{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:W74QOWQSZUF47L2FKE336HYMC4","short_pith_number":"pith:W74QOWQS","canonical_record":{"source":{"id":"1704.04100","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-13T12:54:30Z","cross_cats_sorted":[],"title_canon_sha256":"8a7249d98817b325aadd04af19276f0fd99a49e8ac6788acd9a9be7d3a2e6e14","abstract_canon_sha256":"80d11eb34a10425a521641d4656753f2a3e49252b10e84a53d2cc90c700f3c40"},"schema_version":"1.0"},"canonical_sha256":"b7f9075a12cd0bcfaf455137bf1f0c173cd5d6ff545704a20e3e1966bf1d3e68","source":{"kind":"arxiv","id":"1704.04100","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.04100","created_at":"2026-05-18T00:45:53Z"},{"alias_kind":"arxiv_version","alias_value":"1704.04100v2","created_at":"2026-05-18T00:45:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.04100","created_at":"2026-05-18T00:45:53Z"},{"alias_kind":"pith_short_12","alias_value":"W74QOWQSZUF4","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"W74QOWQSZUF47L2F","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"W74QOWQS","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:W74QOWQSZUF47L2FKE336HYMC4","target":"record","payload":{"canonical_record":{"source":{"id":"1704.04100","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-13T12:54:30Z","cross_cats_sorted":[],"title_canon_sha256":"8a7249d98817b325aadd04af19276f0fd99a49e8ac6788acd9a9be7d3a2e6e14","abstract_canon_sha256":"80d11eb34a10425a521641d4656753f2a3e49252b10e84a53d2cc90c700f3c40"},"schema_version":"1.0"},"canonical_sha256":"b7f9075a12cd0bcfaf455137bf1f0c173cd5d6ff545704a20e3e1966bf1d3e68","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:53.788729Z","signature_b64":"ICXgrmlviq0jI/VdD3DpTPMNts+dD0dDvXlQidM8Nt5vl8jN2Tq5CJOz2mY5WdG4GVbX/+9jERWQLN9HxBYfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7f9075a12cd0bcfaf455137bf1f0c173cd5d6ff545704a20e3e1966bf1d3e68","last_reissued_at":"2026-05-18T00:45:53.788125Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:53.788125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.04100","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":"2026-05-18T00:45:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"chSZoU2c1NIYETeRA0EbkAYdqA/L9plpPQkKfCBrDvkPEU10QaxxWRh3XpOvjRt/fPo4ABEs1NC1L6AhorbZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T10:36:44.832691Z"},"content_sha256":"25aec633bdf1ffacd18be8e16318a342dcdffeb4b13fe6c5d9b6643a8a994715","schema_version":"1.0","event_id":"sha256:25aec633bdf1ffacd18be8e16318a342dcdffeb4b13fe6c5d9b6643a8a994715"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:W74QOWQSZUF47L2FKE336HYMC4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-lingual and cross-domain discourse segmentation of entire documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anders S{\\o}gaard, Chlo\\'e Braud, Oph\\'elie Lacroix","submitted_at":"2017-04-13T12:54:30Z","abstract_excerpt":"Discourse segmentation is a crucial step in building end-to-end discourse parsers. However, discourse segmenters only exist for a few languages and domains. Typically they only detect intra-sentential segment boundaries, assuming gold standard sentence and token segmentation, and relying on high-quality syntactic parses and rich heuristics that are not generally available across languages and domains. In this paper, we propose statistical discourse segmenters for five languages and three domains that do not rely on gold pre-annotations. We also consider the problem of learning discourse segmen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.04100","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":""},"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":"2026-05-18T00:45:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l6LreMXeheFDJJzchDvLfMHKNMJDa9Zx7RTHn/TT+QjGFV8NVoz1cG3xCWnrAi/XlG3/6or+mEc/Ij7y0TI/DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T10:36:44.833062Z"},"content_sha256":"3c44e93095a2200ffca907a384626235e00ea3b555448d6956b9669103ef5a57","schema_version":"1.0","event_id":"sha256:3c44e93095a2200ffca907a384626235e00ea3b555448d6956b9669103ef5a57"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W74QOWQSZUF47L2FKE336HYMC4/bundle.json","state_