{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MPJXNXUNSFBCGLXZPKOH74YMQO","short_pith_number":"pith:MPJXNXUN","canonical_record":{"source":{"id":"2505.01006","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-02T05:04:41Z","cross_cats_sorted":[],"title_canon_sha256":"e0c542e813a5f90d6b6b78a036d19131e199da66b20bdefdd26b58475a64b3b6","abstract_canon_sha256":"21d092af59b9719bd937170ed61f99e81fa2464921120f6cf89fc66e9f1a03d1"},"schema_version":"1.0"},"canonical_sha256":"63d376de8d9142232ef97a9c7ff30c839f71f3cac03c481d1b0f2a7aede58d72","source":{"kind":"arxiv","id":"2505.01006","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.01006","created_at":"2026-07-05T10:57:43Z"},{"alias_kind":"arxiv_version","alias_value":"2505.01006v1","created_at":"2026-07-05T10:57:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01006","created_at":"2026-07-05T10:57:43Z"},{"alias_kind":"pith_short_12","alias_value":"MPJXNXUNSFBC","created_at":"2026-07-05T10:57:43Z"},{"alias_kind":"pith_short_16","alias_value":"MPJXNXUNSFBCGLXZ","created_at":"2026-07-05T10:57:43Z"},{"alias_kind":"pith_short_8","alias_value":"MPJXNXUN","created_at":"2026-07-05T10:57:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MPJXNXUNSFBCGLXZPKOH74YMQO","target":"record","payload":{"canonical_record":{"source":{"id":"2505.01006","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-02T05:04:41Z","cross_cats_sorted":[],"title_canon_sha256":"e0c542e813a5f90d6b6b78a036d19131e199da66b20bdefdd26b58475a64b3b6","abstract_canon_sha256":"21d092af59b9719bd937170ed61f99e81fa2464921120f6cf89fc66e9f1a03d1"},"schema_version":"1.0"},"canonical_sha256":"63d376de8d9142232ef97a9c7ff30c839f71f3cac03c481d1b0f2a7aede58d72","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:43.444612Z","signature_b64":"ifeXwvbkHXpP8kgt924yoDiXoA8jjAv0GqfPIoycDwijb/KRz/Mpf7HJmL7K22RR6AxdnP7nvfO4kf2lQQo1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63d376de8d9142232ef97a9c7ff30c839f71f3cac03c481d1b0f2a7aede58d72","last_reissued_at":"2026-07-05T10:57:43.444112Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:43.444112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.01006","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":"2026-07-05T10:57:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6C31Cstj759BlcOPsGDpRH7RBGsTe8WY2dPUtBqyAM22/vfqz+X5MK9FpLjumlZIAjV1Sc/qB5GHJkdB/PoPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:33:54.578570Z"},"content_sha256":"7af5ab51a711d4639e4818f992910403ab28c3a380d62ccb0bf6af1cc5f4d866","schema_version":"1.0","event_id":"sha256:7af5ab51a711d4639e4818f992910403ab28c3a380d62ccb0bf6af1cc5f4d866"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MPJXNXUNSFBCGLXZPKOH74YMQO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Token-free Models for Sarcasm Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kanika Agarwal, Maitreya Sonawane, Nishanth Sanjeev, Sumit Mamtani","submitted_at":"2025-05-02T05:04:41Z","abstract_excerpt":"Tokenization is a foundational step in most natural language processing (NLP) pipelines, yet it introduces challenges such as vocabulary mismatch and out-of-vocabulary issues. Recent work has shown that models operating directly on raw text at the byte or character level can mitigate these limitations. In this paper, we evaluate two token-free models, ByT5 and CANINE, on the task of sarcasm detection in both social media (Twitter) and non-social media (news headlines) domains. We fine-tune and benchmark these models against token-based baselines and state-of-the-art approaches. Our results sho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01006","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/2505.01006/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":"2026-07-05T10:57:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2KOjDTHFtMfysjmZbyDAbSHjmekWyHbaSNC9S1EA3+n5M7c6aTNpk8RoakO0Cms5wjyrGQh2IwDlWkj73FZABA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:33:54.579604Z"},"content_sha256":"bc377bace44174b1e7aed9b3138a48e1232a2d13c4626029468d3cf24cc6ce60","schema_version":"1.0","event_id":"sha256:bc377bace44174b1e7aed9b3138a48e1232a2d13c4626029468d3cf24cc6ce60"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MPJXNXUNSFBCGLXZPKOH74YMQO/bundle.json","state_url":"https://pith.science