{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CX6ULRWAGFWTZRSP6BAOSDLOVK","short_pith_number":"pith:CX6ULRWA","canonical_record":{"source":{"id":"2104.01566","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-04T08:39:55Z","cross_cats_sorted":[],"title_canon_sha256":"898df35af1a3f7bc6e0df7a2603ce97dd423fff838b018e692afbff1bc17694c","abstract_canon_sha256":"cc0f2d52de0794b16d2c0cbfc7c3208cbee9ecde5018fd51f19d6885e70ceec5"},"schema_version":"1.0"},"canonical_sha256":"15fd45c6c0316d3cc64ff040e90d6eaaac6a6fe89795a672449b6e637079f7fe","source":{"kind":"arxiv","id":"2104.01566","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.01566","created_at":"2026-07-05T02:29:01Z"},{"alias_kind":"arxiv_version","alias_value":"2104.01566v1","created_at":"2026-07-05T02:29:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01566","created_at":"2026-07-05T02:29:01Z"},{"alias_kind":"pith_short_12","alias_value":"CX6ULRWAGFWT","created_at":"2026-07-05T02:29:01Z"},{"alias_kind":"pith_short_16","alias_value":"CX6ULRWAGFWTZRSP","created_at":"2026-07-05T02:29:01Z"},{"alias_kind":"pith_short_8","alias_value":"CX6ULRWA","created_at":"2026-07-05T02:29:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CX6ULRWAGFWTZRSP6BAOSDLOVK","target":"record","payload":{"canonical_record":{"source":{"id":"2104.01566","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-04T08:39:55Z","cross_cats_sorted":[],"title_canon_sha256":"898df35af1a3f7bc6e0df7a2603ce97dd423fff838b018e692afbff1bc17694c","abstract_canon_sha256":"cc0f2d52de0794b16d2c0cbfc7c3208cbee9ecde5018fd51f19d6885e70ceec5"},"schema_version":"1.0"},"canonical_sha256":"15fd45c6c0316d3cc64ff040e90d6eaaac6a6fe89795a672449b6e637079f7fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:01.383873Z","signature_b64":"R6VYr+n/l/gcPi41N0RYl7XWW1+K7fQfj3saPEglMKl3TTQCHwoaMikzPbPUNG2Y+3ntGNvKa2Kq2ZnkVtqlDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15fd45c6c0316d3cc64ff040e90d6eaaac6a6fe89795a672449b6e637079f7fe","last_reissued_at":"2026-07-05T02:29:01.383394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:01.383394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.01566","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":"2026-07-05T02:29:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rPYaXmwCov8ghGXf4STnURK4wgvxRF7cDmuO/mMNj6/U1obpKu2vaRp9wApy/6QvNMiwSbsuCG8bAFGrkWSdCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T07:49:19.540611Z"},"content_sha256":"e564a113e872f4aff4574c162a7521788d321671323922b29020872b762747f6","schema_version":"1.0","event_id":"sha256:e564a113e872f4aff4574c162a7521788d321671323922b29020872b762747f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CX6ULRWAGFWTZRSP6BAOSDLOVK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IITK@Detox at SemEval-2021 Task 5: Semi-Supervised Learning and Dice Loss for Toxic Spans Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhay Kaushik, Archit Bansal, Ashutosh Modi","submitted_at":"2021-04-04T08:39:55Z","abstract_excerpt":"In this work, we present our approach and findings for SemEval-2021 Task 5 - Toxic Spans Detection. The task's main aim was to identify spans to which a given text's toxicity could be attributed. The task is challenging mainly due to two constraints: the small training dataset and imbalanced class distribution. Our paper investigates two techniques, semi-supervised learning and learning with Self-Adjusting Dice Loss, for tackling these challenges. Our submitted system (ranked ninth on the leader board) consisted of an ensemble of various pre-trained Transformer Language Models trained using ei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01566","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/2104.01566/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":"2026-07-05T02:29:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6FdKoJCZB0dTZgIKX3V1ZivDv64WUkpCFq3R0aYOeaEurSuMbRw8j5QwQDpJ7WOHjcATq/ylhlcCE8WoxGUfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T07:49:19.541132Z"},"content_sha256":"42a3cd756bbc0c29e57881c10dbc335862513bf680333afc467291be613d987a","schema_version":"1.0","event_id":"sha256:42a3cd756bbc0c29e57881c10dbc335862513bf680333afc467291be613d987a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CX6ULRWAGFWTZRSP6BAOSDLOVK/bundle.json","state_url":"https://