{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OKZT2V6AH2JTBU2C3HGMUDLVCO","short_pith_number":"pith:OKZT2V6A","canonical_record":{"source":{"id":"2310.13854","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-20T23:15:46Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"df946e948980412d32eae02e1c9201063ab4d8269e783d7e12ac468d9ddfff3d","abstract_canon_sha256":"cb08098b656892b518832d4b43c875dd697f83d199588a9529ccc0a8d9cdf0ec"},"schema_version":"1.0"},"canonical_sha256":"72b33d57c03e9330d342d9ccca0d7513b8fc7ab08afc73f63abcfd20c102ddbb","source":{"kind":"arxiv","id":"2310.13854","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13854","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13854v1","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13854","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"pith_short_12","alias_value":"OKZT2V6AH2JT","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"pith_short_16","alias_value":"OKZT2V6AH2JTBU2C","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"pith_short_8","alias_value":"OKZT2V6A","created_at":"2026-07-05T07:03:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OKZT2V6AH2JTBU2C3HGMUDLVCO","target":"record","payload":{"canonical_record":{"source":{"id":"2310.13854","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-20T23:15:46Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"df946e948980412d32eae02e1c9201063ab4d8269e783d7e12ac468d9ddfff3d","abstract_canon_sha256":"cb08098b656892b518832d4b43c875dd697f83d199588a9529ccc0a8d9cdf0ec"},"schema_version":"1.0"},"canonical_sha256":"72b33d57c03e9330d342d9ccca0d7513b8fc7ab08afc73f63abcfd20c102ddbb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:35.742217Z","signature_b64":"qZuje4JwOpkj1NWVa4bjdxHCD86fDtHTufrLdwoYEBQWGGzIhhrsBY5B5dxfPCMtDNQlGJy/2K8U42yJ5g/XAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72b33d57c03e9330d342d9ccca0d7513b8fc7ab08afc73f63abcfd20c102ddbb","last_reissued_at":"2026-07-05T07:03:35.741825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:35.741825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.13854","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":"2026-07-05T07:03:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/DL9QcuXRPtVPkar+202hNvtiTgUaPWxGLOVSuuAgejEirhzrwHEyF+flnvpDPXra1wsHD6QzDwteMUEn8AADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:38:58.250977Z"},"content_sha256":"ff7b8fb6b0b41f0e06faee65201a4fc2d5989a225f12d88df221b05e3cd37884","schema_version":"1.0","event_id":"sha256:ff7b8fb6b0b41f0e06faee65201a4fc2d5989a225f12d88df221b05e3cd37884"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OKZT2V6AH2JTBU2C3HGMUDLVCO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exponential weight averaging as damped harmonic motion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Henry Li, Jonathan Patsenker, Yuval Kluger","submitted_at":"2023-10-20T23:15:46Z","abstract_excerpt":"The exponential moving average (EMA) is a commonly used statistic for providing stable estimates of stochastic quantities in deep learning optimization. Recently, EMA has seen considerable use in generative models, where it is computed with respect to the model weights, and significantly improves the stability of the inference model during and after training. While the practice of weight averaging at the end of training is well-studied and known to improve estimates of local optima, the benefits of EMA over the course of training is less understood. In this paper, we derive an explicit connect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13854","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/2310.13854/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":"2026-07-05T07:03:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x9SEQyoxzs+gkK9tBHEjbGutxgDXdN7Hi9yyqY6UM8LGc05HFFqejGQ1nj3t2rYSIzJ3cFrBip6u/bTbSCs7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:38:58.251486Z"},"content_sha256":"4b7bb30cac8f27508fe73924f8499f3017daf530ac85af47dc3ab9b2d2510547","schema_version":"1.0","event_id":"sha256:4b7bb30cac8f27508fe73924f8499f3017daf530ac85af47dc3ab9b2d2510547"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OKZT2V6AH2JTBU2C3HGMUDLVCO/bundle.json","state_url":"https://