{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:W4QSCBXBUYQMZY3CN2474OWNWP","short_pith_number":"pith:W4QSCBXB","canonical_record":{"source":{"id":"2509.03407","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-03T15:32:50Z","cross_cats_sorted":[],"title_canon_sha256":"a3df4eb001de8884517ea06a8c83cde08a6941ed326ad2c9af8e0e813e81896b","abstract_canon_sha256":"4e500941c4522ac245c9267c465aeaec50d85bb85544ec44dc4ffcff974ca3f2"},"schema_version":"1.0"},"canonical_sha256":"b7212106e1a620cce3626eb9fe3acdb3fb8921a55528d8db2317f24068972b4d","source":{"kind":"arxiv","id":"2509.03407","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.03407","created_at":"2026-07-05T12:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"2509.03407v1","created_at":"2026-07-05T12:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03407","created_at":"2026-07-05T12:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"W4QSCBXBUYQM","created_at":"2026-07-05T12:04:22Z"},{"alias_kind":"pith_short_16","alias_value":"W4QSCBXBUYQMZY3C","created_at":"2026-07-05T12:04:22Z"},{"alias_kind":"pith_short_8","alias_value":"W4QSCBXB","created_at":"2026-07-05T12:04:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:W4QSCBXBUYQMZY3CN2474OWNWP","target":"record","payload":{"canonical_record":{"source":{"id":"2509.03407","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-03T15:32:50Z","cross_cats_sorted":[],"title_canon_sha256":"a3df4eb001de8884517ea06a8c83cde08a6941ed326ad2c9af8e0e813e81896b","abstract_canon_sha256":"4e500941c4522ac245c9267c465aeaec50d85bb85544ec44dc4ffcff974ca3f2"},"schema_version":"1.0"},"canonical_sha256":"b7212106e1a620cce3626eb9fe3acdb3fb8921a55528d8db2317f24068972b4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:22.052727Z","signature_b64":"VTagl3PTztI+zu7vx+5EIaEHuUD1kBzYZndGjyiUrPI1S18UwKB/1bjSeKgFji2JmbOno4lmNzjSaPmWTk3hBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7212106e1a620cce3626eb9fe3acdb3fb8921a55528d8db2317f24068972b4d","last_reissued_at":"2026-07-05T12:04:22.052221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:22.052221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.03407","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":"2026-07-05T12:04:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FxIr+ErliANzIN141RgVrd86N5Bjr1Qhs1ouAONsyq/4pvLFzsgBaeTYYZSr3rhJlVMQR+Hh/te7b2AUefE4DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:10:48.700707Z"},"content_sha256":"06b8061633e4e134d193bba97b2841d076031ed5f09e43a634b5c1ecce860e1a","schema_version":"1.0","event_id":"sha256:06b8061633e4e134d193bba97b2841d076031ed5f09e43a634b5c1ecce860e1a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:W4QSCBXBUYQMZY3CN2474OWNWP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Mechanism Underlying NLP Pre-Training and Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ella Koresh, Ido Kanter, Or Shpringer, Ronit D. Gross, Shalom Rosner, Tal Halevi, Yarden Tzach","submitted_at":"2025-09-03T15:32:50Z","abstract_excerpt":"Natural language processing (NLP) enables the understanding and generation of meaningful human language, typically using a pre-trained complex architecture on a large dataset to learn the language and next fine-tune its weights to implement a specific task. Twofold goals are examined; to understand the mechanism underlying successful pre-training and to determine the interplay between the pre-training accuracy and the fine-tuning of classification tasks. The following main results were obtained; the accuracy per token (APT) increased with its appearance frequency in the dataset, and its averag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03407","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/2509.03407/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":"2026-07-05T12:04:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sYYrljIWwTyWRHU65El0FRsB/yFBtH+fGQ/+QTtXr1Eo2pflblJAhVw4oHu4aphbRJqtJvXwLGZcv7XwnmAIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:10:48.701557Z"},"content_sha256":"7dc43d43958b2c2c82cbbc94f8fa6346262a79d00a8e533afe3585d83548108f","schema_version":"1.0","event_id":"sha256:7dc43d43958b2c2c82cbbc94f8fa6346262a79d00a8e533afe3585d83548108f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W4QSCBXBUYQMZY3CN2474OWNWP/bundle.json","state_url":"https://pith.science