pith.science/pith/CX6ULRWAGFWTZRSP6BAOSDLOVK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CX6ULRWAGFWTZRSP6BAOSDLOVK/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":"2026-08-18T07:49:19Z","links":{"resolver":"https://pith.science/pith/CX6ULRWAGFWTZRSP6BAOSDLOVK","bundle":"https://pith.science/pith/CX6ULRWAGFWTZRSP6BAOSDLOVK/bundle.json","state":"https://pith.science/pith/CX6ULRWAGFWTZRSP6BAOSDLOVK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CX6ULRWAGFWTZRSP6BAOSDLOVK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CX6ULRWAGFWTZRSP6BAOSDLOVK","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":"cc0f2d52de0794b16d2c0cbfc7c3208cbee9ecde5018fd51f19d6885e70ceec5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-04T08:39:55Z","title_canon_sha256":"898df35af1a3f7bc6e0df7a2603ce97dd423fff838b018e692afbff1bc17694c"},"schema_version":"1.0","source":{"id":"2104.01566","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.01566","created_at":"2026-07-05T02:29:01Z"},{"alias_kind":"arxiv_version","alias_value":"2104.01566v1","created_at":"2026-07-05T02:29:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01566","created_at":"2026-07-05T02:29:01Z"},{"alias_kind":"pith_short_12","alias_value":"CX6ULRWAGFWT","created_at":"2026-07-05T02:29:01Z"},{"alias_kind":"pith_short_16","alias_value":"CX6ULRWAGFWTZRSP","created_at":"2026-07-05T02:29:01Z"},{"alias_kind":"pith_short_8","alias_value":"CX6ULRWA","created_at":"2026-07-05T02:29:01Z"}],"graph_snapshots":[{"event_id":"sha256:42a3cd756bbc0c29e57881c10dbc335862513bf680333afc467291be613d987a","target":"graph","created_at":"2026-07-05T02:29:01Z","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/2104.01566/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we present our approach and findings for SemEval-2021 Task 5 - Toxic Spans Detection. The task's main aim was to identify spans to which a given text's toxicity could be attributed. The task is challenging mainly due to two constraints: the small training dataset and imbalanced class distribution. Our paper investigates two techniques, semi-supervised learning and learning with Self-Adjusting Dice Loss, for tackling these challenges. Our submitted system (ranked ninth on the leader board) consisted of an ensemble of various pre-trained Transformer Language Models trained using ei","authors_text":"Abhay Kaushik, Archit Bansal, Ashutosh Modi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-04T08:39:55Z","title":"IITK@Detox at SemEval-2021 Task 5: Semi-Supervised Learning and Dice Loss for Toxic Spans Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01566","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:e564a113e872f4aff4574c162a7521788d321671323922b29020872b762747f6","target":"record","created_at":"2026-07-05T02:29:01Z","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":"cc0f2d52de0794b16d2c0cbfc7c3208cbee9ecde5018fd51f19d6885e70ceec5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-04T08:39:55Z","title_canon_sha256":"898df35af1a3f7bc6e0df7a2603ce97dd423fff838b018e692afbff1bc17694c"},"schema_version":"1.0","source":{"id":"2104.01566","kind":"arxiv","version":1}},"canonical_sha256":"15fd45c6c0316d3cc64ff040e90d6eaaac6a6fe89795a672449b6e637079f7fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15fd45c6c0316d3cc64ff040e90d6eaaac6a6fe89795a672449b6e637079f7fe","first_computed_at":"2026-07-05T02:29:01.383394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:29:01.383394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R6VYr+n/l/gcPi41N0RYl7XWW1+K7fQfj3saPEglMKl3TTQCHwoaMikzPbPUNG2Y+3ntGNvKa2Kq2ZnkVtqlDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:29:01.383873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.01566","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e564a113e872f4aff4574c162a7521788d321671323922b29020872b762747f6","sha256:42a3cd756bbc0c29e57881c10dbc335862513bf680333afc467291be613d987a"],"state_sha256":"bad54fe3c6f7ebe8a8def55492f8683248f658f3404bd1b6b83bab3a16051321"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zWksPETEN+Z+ldYKtS+YztWlbznK1uOSBWyv/dPAbmA28uCLSAdQo7kMdXD7ek2Re5NWeEdL52bePHMpEreRBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T07:49:19.544819Z","bundle_sha256":"5cda2a1b324133663b9cc36fed52ecc1445bf13ccc393a3358ac29c0803c0697"}}