{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:55RXBJ3U3PHQ4F74D2AQKNHKPH","short_pith_number":"pith:55RXBJ3U","canonical_record":{"source":{"id":"1410.6991","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-10-26T06:00:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e129199a775c628f0eee80efda7bfe918f147a4a9c29d7911c98f577818b8757","abstract_canon_sha256":"82b488e571adf0c99ea41f145238c331fe6c68b2833a000932fa2625c06d3054"},"schema_version":"1.0"},"canonical_sha256":"ef6370a774dbcf0e17fc1e810534ea79f9a978cd0710999c205ede61df14e1b9","source":{"kind":"arxiv","id":"1410.6991","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1410.6991","created_at":"2026-05-18T02:38:38Z"},{"alias_kind":"arxiv_version","alias_value":"1410.6991v3","created_at":"2026-05-18T02:38:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.6991","created_at":"2026-05-18T02:38:38Z"},{"alias_kind":"pith_short_12","alias_value":"55RXBJ3U3PHQ","created_at":"2026-05-18T12:28:14Z"},{"alias_kind":"pith_short_16","alias_value":"55RXBJ3U3PHQ4F74","created_at":"2026-05-18T12:28:14Z"},{"alias_kind":"pith_short_8","alias_value":"55RXBJ3U","created_at":"2026-05-18T12:28:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:55RXBJ3U3PHQ4F74D2AQKNHKPH","target":"record","payload":{"canonical_record":{"source":{"id":"1410.6991","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-10-26T06:00:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e129199a775c628f0eee80efda7bfe918f147a4a9c29d7911c98f577818b8757","abstract_canon_sha256":"82b488e571adf0c99ea41f145238c331fe6c68b2833a000932fa2625c06d3054"},"schema_version":"1.0"},"canonical_sha256":"ef6370a774dbcf0e17fc1e810534ea79f9a978cd0710999c205ede61df14e1b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:38:38.526405Z","signature_b64":"BI6I3zeNExYWMTph6EjGtWQwquDeLfof9slp8zA56nQD4HyyJUVLPhxquIsn/RcQIoLqvCrfo68/Yf1lIFf+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef6370a774dbcf0e17fc1e810534ea79f9a978cd0710999c205ede61df14e1b9","last_reissued_at":"2026-05-18T02:38:38.525958Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:38:38.525958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1410.6991","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:38:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N7cSokAY9EGPywfO+iDZlvyEUmKdKM/yIVibLzLk3RqGP7knjvcCJO4u7vZjqvvEJ7MJkgSpVVl+MNTOfG49AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:31:04.648029Z"},"content_sha256":"1fa12fb18fe6d85f07a6573484191e168ba650178e3229d01228b4de440fd28f","schema_version":"1.0","event_id":"sha256:1fa12fb18fe6d85f07a6573484191e168ba650178e3229d01228b4de440fd28f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:55RXBJ3U3PHQ4F74D2AQKNHKPH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A provable SVD-based algorithm for learning topics in dominant admixture corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chiranjib Bhattacharyya, Ravindran Kannan, Trapit Bansal","submitted_at":"2014-10-26T06:00:36Z","abstract_excerpt":"Topic models, such as Latent Dirichlet Allocation (LDA), posit that documents are drawn from admixtures of distributions over words, known as topics. The inference problem of recovering topics from admixtures, is NP-hard. Assuming separability, a strong assumption, [4] gave the first provable algorithm for inference. For LDA model, [6] gave a provable algorithm using tensor-methods. But [4,6] do not learn topic vectors with bounded $l_1$ error (a natural measure for probability vectors). Our aim is to develop a model which makes intuitive and empirically supported assumptions and to design an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1410.6991","kind":"arxiv","version":3},"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":"2026-05-18T02:38:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RIjQLNGuSH5xibmIJs+hntqEipEoDnux1vbKYhS9Fh/jFyHHfWX2y62OsNFxy6Gsz6g4h3SD/QC1DMDm/wsrBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:31:04.648390Z"},"content_sha256":"a9fb5513ae71370d64ba3ad46fa741709a0a1cbfb7386878459ccee37da07476","schema_version":"1.0","event_id":"sha256:a9fb5513ae71370d64ba3ad46fa741709a0a1cbfb7386878459ccee37da07476"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/55RXBJ3U3PHQ4F74D2AQKNHKPH/bundle.json","state_url":"https://pith.science/pith/55RXBJ3U3PHQ4F74D2AQKNHKPH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/55RXBJ3U3PHQ4F74D2AQKNHKPH/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":"2026-06-01T05:31:04Z","links":{"resolver":"https://pith.science/pith/55RXBJ3U3PHQ4F74D2AQKNHKPH","bundle":"https://pith.science/pith/55RXBJ3U3PHQ4F74D2AQKNHKPH/bundle.json","state":"https://pith.science/pith/55RXBJ3U3PHQ4F74D2AQKNHKPH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/55RXBJ3U3PHQ4F74D2AQKNHKPH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:55RXBJ3U3PHQ4F74D2AQKNHKPH","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":"82b488e571adf0c99ea41f145238c331fe6c68b2833a000932fa2625c06d3054","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-10-26T06:00:36Z","title_canon_sha256":"e129199a775c628f0eee80efda7bfe918f147a4a9c29d7911c98f577818b8757"},"schema_version":"1.0","source":{"id":"1410.6991","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1410.6991","created_at":"2026-05-18T02:38:38Z"},{"alias_kind":"arxiv_version","alias_value":"1410.6991v3","created_at":"2026-05-18T02:38:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.6991","created_at":"2026-05-18T02:38:38Z"},{"alias_kind":"pith_short_12","alias_value":"55RXBJ3U3PHQ","created_at":"2026-05-18T12:28:14Z"},{"alias_kind":"pith_short_16","alias_value":"55RXBJ3U3PHQ4F74","created_at":"2026-05-18T12:28:14Z"},{"alias_kind":"pith_short_8","alias_value":"55RXBJ3U","created_at":"2026-05-18T12:28:14Z"}],"graph_snapshots":[{"event_id":"sha256:a9fb5513ae71370d64ba3ad46fa741709a0a1cbfb7386878459ccee37da07476","target":"graph","created_at":"2026-05-18T02:38:38Z","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":"Topic models, such as Latent Dirichlet Allocation (LDA), posit that documents are drawn from admixtures of distributions over words, known as topics. The inference problem of recovering topics from admixtures, is NP-hard. Assuming separability, a strong assumption, [4] gave the first provable algorithm for inference. For LDA model, [6] gave a provable algorithm using tensor-methods. But [4,6] do not learn topic vectors with bounded $l_1$ error (a natural measure for probability vectors). Our aim is to develop a model which makes intuitive and empirically supported assumptions and to design an ","authors_text":"Chiranjib Bhattacharyya, Ravindran Kannan, Trapit Bansal","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-10-26T06:00:36Z","title":"A provable SVD-based algorithm for learning topics in dominant admixture corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1410.6991","kind":"arxiv","version":3},"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":"sha256:1fa12fb18fe6d85f07a6573484191e168ba650178e3229d01228b4de440fd28f","target":"record","created_at":"2026-05-18T02:38:38Z","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":"82b488e571adf0c99ea41f145238c331fe6c68b2833a000932fa2625c06d3054","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-10-26T06:00:36Z","title_canon_sha256":"e129199a775c628f0eee80efda7bfe918f147a4a9c29d7911c98f577818b8757"},"schema_version":"1.0","source":{"id":"1410.6991","kind":"arxiv","version":3}},"canonical_sha256":"ef6370a774dbcf0e17fc1e810534ea79f9a978cd0710999c205ede61df14e1b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef6370a774dbcf0e17fc1e810534ea79f9a978cd0710999c205ede61df14e1b9","first_computed_at":"2026-05-18T02:38:38.525958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:38:38.525958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BI6I3zeNExYWMTph6EjGtWQwquDeLfof9slp8zA56nQD4HyyJUVLPhxquIsn/RcQIoLqvCrfo68/Yf1lIFf+Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:38:38.526405Z","signed_message":"canonical_sha256_bytes"},"source_id":"1410.6991","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1fa12fb18fe6d85f07a6573484191e168ba650178e3229d01228b4de440fd28f","sha256:a9fb5513ae71370d64ba3ad46fa741709a0a1cbfb7386878459ccee37da07476"],"state_sha256":"2a684713fcaf2556da46f60d1d075cf12f81d66629425cff6cc016129a8ecff4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NSxmYi9w/WixGjyn0zIRYMQoB0gRY38QtusqXBaq07th3hI+El5fRJJszylo0zkAOXWsjSj4Sp43olBna/gyDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T05:31:04.650560Z","bundle_sha256":"b32d21bb2e47ab700bd5ae046a9339c4ac5d649703f96608dc703035e93e57aa"}}