{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SF3RHGDBTI3CJSRYFHRA3XQWZC","short_pith_number":"pith:SF3RHGDB","canonical_record":{"source":{"id":"1902.05085","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-13T19:01:51Z","cross_cats_sorted":[],"title_canon_sha256":"b61105f65942c510521a2bfaf40be9589b08c188c011c26c4e5c377b787827a8","abstract_canon_sha256":"1656f914d752c2c60296b2e1b3cd49f7369bfad291525cbf08d3c15313ebeac8"},"schema_version":"1.0"},"canonical_sha256":"91771398619a3624ca3829e20dde16c8ab10a66833696fa11ba73cabd1be421c","source":{"kind":"arxiv","id":"1902.05085","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.05085","created_at":"2026-05-17T23:54:01Z"},{"alias_kind":"arxiv_version","alias_value":"1902.05085v1","created_at":"2026-05-17T23:54:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05085","created_at":"2026-05-17T23:54:01Z"},{"alias_kind":"pith_short_12","alias_value":"SF3RHGDBTI3C","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SF3RHGDBTI3CJSRY","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SF3RHGDB","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SF3RHGDBTI3CJSRYFHRA3XQWZC","target":"record","payload":{"canonical_record":{"source":{"id":"1902.05085","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-13T19:01:51Z","cross_cats_sorted":[],"title_canon_sha256":"b61105f65942c510521a2bfaf40be9589b08c188c011c26c4e5c377b787827a8","abstract_canon_sha256":"1656f914d752c2c60296b2e1b3cd49f7369bfad291525cbf08d3c15313ebeac8"},"schema_version":"1.0"},"canonical_sha256":"91771398619a3624ca3829e20dde16c8ab10a66833696fa11ba73cabd1be421c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:01.956008Z","signature_b64":"IohkOVzuCprCgbiiU/8JqkaKE4exxcGeq438DQ6LZEShxdsL11rpO9wx5rSmwGz35VVX/sxQswwIW+zKyBJCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91771398619a3624ca3829e20dde16c8ab10a66833696fa11ba73cabd1be421c","last_reissued_at":"2026-05-17T23:54:01.955363Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:01.955363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.05085","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":"2026-05-17T23:54:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tbsItpHYwkLOvSBBrypmDqwJiFKhGNqywLep0ldmUUajfHn0Mvvf1LWueNXQFy/UqN2MATfPHFdD/VI5fpz5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:34:21.930343Z"},"content_sha256":"c3ad5d91de215ed52f26beb8e4df9e306314818c0dff7c7385937ed74e28b439","schema_version":"1.0","event_id":"sha256:c3ad5d91de215ed52f26beb8e4df9e306314818c0dff7c7385937ed74e28b439"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SF3RHGDBTI3CJSRYFHRA3XQWZC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Newswire Treebanks for Parsing Conversational Data with Argument Scrambling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dipti Misra Sharma, Irshad Ahmad Bhat, Riyaz Ahmad Bhat","submitted_at":"2019-02-13T19:01:51Z","abstract_excerpt":"We investigate the problem of parsing conversational data of morphologically-rich languages such as Hindi where argument scrambling occurs frequently. We evaluate a state-of-the-art non-linear transition-based parsing system on a new dataset containing 506 dependency trees for sentences from Bollywood (Hindi) movie scripts and Twitter posts of Hindi monolingual speakers. We show that a dependency parser trained on a newswire treebank is strongly biased towards the canonical structures and degrades when applied to conversational data. Inspired by Transformational Generative Grammar, we mitigate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.05085","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":"2026-05-17T23:54:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tE4vs+DG7xjlgI/KEI+fA0OzbfJOq6GMLk+QzPoTTrEVKsuLydZNY0ETC6afRycnFKy1vGf0veDcyLzxYoCJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:34:21.930703Z"},"content_sha256":"b0f82529b2b64082c59bb32154dd9301406307b0078f4ae4a985f98b70366f9e","schema_version":"1.0","event_id":"sha256:b0f82529b2b64082c59bb32154dd9301406307b0078f4ae4a985f98b70366f9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SF3RHGDBTI3CJSRYFHRA3XQWZC/bundle.json","state_url":"https://pith.science/pith