{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:M7PFVBW4HSVI5BXF2BBNP6RGPD","short_pith_number":"pith:M7PFVBW4","canonical_record":{"source":{"id":"1903.11850","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-28T09:30:16Z","cross_cats_sorted":[],"title_canon_sha256":"2f7369d2d9c2084408ed67da53feb9acc2fc0d6cfa4a83a2809b1370367af097","abstract_canon_sha256":"1ca3c5c47e46e2148816bd99aac6e6adef710ad390c6688cf0d02729f8327bcd"},"schema_version":"1.0"},"canonical_sha256":"67de5a86dc3caa8e86e5d042d7fa2678e8d0198c1bd2e9027e3aa560307314ba","source":{"kind":"arxiv","id":"1903.11850","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.11850","created_at":"2026-05-17T23:49:58Z"},{"alias_kind":"arxiv_version","alias_value":"1903.11850v1","created_at":"2026-05-17T23:49:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.11850","created_at":"2026-05-17T23:49:58Z"},{"alias_kind":"pith_short_12","alias_value":"M7PFVBW4HSVI","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"M7PFVBW4HSVI5BXF","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"M7PFVBW4","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:M7PFVBW4HSVI5BXF2BBNP6RGPD","target":"record","payload":{"canonical_record":{"source":{"id":"1903.11850","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-28T09:30:16Z","cross_cats_sorted":[],"title_canon_sha256":"2f7369d2d9c2084408ed67da53feb9acc2fc0d6cfa4a83a2809b1370367af097","abstract_canon_sha256":"1ca3c5c47e46e2148816bd99aac6e6adef710ad390c6688cf0d02729f8327bcd"},"schema_version":"1.0"},"canonical_sha256":"67de5a86dc3caa8e86e5d042d7fa2678e8d0198c1bd2e9027e3aa560307314ba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:58.926819Z","signature_b64":"yvNVvt8ouvPEJK4ZShBfCf3OZH1sb0R/OzOkOS63iVSmK0T1xRuUU23h0yLYsArT+t6HEJMrVz0Uk06NdHlKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67de5a86dc3caa8e86e5d042d7fa2678e8d0198c1bd2e9027e3aa560307314ba","last_reissued_at":"2026-05-17T23:49:58.926181Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:58.926181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.11850","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":"2026-05-17T23:49:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yz6G4YWrpyMMTxBXbHmWHi5+Yi409Sf8+8wrcLRj1ufCqDyGgEe146xZ1IaLHAJl2zTAG2ClHjDDyaefnWcaCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T09:34:53.644218Z"},"content_sha256":"6e45adfd7adaab98eadc1ca09d2b24de4f98b385aaed311e156e1f32bfcb8549","schema_version":"1.0","event_id":"sha256:6e45adfd7adaab98eadc1ca09d2b24de4f98b385aaed311e156e1f32bfcb8549"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:M7PFVBW4HSVI5BXF2BBNP6RGPD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mining Discourse Markers for Unsupervised Sentence Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Camille Pradel, Damien Sileo, Philippe Muller, Tim Van-De-Cruys","submitted_at":"2019-03-28T09:30:16Z","abstract_excerpt":"Current state of the art systems in NLP heavily rely on manually annotated datasets, which are expensive to construct. Very little work adequately exploits unannotated data -- such as discourse markers between sentences -- mainly because of data sparseness and ineffective extraction methods. In the present work, we propose a method to automatically discover sentence pairs with relevant discourse markers, and apply it to massive amounts of data. Our resulting dataset contains 174 discourse markers with at least 10k examples each, even for rare markers such as coincidentally or amazingly We use "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.11850","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":""},"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":"2026-05-17T23:49:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"os5chuSGHWZA+JPghhu7oVfWZKQ/swmpRwgM//ZNJoCjrGh6ypME5C+rVv7h8Zvh4lF4nVvwCoowVUOJXbTeAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T09:34:53.644908Z"},"content_sha256":"f4b1782bf22536a305115fede45a06b4086700a2852dbac3bd44f45ab7dfdb32","schema_version":"1.0","event_id":"sha256:f4b1782bf22536a305115fede45a06b4086700a2852dbac3bd44f45ab7dfdb32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M7PFVBW4HSVI5BXF2BBNP6RGPD/bundle.json","state_url":"