{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:R6ZXKNVG4L3M6RTWJNLBIYS47X","short_pith_number":"pith:R6ZXKNVG","canonical_record":{"source":{"id":"2606.22917","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T06:57:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7fa8aab34df5dc3aed545bcb43627bfe6de9e3344ed4ab97104ced3bfc3b7302","abstract_canon_sha256":"1231d67015d2b2c994782c427e4602bd12614b15261aebaf5d8bc2a84a2d4e5a"},"schema_version":"1.0"},"canonical_sha256":"8fb37536a6e2f6cf46764b5614625cfdcefc9b3c89419aa0ed783a1918d24fe9","source":{"kind":"arxiv","id":"2606.22917","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22917","created_at":"2026-06-23T03:14:04Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22917v1","created_at":"2026-06-23T03:14:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22917","created_at":"2026-06-23T03:14:04Z"},{"alias_kind":"pith_short_12","alias_value":"R6ZXKNVG4L3M","created_at":"2026-06-23T03:14:04Z"},{"alias_kind":"pith_short_16","alias_value":"R6ZXKNVG4L3M6RTW","created_at":"2026-06-23T03:14:04Z"},{"alias_kind":"pith_short_8","alias_value":"R6ZXKNVG","created_at":"2026-06-23T03:14:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:R6ZXKNVG4L3M6RTWJNLBIYS47X","target":"record","payload":{"canonical_record":{"source":{"id":"2606.22917","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T06:57:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7fa8aab34df5dc3aed545bcb43627bfe6de9e3344ed4ab97104ced3bfc3b7302","abstract_canon_sha256":"1231d67015d2b2c994782c427e4602bd12614b15261aebaf5d8bc2a84a2d4e5a"},"schema_version":"1.0"},"canonical_sha256":"8fb37536a6e2f6cf46764b5614625cfdcefc9b3c89419aa0ed783a1918d24fe9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:04.127617Z","signature_b64":"w9B+T9H/k4VjZbTbmmcjTN9iTxjqbTLPE2HqOVBMeVDvm2K1mCZ7Ixim7ExKz5FDekxz3MUOtpR2ukd9lesdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fb37536a6e2f6cf46764b5614625cfdcefc9b3c89419aa0ed783a1918d24fe9","last_reissued_at":"2026-06-23T03:14:04.127209Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:04.127209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.22917","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":"2026-06-23T03:14:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6WFOLPWXqp+hGhAM60f+JNb0tWVqr76hYqzKYH5DkbOXnn/eVPBe0aMkRDPDU9jaZoLkraJXFFZLn2iLED8jBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T20:35:35.072600Z"},"content_sha256":"421891792a54f94491c3fd84ac5d8b0aac44fbb1cb19db55372c72dcbcc2b325","schema_version":"1.0","event_id":"sha256:421891792a54f94491c3fd84ac5d8b0aac44fbb1cb19db55372c72dcbcc2b325"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:R6ZXKNVG4L3M6RTWJNLBIYS47X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GRAIN: Group Aggregation via Min-Norm Objective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiarui Yao, Lijing Wang, Nghia Bui","submitted_at":"2026-06-22T06:57:30Z","abstract_excerpt":"Learning instability is a long-standing problem across machine learning, but it is especially acute in the overparameterized regime that defines modern deep learning: large models fine-tuned or trained on limited data traverse flat loss landscapes with many nearly-equivalent minima, and stochastic factors (initialization, data order, dropout, hardware non-determinism) can route optimization to very different solutions. The rise of large pretrained models (LPMs) makes the problem more urgent: training cost is high, downstream data is often small, and repeated runs for variance reduction are pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22917","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/2606.22917/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":"2026-06-23T03:14:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PShRA+XFt8pB16AaNhaiSAKr+V2gmDHcfuWCrY2f1uG87FVVAogetBUdtf/qsLzwAkK+S3aQtsqNJgFCO8NYCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T20:35:35.072984Z"},"content_sha256":"ecda82a0a5802387c6f132a32cf947e6b7369b939292c791a3e311901ec79272","schema_version":"1.0","event_id":"sha256:ecda82a0a5802387c6f132a32cf947e6b7369b939292c791a3e311901ec79272"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R6ZXKNVG4L3M6RTWJNLBIYS47X/bundle.json","state_url":"https://pith.science/pith/R6ZXKNVG4L3M6RTWJNLBIYS47X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R6ZXKNVG4L3M6RTWJNLBIYS47X/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":"2026-07-03T20:35:35Z","links":{"resolver":"https://pith.science/pith/R6ZXKNVG4L3M6RTWJNLBIYS47X","bundle":"https://pith.science/pith/R6ZXKNVG4L3M6RTWJNLBIYS47X/bundle.json","state":"https://pith.science/pith/R6ZXKNVG4L3M6RTWJNLBIYS47X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R6ZXKNVG4L3M6RTWJNLBIYS47X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:R6ZXKNVG4L3M6RTWJNLBIYS47X","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":"1231d67015d2b2c994782c427e4602bd12614b15261aebaf5d8bc2a84a2d4e5a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T06:57:30Z","title_canon_sha256":"7fa8aab34df5dc3aed545bcb43627bfe6de9e3344ed4ab97104ced3bfc3b7302"},"schema_version":"1.0","source":{"id":"2606.22917","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22917","created_at":"2026-06-23T03:14:04Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22917v1","created_at":"2026-06-23T03:14:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22917","created_at":"2026-06-23T03:14:04Z"},{"alias_kind":"pith_short_12","alias_value":"R6ZXKNVG4L3M","created_at":"2026-06-23T03:14:04Z"},{"alias_kind":"pith_short_16","alias_value":"R6ZXKNVG4L3M6RTW","created_at":"2026-06-23T03:14:04Z"},{"alias_kind":"pith_short_8","alias_value":"R6ZXKNVG","created_at":"2026-06-23T03:14:04Z"}],"graph_snapshots":[{"event_id":"sha256:ecda82a0a5802387c6f132a32cf947e6b7369b939292c791a3e311901ec79272","target":"graph","created_at":"2026-06-23T03:14:04Z","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/2606.22917/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning instability is a long-standing problem across machine learning, but it is especially acute in the overparameterized regime that defines modern deep learning: large models fine-tuned or trained on limited data traverse flat loss landscapes with many nearly-equivalent minima, and stochastic factors (initialization, data order, dropout, hardware non-determinism) can route optimization to very different solutions. The rise of large pretrained models (LPMs) makes the problem more urgent: training cost is high, downstream data is often small, and repeated runs for variance reduction are pro","authors_text":"Jiarui Yao, Lijing Wang, Nghia Bui","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T06:57:30Z","title":"GRAIN: Group Aggregation via Min-Norm Objective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22917","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":"sha256:421891792a54f94491c3fd84ac5d8b0aac44fbb1cb19db55372c72dcbcc2b325","target":"record","created_at":"2026-06-23T03:14:04Z","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":"1231d67015d2b2c994782c427e4602bd12614b15261aebaf5d8bc2a84a2d4e5a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T06:57:30Z","title_canon_sha256":"7fa8aab34df5dc3aed545bcb43627bfe6de9e3344ed4ab97104ced3bfc3b7302"},"schema_version":"1.0","source":{"id":"2606.22917","kind":"arxiv","version":1}},"canonical_sha256":"8fb37536a6e2f6cf46764b5614625cfdcefc9b3c89419aa0ed783a1918d24fe9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fb37536a6e2f6cf46764b5614625cfdcefc9b3c89419aa0ed783a1918d24fe9","first_computed_at":"2026-06-23T03:14:04.127209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:04.127209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w9B+T9H/k4VjZbTbmmcjTN9iTxjqbTLPE2HqOVBMeVDvm2K1mCZ7Ixim7ExKz5FDekxz3MUOtpR2ukd9lesdAQ==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:04.127617Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22917","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:421891792a54f94491c3fd84ac5d8b0aac44fbb1cb19db55372c72dcbcc2b325","sha256:ecda82a0a5802387c6f132a32cf947e6b7369b939292c791a3e311901ec79272"],"state_sha256":"0c465f097bbbc62438f46c48741d6296086589ac6e4f90c4feda499092683456"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DeacT+X+PDmMTeoIsHUckMPQlQxWXDiBGLFop/TcBmnqa9KbSx9BLEQSMXWJImJzjQP8vZYjeOENNZkFSEYKBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T20:35:35.075084Z","bundle_sha256":"32a1280f61e2d7fe73a027a1582287e714568da1c8de3778a865d237af6fbb7a"}}