{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:PBDU7TBUJA4JJ3UCCDNHMIX3L6","short_pith_number":"pith:PBDU7TBU","canonical_record":{"source":{"id":"1206.3137","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-06-14T15:21:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b63bb3e44909566f65b359cf5d5498f37abf385666af70f711c2c38a830f5534","abstract_canon_sha256":"cd85bfa477ca7df699abaddd5936017133847b75c13cca619119a569d23006ef"},"schema_version":"1.0"},"canonical_sha256":"78474fcc34483894ee8210da7622fb5f89bc30525b8b626996e5e99923f81231","source":{"kind":"arxiv","id":"1206.3137","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.3137","created_at":"2026-05-18T03:53:32Z"},{"alias_kind":"arxiv_version","alias_value":"1206.3137v1","created_at":"2026-05-18T03:53:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.3137","created_at":"2026-05-18T03:53:32Z"},{"alias_kind":"pith_short_12","alias_value":"PBDU7TBUJA4J","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_16","alias_value":"PBDU7TBUJA4JJ3UC","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_8","alias_value":"PBDU7TBU","created_at":"2026-05-18T12:27:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:PBDU7TBUJA4JJ3UCCDNHMIX3L6","target":"record","payload":{"canonical_record":{"source":{"id":"1206.3137","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-06-14T15:21:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b63bb3e44909566f65b359cf5d5498f37abf385666af70f711c2c38a830f5534","abstract_canon_sha256":"cd85bfa477ca7df699abaddd5936017133847b75c13cca619119a569d23006ef"},"schema_version":"1.0"},"canonical_sha256":"78474fcc34483894ee8210da7622fb5f89bc30525b8b626996e5e99923f81231","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:53:32.581493Z","signature_b64":"UCoHeirgRtC27r5ybtqQB3rqyHSjgmlJY6nzZcg68Ag3mgm7+2VsnQ+X/SWxhnr6YCFw+fLVR2t7+GFFTTUSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78474fcc34483894ee8210da7622fb5f89bc30525b8b626996e5e99923f81231","last_reissued_at":"2026-05-18T03:53:32.580708Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:53:32.580708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1206.3137","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":"2026-05-18T03:53:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QFvT3fYnUkt9Vm6pgY9F3R7ohluDq+KFvKA2cl0Sg+ZeM0Ofq3kdaxJADSYtB6VB3zHkrLMlw/jNQH8DrXXCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T05:11:36.888380Z"},"content_sha256":"ea2f2570f37a9e2ff0bb73f750437171f12a4b56364e00ab6a366f21f2b00d06","schema_version":"1.0","event_id":"sha256:ea2f2570f37a9e2ff0bb73f750437171f12a4b56364e00ab6a366f21f2b00d06"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:PBDU7TBUJA4JJ3UCCDNHMIX3L6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Identifiability and Unmixing of Latent Parse Trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Daniel Hsu, Percy Liang, Sham M. Kakade","submitted_at":"2012-06-14T15:21:24Z","abstract_excerpt":"This paper explores unsupervised learning of parsing models along two directions. First, which models are identifiable from infinite data? We use a general technique for numerically checking identifiability based on the rank of a Jacobian matrix, and apply it to several standard constituency and dependency parsing models. Second, for identifiable models, how do we estimate the parameters efficiently? EM suffers from local optima, while recent work using spectral methods cannot be directly applied since the topology of the parse tree varies across sentences. We develop a strategy, unmixing, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.3137","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":"2026-05-18T03:53:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"obdY4cviEXDSj8QVC0TjrhmcUwA8XDLM8IEHqV8BvI2WOoezURKOaf9O3Ka4vLdh/GeUjCEWurUgjF4KpMAJDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T05:11:36.889069Z"},"content_sha256":"284b6a1f03304011b8d3970707f349d7619c710dc8658d690793d23f6a7e9fd5","schema_version":"1.0","event_id":"sha256:284b6a1f03304011b8d3970707f349d7619c710dc8658d690793d23f6a7e9fd5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PBDU7TBUJA4JJ3UCCDNHMIX3L6/bundle.json","state_url":"https://pith.science