{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RKTZMEQEYUQCOYX55T3XRG3NVE","short_pith_number":"pith:RKTZMEQE","canonical_record":{"source":{"id":"2504.16182","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-04-22T18:15:30Z","cross_cats_sorted":[],"title_canon_sha256":"d02a3894661738679d2f3389269700e67d0f82504c74cf0e6c1ef80f4db7faa7","abstract_canon_sha256":"62160699035573f5553e828b59be46f5e8ed77ccf5d5ed70062a567d845a290f"},"schema_version":"1.0"},"canonical_sha256":"8aa7961204c5202762fdecf7789b6da929a255c4530c08201ab13431ebdb121a","source":{"kind":"arxiv","id":"2504.16182","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16182","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16182v3","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16182","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"pith_short_12","alias_value":"RKTZMEQEYUQC","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"pith_short_16","alias_value":"RKTZMEQEYUQCOYX5","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"pith_short_8","alias_value":"RKTZMEQE","created_at":"2026-07-05T11:53:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RKTZMEQEYUQCOYX55T3XRG3NVE","target":"record","payload":{"canonical_record":{"source":{"id":"2504.16182","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-04-22T18:15:30Z","cross_cats_sorted":[],"title_canon_sha256":"d02a3894661738679d2f3389269700e67d0f82504c74cf0e6c1ef80f4db7faa7","abstract_canon_sha256":"62160699035573f5553e828b59be46f5e8ed77ccf5d5ed70062a567d845a290f"},"schema_version":"1.0"},"canonical_sha256":"8aa7961204c5202762fdecf7789b6da929a255c4530c08201ab13431ebdb121a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:45.912280Z","signature_b64":"LaXV48fYrIePBYqzhCSbkUdHoKuLob7ovERLbvORxLwpEFCuXcV/ceAkAhTIeBbcfaz2DT+kuO3vA1UflMxWCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8aa7961204c5202762fdecf7789b6da929a255c4530c08201ab13431ebdb121a","last_reissued_at":"2026-07-05T11:53:45.911759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:45.911759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.16182","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:53:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A0Z3gZJUKnt8my9tTeBPAwxQavkHeYhQSlshAX/3oyEUnJ+H14pMYIK1lV3eeIWNZJ6xTc1nxunvyghYAXp0Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:11:43.577482Z"},"content_sha256":"8d2b681affa61c24536c3269402a0bba765d1754b2c79cc0ca332f5ea5fb969d","schema_version":"1.0","event_id":"sha256:8d2b681affa61c24536c3269402a0bba765d1754b2c79cc0ca332f5ea5fb969d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RKTZMEQEYUQCOYX55T3XRG3NVE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CGD: Modifying the Loss Landscape by Gradient Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Arti Yardi, Shikhar Saxena, Tejas Bodas","submitted_at":"2025-04-22T18:15:30Z","abstract_excerpt":"Line-search methods are commonly used to solve optimization problems. The simplest line search method is steepest descent where one always moves in the direction of the negative gradient. Newton's method on the other hand is a second-order method that uses the curvature information in the Hessian to pick the descent direction. In this work, we propose a new line-search method called Constrained Gradient Descent (CGD) that implicitly changes the landscape of the objective function for efficient optimization. CGD is formulated as a solution to the constrained version of the original problem wher"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16182","kind":"arxiv","version":3},"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/2504.16182/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":"2026-07-05T11:53:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MgQlpaAz+lTwrZxunlt0r5C57CaT77aQ1YGP7vesKU14LMXTb/0Y38qjmsKRm8Qcfx8L0rg2GsymbRyTSlLJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:11:43.578067Z"},"content_sha256":"32b4f26db63744dbbaaca7caca0d030dae70f109d0fc10ee034d624d1dfd19bf","schema_version":"1.0","event_id":"sha256:32b4f26db63744dbbaaca7caca0d030dae70f109d0fc10ee034d624d1dfd19bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RKTZMEQEYUQCOYX55T3XRG3NVE/bundle.json","state_url":"https://pith.science/pith/