{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:OAEHFDCNFXVO3SWZGF5ACSMGGG","short_pith_number":"pith:OAEHFDCN","canonical_record":{"source":{"id":"2204.12511","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-26T18:00:04Z","cross_cats_sorted":[],"title_canon_sha256":"850d73421a08f425aaceb98aa85fbfa64a7fdb8b63c5dfb8fce1730c85dd2431","abstract_canon_sha256":"213dfdff8f87c13d3798e1791387b17d79d3546478a3aafa6e065a04c56218d4"},"schema_version":"1.0"},"canonical_sha256":"7008728c4d2deaedcad9317a014986319fa59495649b766091e5ff0b242afdb7","source":{"kind":"arxiv","id":"2204.12511","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.12511","created_at":"2026-07-05T04:22:20Z"},{"alias_kind":"arxiv_version","alias_value":"2204.12511v2","created_at":"2026-07-05T04:22:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12511","created_at":"2026-07-05T04:22:20Z"},{"alias_kind":"pith_short_12","alias_value":"OAEHFDCNFXVO","created_at":"2026-07-05T04:22:20Z"},{"alias_kind":"pith_short_16","alias_value":"OAEHFDCNFXVO3SWZ","created_at":"2026-07-05T04:22:20Z"},{"alias_kind":"pith_short_8","alias_value":"OAEHFDCN","created_at":"2026-07-05T04:22:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:OAEHFDCNFXVO3SWZGF5ACSMGGG","target":"record","payload":{"canonical_record":{"source":{"id":"2204.12511","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-26T18:00:04Z","cross_cats_sorted":[],"title_canon_sha256":"850d73421a08f425aaceb98aa85fbfa64a7fdb8b63c5dfb8fce1730c85dd2431","abstract_canon_sha256":"213dfdff8f87c13d3798e1791387b17d79d3546478a3aafa6e065a04c56218d4"},"schema_version":"1.0"},"canonical_sha256":"7008728c4d2deaedcad9317a014986319fa59495649b766091e5ff0b242afdb7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:20.861578Z","signature_b64":"HBSmqLjnCNhraquvvfZoZxpSxgxEKn+2Y66dMBH5jv3In5nHnrVvR6S7rYP3FU1BPw7xncRuc6eDY+5koCjFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7008728c4d2deaedcad9317a014986319fa59495649b766091e5ff0b242afdb7","last_reissued_at":"2026-07-05T04:22:20.861120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:20.861120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.12511","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":"2026-07-05T04:22:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jNgpZda5mKYjXF8UhxjGRjqUFJkT6UZSTMDHr6eF8hmjuqLtpe+fYjGZxkHGrUMeJqHhbi7b6pTua+7kiAUFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:15:01.334807Z"},"content_sha256":"4f4ef5deec0ef04f8ce00ad6e9c77204514b6f19ecaacdb386de9647349593d1","schema_version":"1.0","event_id":"sha256:4f4ef5deec0ef04f8ce00ad6e9c77204514b6f19ecaacdb386de9647349593d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:OAEHFDCNFXVO3SWZGF5ACSMGGG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxi Liu, Dragomir Anguelov, Ekin Dogus Cubuk, Mingxing Tan, Shuyang Cheng, Xiaojie Shi, Zhaoqi Leng","submitted_at":"2022-04-26T18:00:04Z","abstract_excerpt":"Cross-entropy loss and focal loss are the most common choices when training deep neural networks for classification problems. Generally speaking, however, a good loss function can take on much more flexible forms, and should be tailored for different tasks and datasets. Motivated by how functions can be approximated via Taylor expansion, we propose a simple framework, named PolyLoss, to view and design loss functions as a linear combination of polynomial functions. Our PolyLoss allows the importance of different polynomial bases to be easily adjusted depending on the targeting tasks and datase"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12511","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/2204.12511/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":"2026-07-05T04:22:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mkNAIwe0s7o02eDLyohBFpmOZnwbzKxmKa0ga4qhUd6Bz3UPRBpIt/6Z6rbVwRiXruJkUO8U4PykWCFMrmztBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:15:01.335317Z"},"content_sha256":"353ffe12871778b99944e4c1d440515858b9f403746456055b8ffcf70bbcb28b","schema_version":"1.0","event_id":"sha256:353ffe12871778b99944e4c1d440515858b9f403746456055b8ffcf70bbcb28b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OAEHFDCNFXVO3SWZGF5ACSMGGG/bundle.json","state_url":"https://pith.science/pith/OAEHFDCNFXVO3SWZGF5ACSMGGG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OAEHFDCNFXVO3SWZGF5ACSMGGG/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":"2026-08-08T07:15:01Z","links":{"resolver":"https://pith.science/pith/OAEHFDCNFXVO3SWZGF5ACSMGGG","bundle":"https://pith.science/pith/OAEHFDCNFXVO3SWZGF5ACSMGGG/bundle.json","state":"https://pith.science/pith/OAEHFDCNFXVO3SWZGF5ACSMGGG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OAEHFDCNFXVO3SWZGF5ACSMGGG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OAEHFDCNFXVO3SWZGF5ACSMGGG","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":"213dfdff8f87c13d3798e1791387b17d79d3546478a3aafa6e065a04c56218d4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-26T18:00:04Z","title_canon_sha256":"850d73421a08f425aaceb98aa85fbfa64a7fdb8b63c5dfb8fce1730c85dd2431"},"schema_version":"1.0","source":{"id":"2204.12511","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.12511","created_at":"2026-07-05T04:22:20Z"},{"alias_kind":"arxiv_version","alias_value":"2204.12511v2","created_at":"2026-07-05T04:22:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12511","created_at":"2026-07-05T04:22:20Z"},{"alias_kind":"pith_short_12","alias_value":"OAEHFDCNFXVO","created_at":"2026-07-05T04:22:20Z"},{"alias_kind":"pith_short_16","alias_value":"OAEHFDCNFXVO3SWZ","created_at":"2026-07-05T04:22:20Z"},{"alias_kind":"pith_short_8","alias_value":"OAEHFDCN","created_at":"2026-07-05T04:22:20Z"}],"graph_snapshots":[{"event_id":"sha256:353ffe12871778b99944e4c1d440515858b9f403746456055b8ffcf70bbcb28b","target":"graph","created_at":"2026-07-05T04:22:20Z","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/2204.12511/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-entropy loss and focal loss are the most common choices when training deep neural networks for classification problems. Generally speaking, however, a good loss function can take on much more flexible forms, and should be tailored for different tasks and datasets. Motivated by how functions can be approximated via Taylor expansion, we propose a simple framework, named PolyLoss, to view and design loss functions as a linear combination of polynomial functions. Our PolyLoss allows the importance of different polynomial bases to be easily adjusted depending on the targeting tasks and datase","authors_text":"Chenxi Liu, Dragomir Anguelov, Ekin Dogus Cubuk, Mingxing Tan, Shuyang Cheng, Xiaojie Shi, Zhaoqi Leng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-26T18:00:04Z","title":"PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12511","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":"sha256:4f4ef5deec0ef04f8ce00ad6e9c77204514b6f19ecaacdb386de9647349593d1","target":"record","created_at":"2026-07-05T04:22:20Z","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":"213dfdff8f87c13d3798e1791387b17d79d3546478a3aafa6e065a04c56218d4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-26T18:00:04Z","title_canon_sha256":"850d73421a08f425aaceb98aa85fbfa64a7fdb8b63c5dfb8fce1730c85dd2431"},"schema_version":"1.0","source":{"id":"2204.12511","kind":"arxiv","version":2}},"canonical_sha256":"7008728c4d2deaedcad9317a014986319fa59495649b766091e5ff0b242afdb7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7008728c4d2deaedcad9317a014986319fa59495649b766091e5ff0b242afdb7","first_computed_at":"2026-07-05T04:22:20.861120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:20.861120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HBSmqLjnCNhraquvvfZoZxpSxgxEKn+2Y66dMBH5jv3In5nHnrVvR6S7rYP3FU1BPw7xncRuc6eDY+5koCjFDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:20.861578Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.12511","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f4ef5deec0ef04f8ce00ad6e9c77204514b6f19ecaacdb386de9647349593d1","sha256:353ffe12871778b99944e4c1d440515858b9f403746456055b8ffcf70bbcb28b"],"state_sha256":"0a222678880a2b9109c16f5ee771a2a9de4b8bc36663ffe6d61a0eb4340a01b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qp1B7vHQMTqhSadrIn8vJWinsBu6c/MDBrnA2A9GGOEcBzPK9Ui4eiIMYGG7KVDGKTo8hy11INbVwivIWN2wCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T07:15:01.340015Z","bundle_sha256":"42052c112333955acb13a2c5707eeee1877228ffdeeae3ab768324d70946127e"}}