url":"https://pith.science/pith/W74QOWQSZUF47L2FKE336HYMC4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W74QOWQSZUF47L2FKE336HYMC4/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":"2026-06-04T10:36:44Z","links":{"resolver":"https://pith.science/pith/W74QOWQSZUF47L2FKE336HYMC4","bundle":"https://pith.science/pith/W74QOWQSZUF47L2FKE336HYMC4/bundle.json","state":"https://pith.science/pith/W74QOWQSZUF47L2FKE336HYMC4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W74QOWQSZUF47L2FKE336HYMC4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:W74QOWQSZUF47L2FKE336HYMC4","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":"80d11eb34a10425a521641d4656753f2a3e49252b10e84a53d2cc90c700f3c40","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-13T12:54:30Z","title_canon_sha256":"8a7249d98817b325aadd04af19276f0fd99a49e8ac6788acd9a9be7d3a2e6e14"},"schema_version":"1.0","source":{"id":"1704.04100","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.04100","created_at":"2026-05-18T00:45:53Z"},{"alias_kind":"arxiv_version","alias_value":"1704.04100v2","created_at":"2026-05-18T00:45:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.04100","created_at":"2026-05-18T00:45:53Z"},{"alias_kind":"pith_short_12","alias_value":"W74QOWQSZUF4","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"W74QOWQSZUF47L2F","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"W74QOWQS","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:3c44e93095a2200ffca907a384626235e00ea3b555448d6956b9669103ef5a57","target":"graph","created_at":"2026-05-18T00:45:53Z","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":"Discourse segmentation is a crucial step in building end-to-end discourse parsers. However, discourse segmenters only exist for a few languages and domains. Typically they only detect intra-sentential segment boundaries, assuming gold standard sentence and token segmentation, and relying on high-quality syntactic parses and rich heuristics that are not generally available across languages and domains. In this paper, we propose statistical discourse segmenters for five languages and three domains that do not rely on gold pre-annotations. We also consider the problem of learning discourse segmen","authors_text":"Anders S{\\o}gaard, Chlo\\'e Braud, Oph\\'elie Lacroix","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-13T12:54:30Z","title":"Cross-lingual and cross-domain discourse segmentation of entire documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.04100","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":"sha256:25aec633bdf1ffacd18be8e16318a342dcdffeb4b13fe6c5d9b6643a8a994715","target":"record","created_at":"2026-05-18T00:45:53Z","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":"80d11eb34a10425a521641d4656753f2a3e49252b10e84a53d2cc90c700f3c40","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-13T12:54:30Z","title_canon_sha256":"8a7249d98817b325aadd04af19276f0fd99a49e8ac6788acd9a9be7d3a2e6e14"},"schema_version":"1.0","source":{"id":"1704.04100","kind":"arxiv","version":2}},"canonical_sha256":"b7f9075a12cd0bcfaf455137bf1f0c173cd5d6ff545704a20e3e1966bf1d3e68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7f9075a12cd0bcfaf455137bf1f0c173cd5d6ff545704a20e3e1966bf1d3e68","first_computed_at":"2026-05-18T00:45:53.788125Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:45:53.788125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ICXgrmlviq0jI/VdD3DpTPMNts+dD0dDvXlQidM8Nt5vl8jN2Tq5CJOz2mY5WdG4GVbX/+9jERWQLN9HxBYfAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:45:53.788729Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.04100","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25aec633bdf1ffacd18be8e16318a342dcdffeb4b13fe6c5d9b6643a8a994715","sha256:3c44e93095a2200ffca907a384626235e00ea3b555448d6956b9669103ef5a57"],"state_sha256":"e3c7e867b0fa8fb67299378d07abd214c0bec031a8b556ac3cf1dd05190b55a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A85wKswUjKUtIgqryaT4PNNOoprbFjuRqqJ3r8aRJZ9erQkH0r3UHlwDc/udu4aTxhNb7PO7AcWGSIXi1x/UAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T10:36:44.835048Z","bundle_sha256":"06e7b86c30e63f288b5fa10095a748760c1e97066d2bb97f4c5b2884b0f21f99"}}