{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NKSNQO5YLYO2EIZHKUQRUN773X","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":"e1496d502b117559b4ffa1d5b694ce269d1fe0193fdf61d9ffeb9276101296eb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T15:18:35Z","title_canon_sha256":"dca44d6c5ec302965d45eb1f7e214b72394537877dafc9efd5cafcd2c43e2592"},"schema_version":"1.0","source":{"id":"2506.05447","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05447","created_at":"2026-07-05T11:37:22Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05447v2","created_at":"2026-07-05T11:37:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05447","created_at":"2026-07-05T11:37:22Z"},{"alias_kind":"pith_short_12","alias_value":"NKSNQO5YLYO2","created_at":"2026-07-05T11:37:22Z"},{"alias_kind":"pith_short_16","alias_value":"NKSNQO5YLYO2EIZH","created_at":"2026-07-05T11:37:22Z"},{"alias_kind":"pith_short_8","alias_value":"NKSNQO5Y","created_at":"2026-07-05T11:37:22Z"}],"graph_snapshots":[{"event_id":"sha256:443a6ae787a3821d5a6f7af65f98ed24a03fd53df9315bf59681f56ade752a1b","target":"graph","created_at":"2026-07-05T11:37:22Z","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/2506.05447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work aims to understand how scaling improves language models, specifically in terms of training dynamics. We find that language models undergo loss deceleration early in training; an abrupt slowdown in the rate of loss improvement, resulting in piecewise linear behaviour of the loss curve in log-log space. Scaling up the model mitigates this transition by (1) decreasing the loss at which deceleration occurs, and (2) improving the log-log rate of loss improvement after deceleration. We attribute loss deceleration to a type of degenerate training dynamics we term zero-sum learning (ZSL). In","authors_text":"Andrei Mircea, Ekaterina Lobacheva, Irina Rish, Milind Naphade, Nima Chitsazan, Sambit Sahu, Supriyo Chakraborty","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T15:18:35Z","title":"Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05447","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":"sha256:814546cbb915febf27315abbf5ddafbe99748b3c068f6053c4a0186e38717dce","target":"record","created_at":"2026-07-05T11:37:22Z","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":"e1496d502b117559b4ffa1d5b694ce269d1fe0193fdf61d9ffeb9276101296eb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T15:18:35Z","title_canon_sha256":"dca44d6c5ec302965d45eb1f7e214b72394537877dafc9efd5cafcd2c43e2592"},"schema_version":"1.0","source":{"id":"2506.05447","kind":"arxiv","version":2}},"canonical_sha256":"6aa4d83bb85e1da2232755211a37ffddd2b97da6dda1e4f470fe0d46bb55feed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6aa4d83bb85e1da2232755211a37ffddd2b97da6dda1e4f470fe0d46bb55feed","first_computed_at":"2026-07-05T11:37:22.835270Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:22.835270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bHBcmz/tZK8oKX9qtfQTFLoF8rkTlXaLUaNx5GR+KTPql6DWU5NajJb/ne2c0sQeC7kdiNKWv0jCIW91QJg/BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:22.835780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05447","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:814546cbb915febf27315abbf5ddafbe99748b3c068f6053c4a0186e38717dce","sha256:443a6ae787a3821d5a6f7af65f98ed24a03fd53df9315bf59681f56ade752a1b"],"state_sha256":"3b5dc5d8fdd124b31db3f051403dac49c34622040ba45e940a8ce4d2bd8c5e93"}