{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:G4L5J6TUKIQAMKPGG4O74LXWDW","short_pith_number":"pith:G4L5J6TU","canonical_record":{"source":{"id":"1909.10056","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-22T18:01:36Z","cross_cats_sorted":[],"title_canon_sha256":"9f54bb7239408ecca6171412834f47da099e9811271008bad58c9461aba2ecb8","abstract_canon_sha256":"98b924b9159593824c02f5b5c17b3099739a901ec31cee2ceaa11f2b01735a6c"},"schema_version":"1.0"},"canonical_sha256":"3717d4fa7452200629e6371dfe2ef61db48559d4dc3c205af4b398ed508fe6a3","source":{"kind":"arxiv","id":"1909.10056","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.10056","created_at":"2026-07-05T00:06:17Z"},{"alias_kind":"arxiv_version","alias_value":"1909.10056v1","created_at":"2026-07-05T00:06:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.10056","created_at":"2026-07-05T00:06:17Z"},{"alias_kind":"pith_short_12","alias_value":"G4L5J6TUKIQA","created_at":"2026-07-05T00:06:17Z"},{"alias_kind":"pith_short_16","alias_value":"G4L5J6TUKIQAMKPG","created_at":"2026-07-05T00:06:17Z"},{"alias_kind":"pith_short_8","alias_value":"G4L5J6TU","created_at":"2026-07-05T00:06:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:G4L5J6TUKIQAMKPGG4O74LXWDW","target":"record","payload":{"canonical_record":{"source":{"id":"1909.10056","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-22T18:01:36Z","cross_cats_sorted":[],"title_canon_sha256":"9f54bb7239408ecca6171412834f47da099e9811271008bad58c9461aba2ecb8","abstract_canon_sha256":"98b924b9159593824c02f5b5c17b3099739a901ec31cee2ceaa11f2b01735a6c"},"schema_version":"1.0"},"canonical_sha256":"3717d4fa7452200629e6371dfe2ef61db48559d4dc3c205af4b398ed508fe6a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:06:17.158581Z","signature_b64":"U801NzuaXNd4fjy1PeTdJ463dwE3JeEgt79YFaZNDDZv+mPLLbexrlr77MKe5G4o4A3xw1uylt7pwgGjqSh8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3717d4fa7452200629e6371dfe2ef61db48559d4dc3c205af4b398ed508fe6a3","last_reissued_at":"2026-07-05T00:06:17.158185Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:06:17.158185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.10056","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":"2026-07-05T00:06:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oygNp9dS5m3UHYVjnF64poqNLrqOidaBHhIBl6VouoA0KjBm/UxHQ45h4XGznv5BZpu1iWqvH2DXNjttpGJTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T11:36:16.290584Z"},"content_sha256":"33f25ff8c94c04bf4c2338ad823dfb2a85fff633d1dd4a85286cf754174ebe1d","schema_version":"1.0","event_id":"sha256:33f25ff8c94c04bf4c2338ad823dfb2a85fff633d1dd4a85286cf754174ebe1d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:G4L5J6TUKIQAMKPGG4O74LXWDW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inducing Constituency Trees through Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kyunghyun Cho, Phu Mon Htut, Samuel R. Bowman","submitted_at":"2019-09-22T18:01:36Z","abstract_excerpt":"Latent tree learning(LTL) methods learn to parse sentences using only indirect supervision from a downstream task. Recent advances in latent tree learning have made it possible to recover moderately high quality tree structures by training with language modeling or auto-encoding objectives. In this work, we explore the hypothesis that decoding in machine translation, as a conditional language modeling task, will produce better tree structures since it offers a similar training signal as language modeling, but with more semantic signal. We adapt two existing latent-tree language models--PRPN an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.10056","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.10056/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":"2026-07-05T00:06:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IhD3Td5o2n2F3EShUqTQGT5fNtMpym9qUPnyMCwaDZv3AxdsmqdDhTosBJrIbf1ZCEKOlycY87sB/mnG9UfVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T11:36:16.291776Z"},"content_sha256":"f6dc1eaa4f8996872e81618f10729018a36c8330e4cd89804dd6ab7e2dd6e474","schema_version":"1.0","event_id":"sha256:f6dc1eaa4f8996872e81618f10729018a36c8330e4cd89804dd6ab7e2dd6e474"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G4L5J6TUKIQAMKPGG4O74LXWDW/bundle.json","state_url":"https://pith.science