/pith/W4QSCBXBUYQMZY3CN2474OWNWP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W4QSCBXBUYQMZY3CN2474OWNWP/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":"2026-08-10T12:10:48Z","links":{"resolver":"https://pith.science/pith/W4QSCBXBUYQMZY3CN2474OWNWP","bundle":"https://pith.science/pith/W4QSCBXBUYQMZY3CN2474OWNWP/bundle.json","state":"https://pith.science/pith/W4QSCBXBUYQMZY3CN2474OWNWP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W4QSCBXBUYQMZY3CN2474OWNWP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W4QSCBXBUYQMZY3CN2474OWNWP","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":"4e500941c4522ac245c9267c465aeaec50d85bb85544ec44dc4ffcff974ca3f2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-03T15:32:50Z","title_canon_sha256":"a3df4eb001de8884517ea06a8c83cde08a6941ed326ad2c9af8e0e813e81896b"},"schema_version":"1.0","source":{"id":"2509.03407","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.03407","created_at":"2026-07-05T12:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"2509.03407v1","created_at":"2026-07-05T12:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03407","created_at":"2026-07-05T12:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"W4QSCBXBUYQM","created_at":"2026-07-05T12:04:22Z"},{"alias_kind":"pith_short_16","alias_value":"W4QSCBXBUYQMZY3C","created_at":"2026-07-05T12:04:22Z"},{"alias_kind":"pith_short_8","alias_value":"W4QSCBXB","created_at":"2026-07-05T12:04:22Z"}],"graph_snapshots":[{"event_id":"sha256:7dc43d43958b2c2c82cbbc94f8fa6346262a79d00a8e533afe3585d83548108f","target":"graph","created_at":"2026-07-05T12:04:22Z","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/2509.03407/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural language processing (NLP) enables the understanding and generation of meaningful human language, typically using a pre-trained complex architecture on a large dataset to learn the language and next fine-tune its weights to implement a specific task. Twofold goals are examined; to understand the mechanism underlying successful pre-training and to determine the interplay between the pre-training accuracy and the fine-tuning of classification tasks. The following main results were obtained; the accuracy per token (APT) increased with its appearance frequency in the dataset, and its averag","authors_text":"Ella Koresh, Ido Kanter, Or Shpringer, Ronit D. Gross, Shalom Rosner, Tal Halevi, Yarden Tzach","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-03T15:32:50Z","title":"Learning Mechanism Underlying NLP Pre-Training and Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03407","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":"sha256:06b8061633e4e134d193bba97b2841d076031ed5f09e43a634b5c1ecce860e1a","target":"record","created_at":"2026-07-05T12:04:22Z","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":"4e500941c4522ac245c9267c465aeaec50d85bb85544ec44dc4ffcff974ca3f2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-03T15:32:50Z","title_canon_sha256":"a3df4eb001de8884517ea06a8c83cde08a6941ed326ad2c9af8e0e813e81896b"},"schema_version":"1.0","source":{"id":"2509.03407","kind":"arxiv","version":1}},"canonical_sha256":"b7212106e1a620cce3626eb9fe3acdb3fb8921a55528d8db2317f24068972b4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7212106e1a620cce3626eb9fe3acdb3fb8921a55528d8db2317f24068972b4d","first_computed_at":"2026-07-05T12:04:22.052221Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:22.052221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VTagl3PTztI+zu7vx+5EIaEHuUD1kBzYZndGjyiUrPI1S18UwKB/1bjSeKgFji2JmbOno4lmNzjSaPmWTk3hBw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:22.052727Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.03407","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06b8061633e4e134d193bba97b2841d076031ed5f09e43a634b5c1ecce860e1a","sha256:7dc43d43958b2c2c82cbbc94f8fa6346262a79d00a8e533afe3585d83548108f"],"state_sha256":"e96f8362c1299b528300bed4a35c40c5372ef2416fa6a95ea7aeff16fc75ab2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qa506lIuPWuIbsd1lFyfkAjGi1yZEdZ+YXM/1A2aD14qiHxVJTW/FnVVr2jeF6lqy8Ct1NJOQTqYBn29UpM2Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:10:48.707781Z","bundle_sha256":"174e9aeae43c112d33800771de5fc515c0b799b3ab2c65c35ae5adf15fab0d04"}}