https://pith.science/pith/M7PFVBW4HSVI5BXF2BBNP6RGPD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M7PFVBW4HSVI5BXF2BBNP6RGPD/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":"2026-05-31T09:34:53Z","links":{"resolver":"https://pith.science/pith/M7PFVBW4HSVI5BXF2BBNP6RGPD","bundle":"https://pith.science/pith/M7PFVBW4HSVI5BXF2BBNP6RGPD/bundle.json","state":"https://pith.science/pith/M7PFVBW4HSVI5BXF2BBNP6RGPD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M7PFVBW4HSVI5BXF2BBNP6RGPD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:M7PFVBW4HSVI5BXF2BBNP6RGPD","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":"1ca3c5c47e46e2148816bd99aac6e6adef710ad390c6688cf0d02729f8327bcd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-28T09:30:16Z","title_canon_sha256":"2f7369d2d9c2084408ed67da53feb9acc2fc0d6cfa4a83a2809b1370367af097"},"schema_version":"1.0","source":{"id":"1903.11850","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.11850","created_at":"2026-05-17T23:49:58Z"},{"alias_kind":"arxiv_version","alias_value":"1903.11850v1","created_at":"2026-05-17T23:49:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.11850","created_at":"2026-05-17T23:49:58Z"},{"alias_kind":"pith_short_12","alias_value":"M7PFVBW4HSVI","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"M7PFVBW4HSVI5BXF","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"M7PFVBW4","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:f4b1782bf22536a305115fede45a06b4086700a2852dbac3bd44f45ab7dfdb32","target":"graph","created_at":"2026-05-17T23:49:58Z","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"},"paper":{"abstract_excerpt":"Current state of the art systems in NLP heavily rely on manually annotated datasets, which are expensive to construct. Very little work adequately exploits unannotated data -- such as discourse markers between sentences -- mainly because of data sparseness and ineffective extraction methods. In the present work, we propose a method to automatically discover sentence pairs with relevant discourse markers, and apply it to massive amounts of data. Our resulting dataset contains 174 discourse markers with at least 10k examples each, even for rare markers such as coincidentally or amazingly We use ","authors_text":"Camille Pradel, Damien Sileo, Philippe Muller, Tim Van-De-Cruys","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-28T09:30:16Z","title":"Mining Discourse Markers for Unsupervised Sentence Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.11850","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":"sha256:6e45adfd7adaab98eadc1ca09d2b24de4f98b385aaed311e156e1f32bfcb8549","target":"record","created_at":"2026-05-17T23:49:58Z","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":"1ca3c5c47e46e2148816bd99aac6e6adef710ad390c6688cf0d02729f8327bcd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-28T09:30:16Z","title_canon_sha256":"2f7369d2d9c2084408ed67da53feb9acc2fc0d6cfa4a83a2809b1370367af097"},"schema_version":"1.0","source":{"id":"1903.11850","kind":"arxiv","version":1}},"canonical_sha256":"67de5a86dc3caa8e86e5d042d7fa2678e8d0198c1bd2e9027e3aa560307314ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67de5a86dc3caa8e86e5d042d7fa2678e8d0198c1bd2e9027e3aa560307314ba","first_computed_at":"2026-05-17T23:49:58.926181Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:58.926181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yvNVvt8ouvPEJK4ZShBfCf3OZH1sb0R/OzOkOS63iVSmK0T1xRuUU23h0yLYsArT+t6HEJMrVz0Uk06NdHlKBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:58.926819Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.11850","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e45adfd7adaab98eadc1ca09d2b24de4f98b385aaed311e156e1f32bfcb8549","sha256:f4b1782bf22536a305115fede45a06b4086700a2852dbac3bd44f45ab7dfdb32"],"state_sha256":"0f65512ad4c18ce1555bf4c90a104814421f2ac12971f84c358766b33b1e234c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/bAW2B4QbaIAzAA69Xxnazu4l9MdvuCT5qTNxgknUohNALs0CfbPHkS7/9L0G/pRQ057qFTh4jUq5my0KjmpBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T09:34:53.648581Z","bundle_sha256":"5e9372dc56735fa0039d6e3a4f5374df41a00e4cbd1ffa168fef6c7a01a61581"}}