/pith/G4L5J6TUKIQAMKPGG4O74LXWDW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G4L5J6TUKIQAMKPGG4O74LXWDW/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":"2026-08-01T11:36:16Z","links":{"resolver":"https://pith.science/pith/G4L5J6TUKIQAMKPGG4O74LXWDW","bundle":"https://pith.science/pith/G4L5J6TUKIQAMKPGG4O74LXWDW/bundle.json","state":"https://pith.science/pith/G4L5J6TUKIQAMKPGG4O74LXWDW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G4L5J6TUKIQAMKPGG4O74LXWDW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:G4L5J6TUKIQAMKPGG4O74LXWDW","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":"98b924b9159593824c02f5b5c17b3099739a901ec31cee2ceaa11f2b01735a6c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-22T18:01:36Z","title_canon_sha256":"9f54bb7239408ecca6171412834f47da099e9811271008bad58c9461aba2ecb8"},"schema_version":"1.0","source":{"id":"1909.10056","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.10056","created_at":"2026-07-05T00:06:17Z"},{"alias_kind":"arxiv_version","alias_value":"1909.10056v1","created_at":"2026-07-05T00:06:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.10056","created_at":"2026-07-05T00:06:17Z"},{"alias_kind":"pith_short_12","alias_value":"G4L5J6TUKIQA","created_at":"2026-07-05T00:06:17Z"},{"alias_kind":"pith_short_16","alias_value":"G4L5J6TUKIQAMKPG","created_at":"2026-07-05T00:06:17Z"},{"alias_kind":"pith_short_8","alias_value":"G4L5J6TU","created_at":"2026-07-05T00:06:17Z"}],"graph_snapshots":[{"event_id":"sha256:f6dc1eaa4f8996872e81618f10729018a36c8330e4cd89804dd6ab7e2dd6e474","target":"graph","created_at":"2026-07-05T00:06:17Z","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/1909.10056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Latent tree learning(LTL) methods learn to parse sentences using only indirect supervision from a downstream task. Recent advances in latent tree learning have made it possible to recover moderately high quality tree structures by training with language modeling or auto-encoding objectives. In this work, we explore the hypothesis that decoding in machine translation, as a conditional language modeling task, will produce better tree structures since it offers a similar training signal as language modeling, but with more semantic signal. We adapt two existing latent-tree language models--PRPN an","authors_text":"Kyunghyun Cho, Phu Mon Htut, Samuel R. Bowman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-22T18:01:36Z","title":"Inducing Constituency Trees through Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.10056","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":"sha256:33f25ff8c94c04bf4c2338ad823dfb2a85fff633d1dd4a85286cf754174ebe1d","target":"record","created_at":"2026-07-05T00:06:17Z","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":"98b924b9159593824c02f5b5c17b3099739a901ec31cee2ceaa11f2b01735a6c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-22T18:01:36Z","title_canon_sha256":"9f54bb7239408ecca6171412834f47da099e9811271008bad58c9461aba2ecb8"},"schema_version":"1.0","source":{"id":"1909.10056","kind":"arxiv","version":1}},"canonical_sha256":"3717d4fa7452200629e6371dfe2ef61db48559d4dc3c205af4b398ed508fe6a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3717d4fa7452200629e6371dfe2ef61db48559d4dc3c205af4b398ed508fe6a3","first_computed_at":"2026-07-05T00:06:17.158185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:06:17.158185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U801NzuaXNd4fjy1PeTdJ463dwE3JeEgt79YFaZNDDZv+mPLLbexrlr77MKe5G4o4A3xw1uylt7pwgGjqSh8AA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:06:17.158581Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.10056","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33f25ff8c94c04bf4c2338ad823dfb2a85fff633d1dd4a85286cf754174ebe1d","sha256:f6dc1eaa4f8996872e81618f10729018a36c8330e4cd89804dd6ab7e2dd6e474"],"state_sha256":"f20f5629c1baf417238514e70e82a76ce15e14bc7fbefc6bb1df87caabd6c23e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rYNGVKoeGtM7C2cI0GwkgJa5cupF4My7fzVGRBSd3Egn0bOVXOdOtR8sqTF31A1LHLSPhaiY6blStmoMPH9RDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T11:36:16.298406Z","bundle_sha256":"2e94778e8555012c48fec3482c2f338ec9510531fd7f5e29925a6a84076c5cc2"}}