{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:L7AVAQQHYV235H2IWFCRP3CXC3","short_pith_number":"pith:L7AVAQQH","canonical_record":{"source":{"id":"2501.19105","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T12:57:58Z","cross_cats_sorted":["math.PR"],"title_canon_sha256":"8ccaa808318fbf62289bb5d40b66ceff747222e6a885034b7ff987239a704f03","abstract_canon_sha256":"aed4e2d1bd30af9f397b2c07b45c7e1c802d2a24616d1cbac755f280716463ad"},"schema_version":"1.0"},"canonical_sha256":"5fc1504207c575be9f48b14517ec5716f7999c508b06450cfb3f3b7ae3e9abe4","source":{"kind":"arxiv","id":"2501.19105","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.19105","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"arxiv_version","alias_value":"2501.19105v2","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.19105","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"pith_short_12","alias_value":"L7AVAQQHYV23","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"pith_short_16","alias_value":"L7AVAQQHYV235H2I","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"pith_short_8","alias_value":"L7AVAQQH","created_at":"2026-07-05T10:09:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:L7AVAQQHYV235H2IWFCRP3CXC3","target":"record","payload":{"canonical_record":{"source":{"id":"2501.19105","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T12:57:58Z","cross_cats_sorted":["math.PR"],"title_canon_sha256":"8ccaa808318fbf62289bb5d40b66ceff747222e6a885034b7ff987239a704f03","abstract_canon_sha256":"aed4e2d1bd30af9f397b2c07b45c7e1c802d2a24616d1cbac755f280716463ad"},"schema_version":"1.0"},"canonical_sha256":"5fc1504207c575be9f48b14517ec5716f7999c508b06450cfb3f3b7ae3e9abe4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:16.037587Z","signature_b64":"wxf/VYh5MwcXAlUbfFl+IeL5EKPYJzlqLs5T2C8jOJ0YZsdTbMUdeBrYsfteKzpbAE0z3/zJJvV6J5L3go/rCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fc1504207c575be9f48b14517ec5716f7999c508b06450cfb3f3b7ae3e9abe4","last_reissued_at":"2026-07-05T10:09:16.037119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:16.037119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.19105","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:09:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ps/G04q4VEcTfNTfEAw+hcpiYi6L1bpMhJd1lrJs1hPzdx36sZ8C0ZuCrtPjbB13FHvccNILf5+O3WjfoEJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:44:38.940552Z"},"content_sha256":"9c064e9e0a52167ba0d688bc1e1c0c77ee16612e7a1bfbfae5b484cc798fd062","schema_version":"1.0","event_id":"sha256:9c064e9e0a52167ba0d688bc1e1c0c77ee16612e7a1bfbfae5b484cc798fd062"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:L7AVAQQHYV235H2IWFCRP3CXC3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Relating Misfit to Gain in Weak-to-Strong Generalization Beyond the Squared Loss","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.PR"],"primary_cat":"cs.LG","authors_text":"Abhijeet Mulgund, Chirag Pabbaraju","submitted_at":"2025-01-31T12:57:58Z","abstract_excerpt":"The paradigm of weak-to-strong generalization constitutes the training of a strong AI model on data labeled by a weak AI model, with the goal that the strong model nevertheless outperforms its weak supervisor on the target task of interest. For the setting of real-valued regression with the squared loss, recent work quantitatively characterizes the gain in performance of the strong model over the weak model in terms of the misfit between the strong and weak model. We generalize such a characterization to learning tasks whose loss functions correspond to arbitrary Bregman divergences when the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.19105","kind":"arxiv","version":2},"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/2501.19105/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":"2026-07-05T10:09:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mHeNg4YGMqNKVUsYbyLk4UXY5zgLesb0YPqCjje+qglrlg7lqBGHHv/Dd1iWtemcU78iC4zrLopD3tw2yeWwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:44:38.941111Z"},"content_sha256":"40b77df3de5c076db922ac6e25e1e3c99111468c728cc1ae37bc4390b0525b1c","schema_version":"1.0","event_id":"sha256:40b77df3de5c076db922ac6e25e1e3c99111468c728cc1ae37bc4390b0525b1c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L7AVAQQHYV235H2IWFCRP3CXC3/bundle.json","state_url":"https://pith