RKTZMEQEYUQCOYX55T3XRG3NVE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RKTZMEQEYUQCOYX55T3XRG3NVE/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":"2026-08-18T19:11:43Z","links":{"resolver":"https://pith.science/pith/RKTZMEQEYUQCOYX55T3XRG3NVE","bundle":"https://pith.science/pith/RKTZMEQEYUQCOYX55T3XRG3NVE/bundle.json","state":"https://pith.science/pith/RKTZMEQEYUQCOYX55T3XRG3NVE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RKTZMEQEYUQCOYX55T3XRG3NVE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RKTZMEQEYUQCOYX55T3XRG3NVE","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":"62160699035573f5553e828b59be46f5e8ed77ccf5d5ed70062a567d845a290f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-04-22T18:15:30Z","title_canon_sha256":"d02a3894661738679d2f3389269700e67d0f82504c74cf0e6c1ef80f4db7faa7"},"schema_version":"1.0","source":{"id":"2504.16182","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16182","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16182v3","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16182","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"pith_short_12","alias_value":"RKTZMEQEYUQC","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"pith_short_16","alias_value":"RKTZMEQEYUQCOYX5","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"pith_short_8","alias_value":"RKTZMEQE","created_at":"2026-07-05T11:53:45Z"}],"graph_snapshots":[{"event_id":"sha256:32b4f26db63744dbbaaca7caca0d030dae70f109d0fc10ee034d624d1dfd19bf","target":"graph","created_at":"2026-07-05T11:53:45Z","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/2504.16182/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Line-search methods are commonly used to solve optimization problems. The simplest line search method is steepest descent where one always moves in the direction of the negative gradient. Newton's method on the other hand is a second-order method that uses the curvature information in the Hessian to pick the descent direction. In this work, we propose a new line-search method called Constrained Gradient Descent (CGD) that implicitly changes the landscape of the objective function for efficient optimization. CGD is formulated as a solution to the constrained version of the original problem wher","authors_text":"Arti Yardi, Shikhar Saxena, Tejas Bodas","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-04-22T18:15:30Z","title":"CGD: Modifying the Loss Landscape by Gradient Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16182","kind":"arxiv","version":3},"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":"sha256:8d2b681affa61c24536c3269402a0bba765d1754b2c79cc0ca332f5ea5fb969d","target":"record","created_at":"2026-07-05T11:53:45Z","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":"62160699035573f5553e828b59be46f5e8ed77ccf5d5ed70062a567d845a290f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-04-22T18:15:30Z","title_canon_sha256":"d02a3894661738679d2f3389269700e67d0f82504c74cf0e6c1ef80f4db7faa7"},"schema_version":"1.0","source":{"id":"2504.16182","kind":"arxiv","version":3}},"canonical_sha256":"8aa7961204c5202762fdecf7789b6da929a255c4530c08201ab13431ebdb121a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8aa7961204c5202762fdecf7789b6da929a255c4530c08201ab13431ebdb121a","first_computed_at":"2026-07-05T11:53:45.911759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:45.911759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LaXV48fYrIePBYqzhCSbkUdHoKuLob7ovERLbvORxLwpEFCuXcV/ceAkAhTIeBbcfaz2DT+kuO3vA1UflMxWCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:45.912280Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.16182","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d2b681affa61c24536c3269402a0bba765d1754b2c79cc0ca332f5ea5fb969d","sha256:32b4f26db63744dbbaaca7caca0d030dae70f109d0fc10ee034d624d1dfd19bf"],"state_sha256":"617f577b822e7e5e4f91579381d011611b77be47a5f37cf5b84f8e634f824bf7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ol4XzQMGk+PEdPmjCnoY6aTr5gNf/hF5WQaCh9ToPh8xxQOWl/YjcMXSoyxiH9LTtxthR7a8tU7megKTbSqKCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T19:11:43.581473Z","bundle_sha256":"d2ef5a5fe5eab8719fef96deaf922e41b6c28e5700018f73e14423ad7d657309"}}