{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SNDHU6XKKHJCX5UYQUNOMO5VQT","short_pith_number":"pith:SNDHU6XK","canonical_record":{"source":{"id":"2507.15236","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-21T04:43:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a189de23a6c7918a62b25b2719a6e60f70f3d641ccdf15d6f72f0316cf5ba7ec","abstract_canon_sha256":"7db41581b632845a8ffcce5461cc6ae7253a9bd47345a00e2e4fda25ac9cb7f1"},"schema_version":"1.0"},"canonical_sha256":"93467a7aea51d22bf698851ae63bb584e3b349f8a27ea9ca0d9664232b23763f","source":{"kind":"arxiv","id":"2507.15236","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15236","created_at":"2026-07-05T11:40:20Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15236v1","created_at":"2026-07-05T11:40:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15236","created_at":"2026-07-05T11:40:20Z"},{"alias_kind":"pith_short_12","alias_value":"SNDHU6XKKHJC","created_at":"2026-07-05T11:40:20Z"},{"alias_kind":"pith_short_16","alias_value":"SNDHU6XKKHJCX5UY","created_at":"2026-07-05T11:40:20Z"},{"alias_kind":"pith_short_8","alias_value":"SNDHU6XK","created_at":"2026-07-05T11:40:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SNDHU6XKKHJCX5UYQUNOMO5VQT","target":"record","payload":{"canonical_record":{"source":{"id":"2507.15236","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-21T04:43:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a189de23a6c7918a62b25b2719a6e60f70f3d641ccdf15d6f72f0316cf5ba7ec","abstract_canon_sha256":"7db41581b632845a8ffcce5461cc6ae7253a9bd47345a00e2e4fda25ac9cb7f1"},"schema_version":"1.0"},"canonical_sha256":"93467a7aea51d22bf698851ae63bb584e3b349f8a27ea9ca0d9664232b23763f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:20.764944Z","signature_b64":"dap+uCvesL4emSArUDhomIR+3K+XQRa+PV16mANXedUzZdstmRyFLtY0v3ayJKxf+zY5+zBmATcmXuyn3XNYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93467a7aea51d22bf698851ae63bb584e3b349f8a27ea9ca0d9664232b23763f","last_reissued_at":"2026-07-05T11:40:20.764446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:20.764446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.15236","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":"2026-07-05T11:40:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+jeU0AEfzCz7Y4QNtPI9H/ia1Db4BciKmRtivC4lGgx7x2nwQwyBQT61rq08rpOLF1jw7sBPmbz8fMv/jg0pAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:20:47.228201Z"},"content_sha256":"46bb1bcc92c1e6d602594c477a21711909287d1faf2a2d2953a82d37bd8437f2","schema_version":"1.0","event_id":"sha256:46bb1bcc92c1e6d602594c477a21711909287d1faf2a2d2953a82d37bd8437f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SNDHU6XKKHJCX5UYQUNOMO5VQT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SOI Matters: Analyzing Multi-Setting Training Dynamics in Pretrained Language Models via Subsets of Interest","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Amirhossein Dabiriaghdam, Mohammadreza Bakhtiari, Shayan Vassef, Yadollah Yaghoobzadeh","submitted_at":"2025-07-21T04:43:21Z","abstract_excerpt":"This work investigates the impact of multi-task, multi-lingual, and multi-source learning approaches on the robustness and performance of pretrained language models. To enhance this analysis, we introduce Subsets of Interest (SOI), a novel categorization framework that identifies six distinct learning behavior patterns during training, including forgettable examples, unlearned examples, and always correct examples. Through SOI transition heatmaps and dataset cartography visualization, we analyze how examples shift between these categories when transitioning from single-setting to multi-setting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15236","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/2507.15236/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":"2026-07-05T11:40:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f3pKSq52P2Ic1c7eZMz6dQre7nr9ARWPpUwMfq5Atx/XgA09ngdwSqkTy15eWXsBAONWn4cjGxV72XUJg+yiDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:20:47.228904Z"},"content_sha256":"c479f850bef48ca66771ef5a7d65c196fbf39044214eaf7d43827de52456ff84","schema_version":"1.0","event_id":"sha256:c479f850bef48ca66771ef5a7d65c196fbf39044214eaf7d43827de52456ff84"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SNDHU6XKKHJCX5UYQUNOMO5VQT/bundle.json","state_url":"https://pith