{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:75KFZUZRTBPR7W6O5BI65ZQ4A4","short_pith_number":"pith:75KFZUZR","canonical_record":{"source":{"id":"2204.03954","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-08T09:28:20Z","cross_cats_sorted":[],"title_canon_sha256":"dd5c7bb8dbb82ee4bfd2bca7872d6beecd9ce7d78de6f2e09457206e6627dd8b","abstract_canon_sha256":"16383b3b999d2a49e9ca65c7485b9d8d1d155c69b7424ba0bfbf1ebdcbb76ecf"},"schema_version":"1.0"},"canonical_sha256":"ff545cd331985f1fdbcee851eee61c071ef3cfd83b27adb15d82fc5d618fab3a","source":{"kind":"arxiv","id":"2204.03954","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.03954","created_at":"2026-07-05T10:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"2204.03954v6","created_at":"2026-07-05T10:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03954","created_at":"2026-07-05T10:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"75KFZUZRTBPR","created_at":"2026-07-05T10:02:39Z"},{"alias_kind":"pith_short_16","alias_value":"75KFZUZRTBPR7W6O","created_at":"2026-07-05T10:02:39Z"},{"alias_kind":"pith_short_8","alias_value":"75KFZUZR","created_at":"2026-07-05T10:02:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:75KFZUZRTBPR7W6O5BI65ZQ4A4","target":"record","payload":{"canonical_record":{"source":{"id":"2204.03954","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-08T09:28:20Z","cross_cats_sorted":[],"title_canon_sha256":"dd5c7bb8dbb82ee4bfd2bca7872d6beecd9ce7d78de6f2e09457206e6627dd8b","abstract_canon_sha256":"16383b3b999d2a49e9ca65c7485b9d8d1d155c69b7424ba0bfbf1ebdcbb76ecf"},"schema_version":"1.0"},"canonical_sha256":"ff545cd331985f1fdbcee851eee61c071ef3cfd83b27adb15d82fc5d618fab3a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:39.205191Z","signature_b64":"rDpUGXVfnziHqgBwlb0V6+OYgFqElX3dC1GC1mXntK7Utk5quy4EloHOD+KWuqbfQ2N8FSO/FiipJnyAHqM8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff545cd331985f1fdbcee851eee61c071ef3cfd83b27adb15d82fc5d618fab3a","last_reissued_at":"2026-07-05T10:02:39.204753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:39.204753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.03954","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:02:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l+NX/NXdat1H/ufAahW3UG7nw1PTNRpZBLIDO0CV5jA4VJN+yqAQodbiT+2A1ky1X7GMiO7l/Fnmlrh9QZpuDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:05:27.548502Z"},"content_sha256":"c745ec91419ffa4f81ac6ad143e98d311d55740906634f24711fedc7ab961678","schema_version":"1.0","event_id":"sha256:c745ec91419ffa4f81ac6ad143e98d311d55740906634f24711fedc7ab961678"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:75KFZUZRTBPR7W6O5BI65ZQ4A4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Are We Really Making Much Progress in Text Classification? A Comparative Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andor Diera, Ansgar Scherp, Bao Xin Lin, Bhakti Khera, Fabian Karl, Lukas Galke, Tim Meuser, Tushar Singhal","submitted_at":"2022-04-08T09:28:20Z","abstract_excerpt":"We analyze various methods for single-label and multi-label text classification across well-known datasets, categorizing them into bag-of-words, sequence-based, graph-based, and hierarchical approaches. Despite the surge in methods like graph-based models, encoder-only pre-trained language models, notably BERT, remain state-of-the-art. However, recent findings suggest simpler models like logistic regression and trigram-based SVMs outperform newer techniques. While decoder-only generative language models show promise in learning with limited data, they lag behind encoder-only models in performa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03954","kind":"arxiv","version":6},"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/2204.03954/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":"2026-07-05T10:02:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6cvWQjNqTT4frE0KMXjjSEWEKldizgTLdyNiM8qcbWPLD0n0jO4AkEbI60JBc0NmFHCU1rz/5+N0+3l2UdvOCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:05:27.549053Z"},"content_sha256":"6d155f1cc734488a8441aa5134f090560e8f3323ae015a86555c1e75efecd14d","schema_version":"1.0","event_id":"sha256:6d155f1cc734488a8441aa5134f090560e8f3323ae015a86555c1e75efecd14d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/75KFZUZRTBPR7W6O5BI65ZQ4A4/bundle.json","state_url":"https://pith.science/