/SF3RHGDBTI3CJSRYFHRA3XQWZC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SF3RHGDBTI3CJSRYFHRA3XQWZC/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":"2026-05-31T06:34:21Z","links":{"resolver":"https://pith.science/pith/SF3RHGDBTI3CJSRYFHRA3XQWZC","bundle":"https://pith.science/pith/SF3RHGDBTI3CJSRYFHRA3XQWZC/bundle.json","state":"https://pith.science/pith/SF3RHGDBTI3CJSRYFHRA3XQWZC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SF3RHGDBTI3CJSRYFHRA3XQWZC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SF3RHGDBTI3CJSRYFHRA3XQWZC","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":"1656f914d752c2c60296b2e1b3cd49f7369bfad291525cbf08d3c15313ebeac8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-13T19:01:51Z","title_canon_sha256":"b61105f65942c510521a2bfaf40be9589b08c188c011c26c4e5c377b787827a8"},"schema_version":"1.0","source":{"id":"1902.05085","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.05085","created_at":"2026-05-17T23:54:01Z"},{"alias_kind":"arxiv_version","alias_value":"1902.05085v1","created_at":"2026-05-17T23:54:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05085","created_at":"2026-05-17T23:54:01Z"},{"alias_kind":"pith_short_12","alias_value":"SF3RHGDBTI3C","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SF3RHGDBTI3CJSRY","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SF3RHGDB","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:b0f82529b2b64082c59bb32154dd9301406307b0078f4ae4a985f98b70366f9e","target":"graph","created_at":"2026-05-17T23:54:01Z","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":"We investigate the problem of parsing conversational data of morphologically-rich languages such as Hindi where argument scrambling occurs frequently. We evaluate a state-of-the-art non-linear transition-based parsing system on a new dataset containing 506 dependency trees for sentences from Bollywood (Hindi) movie scripts and Twitter posts of Hindi monolingual speakers. We show that a dependency parser trained on a newswire treebank is strongly biased towards the canonical structures and degrades when applied to conversational data. Inspired by Transformational Generative Grammar, we mitigate","authors_text":"Dipti Misra Sharma, Irshad Ahmad Bhat, Riyaz Ahmad Bhat","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-13T19:01:51Z","title":"Leveraging Newswire Treebanks for Parsing Conversational Data with Argument Scrambling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.05085","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:c3ad5d91de215ed52f26beb8e4df9e306314818c0dff7c7385937ed74e28b439","target":"record","created_at":"2026-05-17T23:54:01Z","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":"1656f914d752c2c60296b2e1b3cd49f7369bfad291525cbf08d3c15313ebeac8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-13T19:01:51Z","title_canon_sha256":"b61105f65942c510521a2bfaf40be9589b08c188c011c26c4e5c377b787827a8"},"schema_version":"1.0","source":{"id":"1902.05085","kind":"arxiv","version":1}},"canonical_sha256":"91771398619a3624ca3829e20dde16c8ab10a66833696fa11ba73cabd1be421c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91771398619a3624ca3829e20dde16c8ab10a66833696fa11ba73cabd1be421c","first_computed_at":"2026-05-17T23:54:01.955363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:01.955363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IohkOVzuCprCgbiiU/8JqkaKE4exxcGeq438DQ6LZEShxdsL11rpO9wx5rSmwGz35VVX/sxQswwIW+zKyBJCBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:01.956008Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.05085","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3ad5d91de215ed52f26beb8e4df9e306314818c0dff7c7385937ed74e28b439","sha256:b0f82529b2b64082c59bb32154dd9301406307b0078f4ae4a985f98b70366f9e"],"state_sha256":"e3281d929b4eda685d02e46ff557a0e2e07bf1c3e55f1c63962f1dccfe24c808"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hYAPrsySP7Uo+rh34ZRVYaHY7tDmR2K0hVRZpWBXdbxJ6+rkvTuFOuCbWhLwTIVqMwNe5aUCBzKbUAMTRKPFCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T06:34:21.932646Z","bundle_sha256":"c7781eb69668e4d5e4c5a9364649658076de48b926abee65b36922faa457fdd6"}}