.science/pith/SNDHU6XKKHJCX5UYQUNOMO5VQT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SNDHU6XKKHJCX5UYQUNOMO5VQT/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":"2026-08-15T23:20:47Z","links":{"resolver":"https://pith.science/pith/SNDHU6XKKHJCX5UYQUNOMO5VQT","bundle":"https://pith.science/pith/SNDHU6XKKHJCX5UYQUNOMO5VQT/bundle.json","state":"https://pith.science/pith/SNDHU6XKKHJCX5UYQUNOMO5VQT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SNDHU6XKKHJCX5UYQUNOMO5VQT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SNDHU6XKKHJCX5UYQUNOMO5VQT","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":"7db41581b632845a8ffcce5461cc6ae7253a9bd47345a00e2e4fda25ac9cb7f1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-21T04:43:21Z","title_canon_sha256":"a189de23a6c7918a62b25b2719a6e60f70f3d641ccdf15d6f72f0316cf5ba7ec"},"schema_version":"1.0","source":{"id":"2507.15236","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15236","created_at":"2026-07-05T11:40:20Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15236v1","created_at":"2026-07-05T11:40:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15236","created_at":"2026-07-05T11:40:20Z"},{"alias_kind":"pith_short_12","alias_value":"SNDHU6XKKHJC","created_at":"2026-07-05T11:40:20Z"},{"alias_kind":"pith_short_16","alias_value":"SNDHU6XKKHJCX5UY","created_at":"2026-07-05T11:40:20Z"},{"alias_kind":"pith_short_8","alias_value":"SNDHU6XK","created_at":"2026-07-05T11:40:20Z"}],"graph_snapshots":[{"event_id":"sha256:c479f850bef48ca66771ef5a7d65c196fbf39044214eaf7d43827de52456ff84","target":"graph","created_at":"2026-07-05T11:40:20Z","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/2507.15236/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work investigates the impact of multi-task, multi-lingual, and multi-source learning approaches on the robustness and performance of pretrained language models. To enhance this analysis, we introduce Subsets of Interest (SOI), a novel categorization framework that identifies six distinct learning behavior patterns during training, including forgettable examples, unlearned examples, and always correct examples. Through SOI transition heatmaps and dataset cartography visualization, we analyze how examples shift between these categories when transitioning from single-setting to multi-setting","authors_text":"Amirhossein Dabiriaghdam, Mohammadreza Bakhtiari, Shayan Vassef, Yadollah Yaghoobzadeh","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-21T04:43:21Z","title":"SOI Matters: Analyzing Multi-Setting Training Dynamics in Pretrained Language Models via Subsets of Interest"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15236","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":"sha256:46bb1bcc92c1e6d602594c477a21711909287d1faf2a2d2953a82d37bd8437f2","target":"record","created_at":"2026-07-05T11:40:20Z","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":"7db41581b632845a8ffcce5461cc6ae7253a9bd47345a00e2e4fda25ac9cb7f1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-21T04:43:21Z","title_canon_sha256":"a189de23a6c7918a62b25b2719a6e60f70f3d641ccdf15d6f72f0316cf5ba7ec"},"schema_version":"1.0","source":{"id":"2507.15236","kind":"arxiv","version":1}},"canonical_sha256":"93467a7aea51d22bf698851ae63bb584e3b349f8a27ea9ca0d9664232b23763f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93467a7aea51d22bf698851ae63bb584e3b349f8a27ea9ca0d9664232b23763f","first_computed_at":"2026-07-05T11:40:20.764446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:20.764446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dap+uCvesL4emSArUDhomIR+3K+XQRa+PV16mANXedUzZdstmRyFLtY0v3ayJKxf+zY5+zBmATcmXuyn3XNYBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:20.764944Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15236","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46bb1bcc92c1e6d602594c477a21711909287d1faf2a2d2953a82d37bd8437f2","sha256:c479f850bef48ca66771ef5a7d65c196fbf39044214eaf7d43827de52456ff84"],"state_sha256":"35d32b8e229b9d9939bd5c0089386f126ce433be46f875b95a2bc5b7a5694341"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BghKyFWJHCQWtySQhTBGm4g437hfAJVXXURmUCBuM2p65aSC2uQD49UKODUIwWV1MpulHFCphLsUCG7w5X1iBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T23:20:47.234087Z","bundle_sha256":"be9d621beffddaf1c787ea8d7b192aa119cfd79706016964f18cda96c4e7a078"}}