:45:54Z"},{"alias_kind":"pith_short_16","alias_value":"KBMSTO4EVBTKYQF2","created_at":"2026-07-05T07:45:54Z"},{"alias_kind":"pith_short_8","alias_value":"KBMSTO4E","created_at":"2026-07-05T07:45:54Z"}],"graph_snapshots":[{"event_id":"sha256:97ea6be1a42e3b331163a7ad91f6136f02d0b1012506ae69965a976862f92f6d","target":"graph","created_at":"2026-07-05T07:45:54Z","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/2402.10339/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Oftentimes, machine learning applications using neural networks involve solving discrete optimization problems, such as in pruning, parameter-isolation-based continual learning and training of binary networks. Still, these discrete problems are combinatorial in nature and are also not amenable to gradient-based optimization. Additionally, classical approaches used in discrete settings do not scale well to large neural networks, forcing scientists and empiricists to rely on alternative methods. Among these, two main distinct sources of top-down information can be used to lead the model to good ","authors_text":"Hugo Silva, Martha White","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T21:57:43Z","title":"What to Do When Your Discrete Optimization Is the Size of a Neural Network?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10339","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:e00813630ff5dfb16ed5b1ce1738255d902b84e042960045b95363640c989ed3","target":"record","created_at":"2026-07-05T07:45:54Z","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":"abac333e930cc6de9bf3b4979ccc8bd4aa5db39ec3106209284affd5fa2b8c4e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T21:57:43Z","title_canon_sha256":"357e0db12d88625118450c2147a0a00fa16c2ec9554b6a18e34609dc662782f2"},"schema_version":"1.0","source":{"id":"2402.10339","kind":"arxiv","version":1}},"canonical_sha256":"505929bb84a866ac40bac855a70c8be70b78316f49727c8b7be7fdabb21356fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"505929bb84a866ac40bac855a70c8be70b78316f49727c8b7be7fdabb21356fd","first_computed_at":"2026-07-05T07:45:54.861716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:45:54.861716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1h1JrBCaDO2uuNGRpCwTFcYt0WZ0xEAJiWHP3IMDe/lZPFPc6qpibZ6MUGiEEwxbGkcEtek9wo/h1do7D53IDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:45:54.862152Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.10339","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e00813630ff5dfb16ed5b1ce1738255d902b84e042960045b95363640c989ed3","sha256:97ea6be1a42e3b331163a7ad91f6136f02d0b1012506ae69965a976862f92f6d"],"state_sha256":"0d703c230f84fc387c0c8e19fc2b964fd4228c16329b3093c1d29f96611cff59"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R5ToCY1BzG0yHH83rv31T5GlZkBQQjNdRxfOYa7YuqArMPIlDf2q8QoZeEzTVs3oE5hCY9sk9TJyxPTUr5SVAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T04:46:16.873626Z","bundle_sha256":"66ba7005a6c2b7801c067d3e2409f04faf850e5e188a8c8ca67fd4bda530f40e"}}