.science/pith/L7AVAQQHYV235H2IWFCRP3CXC3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L7AVAQQHYV235H2IWFCRP3CXC3/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":"2026-08-09T12:44:38Z","links":{"resolver":"https://pith.science/pith/L7AVAQQHYV235H2IWFCRP3CXC3","bundle":"https://pith.science/pith/L7AVAQQHYV235H2IWFCRP3CXC3/bundle.json","state":"https://pith.science/pith/L7AVAQQHYV235H2IWFCRP3CXC3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L7AVAQQHYV235H2IWFCRP3CXC3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L7AVAQQHYV235H2IWFCRP3CXC3","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":"aed4e2d1bd30af9f397b2c07b45c7e1c802d2a24616d1cbac755f280716463ad","cross_cats_sorted":["math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T12:57:58Z","title_canon_sha256":"8ccaa808318fbf62289bb5d40b66ceff747222e6a885034b7ff987239a704f03"},"schema_version":"1.0","source":{"id":"2501.19105","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.19105","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"arxiv_version","alias_value":"2501.19105v2","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.19105","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"pith_short_12","alias_value":"L7AVAQQHYV23","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"pith_short_16","alias_value":"L7AVAQQHYV235H2I","created_at":"2026-07-05T10:09:16Z"},{"alias_kind":"pith_short_8","alias_value":"L7AVAQQH","created_at":"2026-07-05T10:09:16Z"}],"graph_snapshots":[{"event_id":"sha256:40b77df3de5c076db922ac6e25e1e3c99111468c728cc1ae37bc4390b0525b1c","target":"graph","created_at":"2026-07-05T10:09:16Z","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/2501.19105/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The paradigm of weak-to-strong generalization constitutes the training of a strong AI model on data labeled by a weak AI model, with the goal that the strong model nevertheless outperforms its weak supervisor on the target task of interest. For the setting of real-valued regression with the squared loss, recent work quantitatively characterizes the gain in performance of the strong model over the weak model in terms of the misfit between the strong and weak model. We generalize such a characterization to learning tasks whose loss functions correspond to arbitrary Bregman divergences when the s","authors_text":"Abhijeet Mulgund, Chirag Pabbaraju","cross_cats":["math.PR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T12:57:58Z","title":"Relating Misfit to Gain in Weak-to-Strong Generalization Beyond the Squared Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.19105","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":"sha256:9c064e9e0a52167ba0d688bc1e1c0c77ee16612e7a1bfbfae5b484cc798fd062","target":"record","created_at":"2026-07-05T10:09:16Z","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":"aed4e2d1bd30af9f397b2c07b45c7e1c802d2a24616d1cbac755f280716463ad","cross_cats_sorted":["math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T12:57:58Z","title_canon_sha256":"8ccaa808318fbf62289bb5d40b66ceff747222e6a885034b7ff987239a704f03"},"schema_version":"1.0","source":{"id":"2501.19105","kind":"arxiv","version":2}},"canonical_sha256":"5fc1504207c575be9f48b14517ec5716f7999c508b06450cfb3f3b7ae3e9abe4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fc1504207c575be9f48b14517ec5716f7999c508b06450cfb3f3b7ae3e9abe4","first_computed_at":"2026-07-05T10:09:16.037119Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:16.037119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wxf/VYh5MwcXAlUbfFl+IeL5EKPYJzlqLs5T2C8jOJ0YZsdTbMUdeBrYsfteKzpbAE0z3/zJJvV6J5L3go/rCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:16.037587Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.19105","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c064e9e0a52167ba0d688bc1e1c0c77ee16612e7a1bfbfae5b484cc798fd062","sha256:40b77df3de5c076db922ac6e25e1e3c99111468c728cc1ae37bc4390b0525b1c"],"state_sha256":"0679691f35666990d288beaf755f8b2902df5e901088f5820dc96415b3968204"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yP6obMGZydMKOdU0/Pi2ovzJy9ZC9gKIEWATA7gNhqcxR7Hfjuc7NNMcVKMD6uI7jfOgsUKG7paaTr4Y7KT9Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T12:44:38.944436Z","bundle_sha256":"c1e44c9bf338b19423e57e92b3281f53b0c84019e7b98ea54019a57a2282eb20"}}