pith.science/pith/OKZT2V6AH2JTBU2C3HGMUDLVCO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OKZT2V6AH2JTBU2C3HGMUDLVCO/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":"2026-08-18T01:38:58Z","links":{"resolver":"https://pith.science/pith/OKZT2V6AH2JTBU2C3HGMUDLVCO","bundle":"https://pith.science/pith/OKZT2V6AH2JTBU2C3HGMUDLVCO/bundle.json","state":"https://pith.science/pith/OKZT2V6AH2JTBU2C3HGMUDLVCO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OKZT2V6AH2JTBU2C3HGMUDLVCO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OKZT2V6AH2JTBU2C3HGMUDLVCO","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":"cb08098b656892b518832d4b43c875dd697f83d199588a9529ccc0a8d9cdf0ec","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-20T23:15:46Z","title_canon_sha256":"df946e948980412d32eae02e1c9201063ab4d8269e783d7e12ac468d9ddfff3d"},"schema_version":"1.0","source":{"id":"2310.13854","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13854","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13854v1","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13854","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"pith_short_12","alias_value":"OKZT2V6AH2JT","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"pith_short_16","alias_value":"OKZT2V6AH2JTBU2C","created_at":"2026-07-05T07:03:35Z"},{"alias_kind":"pith_short_8","alias_value":"OKZT2V6A","created_at":"2026-07-05T07:03:35Z"}],"graph_snapshots":[{"event_id":"sha256:4b7bb30cac8f27508fe73924f8499f3017daf530ac85af47dc3ab9b2d2510547","target":"graph","created_at":"2026-07-05T07:03:35Z","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/2310.13854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The exponential moving average (EMA) is a commonly used statistic for providing stable estimates of stochastic quantities in deep learning optimization. Recently, EMA has seen considerable use in generative models, where it is computed with respect to the model weights, and significantly improves the stability of the inference model during and after training. While the practice of weight averaging at the end of training is well-studied and known to improve estimates of local optima, the benefits of EMA over the course of training is less understood. In this paper, we derive an explicit connect","authors_text":"Henry Li, Jonathan Patsenker, Yuval Kluger","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-20T23:15:46Z","title":"Exponential weight averaging as damped harmonic motion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13854","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:ff7b8fb6b0b41f0e06faee65201a4fc2d5989a225f12d88df221b05e3cd37884","target":"record","created_at":"2026-07-05T07:03:35Z","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":"cb08098b656892b518832d4b43c875dd697f83d199588a9529ccc0a8d9cdf0ec","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-20T23:15:46Z","title_canon_sha256":"df946e948980412d32eae02e1c9201063ab4d8269e783d7e12ac468d9ddfff3d"},"schema_version":"1.0","source":{"id":"2310.13854","kind":"arxiv","version":1}},"canonical_sha256":"72b33d57c03e9330d342d9ccca0d7513b8fc7ab08afc73f63abcfd20c102ddbb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72b33d57c03e9330d342d9ccca0d7513b8fc7ab08afc73f63abcfd20c102ddbb","first_computed_at":"2026-07-05T07:03:35.741825Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:35.741825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qZuje4JwOpkj1NWVa4bjdxHCD86fDtHTufrLdwoYEBQWGGzIhhrsBY5B5dxfPCMtDNQlGJy/2K8U42yJ5g/XAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:35.742217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.13854","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff7b8fb6b0b41f0e06faee65201a4fc2d5989a225f12d88df221b05e3cd37884","sha256:4b7bb30cac8f27508fe73924f8499f3017daf530ac85af47dc3ab9b2d2510547"],"state_sha256":"b682c79d9cd0dde8b9707f14abbf2c1f6732ee95280db567bcb73d3bd8052467"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4hyJWbBOhBlYpHwcw9khliZOUkUkJacos79/O+knfAsdQ7ORkKL8PnOHdZUod1tLHTRYuNMlxZe4LRNkVW3pBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T01:38:58.256483Z","bundle_sha256":"22f00e34622a933a20d122069ebbbe8ad9c9a343f66f163acd234fbfb27f4fa3"}}