pith/75KFZUZRTBPR7W6O5BI65ZQ4A4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/75KFZUZRTBPR7W6O5BI65ZQ4A4/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":"2026-08-09T03:05:27Z","links":{"resolver":"https://pith.science/pith/75KFZUZRTBPR7W6O5BI65ZQ4A4","bundle":"https://pith.science/pith/75KFZUZRTBPR7W6O5BI65ZQ4A4/bundle.json","state":"https://pith.science/pith/75KFZUZRTBPR7W6O5BI65ZQ4A4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/75KFZUZRTBPR7W6O5BI65ZQ4A4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:75KFZUZRTBPR7W6O5BI65ZQ4A4","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":"16383b3b999d2a49e9ca65c7485b9d8d1d155c69b7424ba0bfbf1ebdcbb76ecf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-08T09:28:20Z","title_canon_sha256":"dd5c7bb8dbb82ee4bfd2bca7872d6beecd9ce7d78de6f2e09457206e6627dd8b"},"schema_version":"1.0","source":{"id":"2204.03954","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.03954","created_at":"2026-07-05T10:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"2204.03954v6","created_at":"2026-07-05T10:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03954","created_at":"2026-07-05T10:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"75KFZUZRTBPR","created_at":"2026-07-05T10:02:39Z"},{"alias_kind":"pith_short_16","alias_value":"75KFZUZRTBPR7W6O","created_at":"2026-07-05T10:02:39Z"},{"alias_kind":"pith_short_8","alias_value":"75KFZUZR","created_at":"2026-07-05T10:02:39Z"}],"graph_snapshots":[{"event_id":"sha256:6d155f1cc734488a8441aa5134f090560e8f3323ae015a86555c1e75efecd14d","target":"graph","created_at":"2026-07-05T10:02:39Z","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/2204.03954/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We analyze various methods for single-label and multi-label text classification across well-known datasets, categorizing them into bag-of-words, sequence-based, graph-based, and hierarchical approaches. Despite the surge in methods like graph-based models, encoder-only pre-trained language models, notably BERT, remain state-of-the-art. However, recent findings suggest simpler models like logistic regression and trigram-based SVMs outperform newer techniques. While decoder-only generative language models show promise in learning with limited data, they lag behind encoder-only models in performa","authors_text":"Andor Diera, Ansgar Scherp, Bao Xin Lin, Bhakti Khera, Fabian Karl, Lukas Galke, Tim Meuser, Tushar Singhal","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-08T09:28:20Z","title":"Are We Really Making Much Progress in Text Classification? A Comparative Review"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03954","kind":"arxiv","version":6},"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:c745ec91419ffa4f81ac6ad143e98d311d55740906634f24711fedc7ab961678","target":"record","created_at":"2026-07-05T10:02:39Z","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":"16383b3b999d2a49e9ca65c7485b9d8d1d155c69b7424ba0bfbf1ebdcbb76ecf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-08T09:28:20Z","title_canon_sha256":"dd5c7bb8dbb82ee4bfd2bca7872d6beecd9ce7d78de6f2e09457206e6627dd8b"},"schema_version":"1.0","source":{"id":"2204.03954","kind":"arxiv","version":6}},"canonical_sha256":"ff545cd331985f1fdbcee851eee61c071ef3cfd83b27adb15d82fc5d618fab3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff545cd331985f1fdbcee851eee61c071ef3cfd83b27adb15d82fc5d618fab3a","first_computed_at":"2026-07-05T10:02:39.204753Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:39.204753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rDpUGXVfnziHqgBwlb0V6+OYgFqElX3dC1GC1mXntK7Utk5quy4EloHOD+KWuqbfQ2N8FSO/FiipJnyAHqM8DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:39.205191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.03954","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c745ec91419ffa4f81ac6ad143e98d311d55740906634f24711fedc7ab961678","sha256:6d155f1cc734488a8441aa5134f090560e8f3323ae015a86555c1e75efecd14d"],"state_sha256":"9cde0e7e2a213242ea2616c0b659d83fc11b7e6dcf52aa54936a18ed8fff5a10"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iwvshqx0Tp9XQb7QBxpdAfWiFHwWTNSEzmXnUA4mmtk5DC/OukPcr4+13Aj+vnvvijUYByDQOWfdz/OhYgw9Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:05:27.553659Z","bundle_sha256":"b4ece8d275950b34c2b0ade304dbf1b995121985709b5ac335950ebecff18463"}}