{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MWOX7VCSPTVZNY5OL5H2LW2NLQ","short_pith_number":"pith:MWOX7VCS","canonical_record":{"source":{"id":"2109.08113","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-16T17:07:45Z","cross_cats_sorted":[],"title_canon_sha256":"42f450db3d317797ceb8cd2d5bec6ffa825dd520588a6225161fefdc0836e6f0","abstract_canon_sha256":"81f9e01b4da8201b24c6a19ce817719ea681a775e7c24cc8286815655294a9d9"},"schema_version":"1.0"},"canonical_sha256":"659d7fd4527ceb96e3ae5f4fa5db4d5c3946581e7803473fe1a6302549320c00","source":{"kind":"arxiv","id":"2109.08113","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.08113","created_at":"2026-07-05T03:27:58Z"},{"alias_kind":"arxiv_version","alias_value":"2109.08113v2","created_at":"2026-07-05T03:27:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.08113","created_at":"2026-07-05T03:27:58Z"},{"alias_kind":"pith_short_12","alias_value":"MWOX7VCSPTVZ","created_at":"2026-07-05T03:27:58Z"},{"alias_kind":"pith_short_16","alias_value":"MWOX7VCSPTVZNY5O","created_at":"2026-07-05T03:27:58Z"},{"alias_kind":"pith_short_8","alias_value":"MWOX7VCS","created_at":"2026-07-05T03:27:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MWOX7VCSPTVZNY5OL5H2LW2NLQ","target":"record","payload":{"canonical_record":{"source":{"id":"2109.08113","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-16T17:07:45Z","cross_cats_sorted":[],"title_canon_sha256":"42f450db3d317797ceb8cd2d5bec6ffa825dd520588a6225161fefdc0836e6f0","abstract_canon_sha256":"81f9e01b4da8201b24c6a19ce817719ea681a775e7c24cc8286815655294a9d9"},"schema_version":"1.0"},"canonical_sha256":"659d7fd4527ceb96e3ae5f4fa5db4d5c3946581e7803473fe1a6302549320c00","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:58.800531Z","signature_b64":"OsbN3iXZ5GJHHFCiHbvFiXdyHGOB6R5srMlfVe2oFpHnTF+r6hZdJQMtKLk53CPO2hUD4QwwpkZucl4XI12FBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"659d7fd4527ceb96e3ae5f4fa5db4d5c3946581e7803473fe1a6302549320c00","last_reissued_at":"2026-07-05T03:27:58.800092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:58.800092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.08113","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":"2026-07-05T03:27:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FtHtTXxc5rh3mCzpM9WzBG7Vzn1gHZzJP3Og7Z9vW7a/ZH7dSkPo3+UIaKfHlikCBTuF2/4SWYZ398ySRrpdDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T00:48:36.722057Z"},"content_sha256":"dd3e3e2d7e43a920452cf846c4b4b6e43b317c31fee08fdb00e05d65304871ed","schema_version":"1.0","event_id":"sha256:dd3e3e2d7e43a920452cf846c4b4b6e43b317c31fee08fdb00e05d65304871ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MWOX7VCSPTVZNY5OL5H2LW2NLQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MeLT: Message-Level Transformer with Masked Document Representations as Pre-Training for Stance Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"H. Andrew Schwartz, Matthew Matero, Nikita Soni, Niranjan Balasubramanian","submitted_at":"2021-09-16T17:07:45Z","abstract_excerpt":"Much of natural language processing is focused on leveraging large capacity language models, typically trained over single messages with a task of predicting one or more tokens. However, modeling human language at higher-levels of context (i.e., sequences of messages) is under-explored. In stance detection and other social media tasks where the goal is to predict an attribute of a message, we have contextual data that is loosely semantically connected by authorship. Here, we introduce Message-Level Transformer (MeLT) -- a hierarchical message-encoder pre-trained over Twitter and applied to the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.08113","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/2109.08113/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":"2026-07-05T03:27:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BCz0LGS/ni93F6zvXp/iQ57usbVHidpOqdb5d/ftpMQzEwvKN0nLGlqtdTTo//nQVJBNAkJgoxwgQx6TNbvTCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T00:48:36.722443Z"},"content_sha256":"4192d5e9e2e7e4ecd864f971710e71e4df5a03ae2b9dde59d0bf9a18e74bf4d3","schema_version":"1.0","event_id":"sha256:4192d5e9e2e7e4ecd864f971710e71e4df5a03ae2b9dde59d0bf9a18e74bf4d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MWOX7VCSPTVZNY5OL5H2LW2NLQ/bundle.json","state_url":"https://pith.science/pith/MWOX7VCSPTVZNY5OL5H2LW2NLQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MWOX7VCSPTVZNY5OL5H2LW2NLQ/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":"2026-07-17T00:48:36Z","links":{"resolver":"https://pith.science/pith/MWOX7VCSPTVZNY5OL5H2LW2NLQ","bundle":"https://pith.science/pith/MWOX7VCSPTVZNY5OL5H2LW2NLQ/bundle.json","state":"https://pith.science/pith/MWOX7VCSPTVZNY5OL5H2LW2NLQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MWOX7VCSPTVZNY5OL5H2LW2NLQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MWOX7VCSPTVZNY5OL5H2LW2NLQ","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":"81f9e01b4da8201b24c6a19ce817719ea681a775e7c24cc8286815655294a9d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-16T17:07:45Z","title_canon_sha256":"42f450db3d317797ceb8cd2d5bec6ffa825dd520588a6225161fefdc0836e6f0"},"schema_version":"1.0","source":{"id":"2109.08113","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.08113","created_at":"2026-07-05T03:27:58Z"},{"alias_kind":"arxiv_version","alias_value":"2109.08113v2","created_at":"2026-07-05T03:27:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.08113","created_at":"2026-07-05T03:27:58Z"},{"alias_kind":"pith_short_12","alias_value":"MWOX7VCSPTVZ","created_at":"2026-07-05T03:27:58Z"},{"alias_kind":"pith_short_16","alias_value":"MWOX7VCSPTVZNY5O","created_at":"2026-07-05T03:27:58Z"},{"alias_kind":"pith_short_8","alias_value":"MWOX7VCS","created_at":"2026-07-05T03:27:58Z"}],"graph_snapshots":[{"event_id":"sha256:4192d5e9e2e7e4ecd864f971710e71e4df5a03ae2b9dde59d0bf9a18e74bf4d3","target":"graph","created_at":"2026-07-05T03:27:58Z","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/2109.08113/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Much of natural language processing is focused on leveraging large capacity language models, typically trained over single messages with a task of predicting one or more tokens. However, modeling human language at higher-levels of context (i.e., sequences of messages) is under-explored. In stance detection and other social media tasks where the goal is to predict an attribute of a message, we have contextual data that is loosely semantically connected by authorship. Here, we introduce Message-Level Transformer (MeLT) -- a hierarchical message-encoder pre-trained over Twitter and applied to the","authors_text":"H. Andrew Schwartz, Matthew Matero, Nikita Soni, Niranjan Balasubramanian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-16T17:07:45Z","title":"MeLT: Message-Level Transformer with Masked Document Representations as Pre-Training for Stance Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.08113","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:dd3e3e2d7e43a920452cf846c4b4b6e43b317c31fee08fdb00e05d65304871ed","target":"record","created_at":"2026-07-05T03:27:58Z","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":"81f9e01b4da8201b24c6a19ce817719ea681a775e7c24cc8286815655294a9d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-16T17:07:45Z","title_canon_sha256":"42f450db3d317797ceb8cd2d5bec6ffa825dd520588a6225161fefdc0836e6f0"},"schema_version":"1.0","source":{"id":"2109.08113","kind":"arxiv","version":2}},"canonical_sha256":"659d7fd4527ceb96e3ae5f4fa5db4d5c3946581e7803473fe1a6302549320c00","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"659d7fd4527ceb96e3ae5f4fa5db4d5c3946581e7803473fe1a6302549320c00","first_computed_at":"2026-07-05T03:27:58.800092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:27:58.800092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OsbN3iXZ5GJHHFCiHbvFiXdyHGOB6R5srMlfVe2oFpHnTF+r6hZdJQMtKLk53CPO2hUD4QwwpkZucl4XI12FBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:27:58.800531Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.08113","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd3e3e2d7e43a920452cf846c4b4b6e43b317c31fee08fdb00e05d65304871ed","sha256:4192d5e9e2e7e4ecd864f971710e71e4df5a03ae2b9dde59d0bf9a18e74bf4d3"],"state_sha256":"e4652b8008d636d81175c3ccfc5130b939d848ae07dbb6020d742f0250bd80d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SEIEQxJB+Nfm3RkiveW27SVFquHT57OxT64BlOiQMYrGAvG7NT+dAsdWVhXxE1MMWfzY1LNOfG1fAMF1Wmw/Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T00:48:36.724939Z","bundle_sha256":"c4f02e5132f47e0f52470722a92ba79e8e9ba36b2f31b0a6dce6d4d6ffe7dd62"}}