/pith/MPJXNXUNSFBCGLXZPKOH74YMQO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MPJXNXUNSFBCGLXZPKOH74YMQO/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":"2026-08-17T12:33:54Z","links":{"resolver":"https://pith.science/pith/MPJXNXUNSFBCGLXZPKOH74YMQO","bundle":"https://pith.science/pith/MPJXNXUNSFBCGLXZPKOH74YMQO/bundle.json","state":"https://pith.science/pith/MPJXNXUNSFBCGLXZPKOH74YMQO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MPJXNXUNSFBCGLXZPKOH74YMQO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MPJXNXUNSFBCGLXZPKOH74YMQO","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":"21d092af59b9719bd937170ed61f99e81fa2464921120f6cf89fc66e9f1a03d1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-02T05:04:41Z","title_canon_sha256":"e0c542e813a5f90d6b6b78a036d19131e199da66b20bdefdd26b58475a64b3b6"},"schema_version":"1.0","source":{"id":"2505.01006","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.01006","created_at":"2026-07-05T10:57:43Z"},{"alias_kind":"arxiv_version","alias_value":"2505.01006v1","created_at":"2026-07-05T10:57:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01006","created_at":"2026-07-05T10:57:43Z"},{"alias_kind":"pith_short_12","alias_value":"MPJXNXUNSFBC","created_at":"2026-07-05T10:57:43Z"},{"alias_kind":"pith_short_16","alias_value":"MPJXNXUNSFBCGLXZ","created_at":"2026-07-05T10:57:43Z"},{"alias_kind":"pith_short_8","alias_value":"MPJXNXUN","created_at":"2026-07-05T10:57:43Z"}],"graph_snapshots":[{"event_id":"sha256:bc377bace44174b1e7aed9b3138a48e1232a2d13c4626029468d3cf24cc6ce60","target":"graph","created_at":"2026-07-05T10:57:43Z","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/2505.01006/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokenization is a foundational step in most natural language processing (NLP) pipelines, yet it introduces challenges such as vocabulary mismatch and out-of-vocabulary issues. Recent work has shown that models operating directly on raw text at the byte or character level can mitigate these limitations. In this paper, we evaluate two token-free models, ByT5 and CANINE, on the task of sarcasm detection in both social media (Twitter) and non-social media (news headlines) domains. We fine-tune and benchmark these models against token-based baselines and state-of-the-art approaches. Our results sho","authors_text":"Kanika Agarwal, Maitreya Sonawane, Nishanth Sanjeev, Sumit Mamtani","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-02T05:04:41Z","title":"Token-free Models for Sarcasm Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01006","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":"sha256:7af5ab51a711d4639e4818f992910403ab28c3a380d62ccb0bf6af1cc5f4d866","target":"record","created_at":"2026-07-05T10:57:43Z","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":"21d092af59b9719bd937170ed61f99e81fa2464921120f6cf89fc66e9f1a03d1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-02T05:04:41Z","title_canon_sha256":"e0c542e813a5f90d6b6b78a036d19131e199da66b20bdefdd26b58475a64b3b6"},"schema_version":"1.0","source":{"id":"2505.01006","kind":"arxiv","version":1}},"canonical_sha256":"63d376de8d9142232ef97a9c7ff30c839f71f3cac03c481d1b0f2a7aede58d72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63d376de8d9142232ef97a9c7ff30c839f71f3cac03c481d1b0f2a7aede58d72","first_computed_at":"2026-07-05T10:57:43.444112Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:57:43.444112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ifeXwvbkHXpP8kgt924yoDiXoA8jjAv0GqfPIoycDwijb/KRz/Mpf7HJmL7K22RR6AxdnP7nvfO4kf2lQQo1AA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:57:43.444612Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.01006","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7af5ab51a711d4639e4818f992910403ab28c3a380d62ccb0bf6af1cc5f4d866","sha256:bc377bace44174b1e7aed9b3138a48e1232a2d13c4626029468d3cf24cc6ce60"],"state_sha256":"f0966f08ded722cd3a98a23d6e6755c9ddbfcda4e6f94defc78f660492c8f276"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dymLcthZG+BMJxEbRJbaXnVCsKPxi8BU0bSsjdgtsAV8w4ehqJhrTiAEK9pLHtd6vy5y1A8kAJ9us27wArH1Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T12:33:54.593141Z","bundle_sha256":"9e66ad876fa712d0d560c94be210532e21c0e0fb3cbf3373eb29efba8da2984e"}}