/pith/PBDU7TBUJA4JJ3UCCDNHMIX3L6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PBDU7TBUJA4JJ3UCCDNHMIX3L6/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":"2026-05-26T05:11:36Z","links":{"resolver":"https://pith.science/pith/PBDU7TBUJA4JJ3UCCDNHMIX3L6","bundle":"https://pith.science/pith/PBDU7TBUJA4JJ3UCCDNHMIX3L6/bundle.json","state":"https://pith.science/pith/PBDU7TBUJA4JJ3UCCDNHMIX3L6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PBDU7TBUJA4JJ3UCCDNHMIX3L6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:PBDU7TBUJA4JJ3UCCDNHMIX3L6","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":"cd85bfa477ca7df699abaddd5936017133847b75c13cca619119a569d23006ef","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-06-14T15:21:24Z","title_canon_sha256":"b63bb3e44909566f65b359cf5d5498f37abf385666af70f711c2c38a830f5534"},"schema_version":"1.0","source":{"id":"1206.3137","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.3137","created_at":"2026-05-18T03:53:32Z"},{"alias_kind":"arxiv_version","alias_value":"1206.3137v1","created_at":"2026-05-18T03:53:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.3137","created_at":"2026-05-18T03:53:32Z"},{"alias_kind":"pith_short_12","alias_value":"PBDU7TBUJA4J","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_16","alias_value":"PBDU7TBUJA4JJ3UC","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_8","alias_value":"PBDU7TBU","created_at":"2026-05-18T12:27:18Z"}],"graph_snapshots":[{"event_id":"sha256:284b6a1f03304011b8d3970707f349d7619c710dc8658d690793d23f6a7e9fd5","target":"graph","created_at":"2026-05-18T03:53:32Z","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":"This paper explores unsupervised learning of parsing models along two directions. First, which models are identifiable from infinite data? We use a general technique for numerically checking identifiability based on the rank of a Jacobian matrix, and apply it to several standard constituency and dependency parsing models. Second, for identifiable models, how do we estimate the parameters efficiently? EM suffers from local optima, while recent work using spectral methods cannot be directly applied since the topology of the parse tree varies across sentences. We develop a strategy, unmixing, whi","authors_text":"Daniel Hsu, Percy Liang, Sham M. Kakade","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-06-14T15:21:24Z","title":"Identifiability and Unmixing of Latent Parse Trees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.3137","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:ea2f2570f37a9e2ff0bb73f750437171f12a4b56364e00ab6a366f21f2b00d06","target":"record","created_at":"2026-05-18T03:53:32Z","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":"cd85bfa477ca7df699abaddd5936017133847b75c13cca619119a569d23006ef","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-06-14T15:21:24Z","title_canon_sha256":"b63bb3e44909566f65b359cf5d5498f37abf385666af70f711c2c38a830f5534"},"schema_version":"1.0","source":{"id":"1206.3137","kind":"arxiv","version":1}},"canonical_sha256":"78474fcc34483894ee8210da7622fb5f89bc30525b8b626996e5e99923f81231","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78474fcc34483894ee8210da7622fb5f89bc30525b8b626996e5e99923f81231","first_computed_at":"2026-05-18T03:53:32.580708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:53:32.580708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UCoHeirgRtC27r5ybtqQB3rqyHSjgmlJY6nzZcg68Ag3mgm7+2VsnQ+X/SWxhnr6YCFw+fLVR2t7+GFFTTUSBg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:53:32.581493Z","signed_message":"canonical_sha256_bytes"},"source_id":"1206.3137","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea2f2570f37a9e2ff0bb73f750437171f12a4b56364e00ab6a366f21f2b00d06","sha256:284b6a1f03304011b8d3970707f349d7619c710dc8658d690793d23f6a7e9fd5"],"state_sha256":"0880a20dce24224bb0d5d0275eeceaf535d7a7d5f887360ee7384bb5f43e7080"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZoTcEGDgt7chw3BzF7OSCHIXT14/CSjwq4STvxL4u2c4uoVtJqRFQ20yvHtqHqkRvGz2r5bfkWEaF3Tbp3pGCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T05:11:36.892380Z","bundle_sha256":"e313db331b44fc21c3c2049fe541c62164bf0a50ee476b859da0c628885201b7"}}