{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:53KEEWJN6OMDOOGFKQEK7JOUOT","short_pith_number":"pith:53KEEWJN","canonical_record":{"source":{"id":"2104.09576","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-19T19:14:32Z","cross_cats_sorted":[],"title_canon_sha256":"2ab7f687dc3cb13133b97fd088496ef0c53fe1b6f4ded25845d65d40ccbdc2cb","abstract_canon_sha256":"de48415c8bb289f8a754b62e37b5d0b786bbb5008586aab54167782d6c6f8aa5"},"schema_version":"1.0"},"canonical_sha256":"eed442592df3983738c55408afa5d474c48c9209e35619c4b4db93038ce3106d","source":{"kind":"arxiv","id":"2104.09576","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.09576","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"arxiv_version","alias_value":"2104.09576v2","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09576","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"pith_short_12","alias_value":"53KEEWJN6OMD","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"pith_short_16","alias_value":"53KEEWJN6OMDOOGF","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"pith_short_8","alias_value":"53KEEWJN","created_at":"2026-07-05T02:34:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:53KEEWJN6OMDOOGFKQEK7JOUOT","target":"record","payload":{"canonical_record":{"source":{"id":"2104.09576","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-19T19:14:32Z","cross_cats_sorted":[],"title_canon_sha256":"2ab7f687dc3cb13133b97fd088496ef0c53fe1b6f4ded25845d65d40ccbdc2cb","abstract_canon_sha256":"de48415c8bb289f8a754b62e37b5d0b786bbb5008586aab54167782d6c6f8aa5"},"schema_version":"1.0"},"canonical_sha256":"eed442592df3983738c55408afa5d474c48c9209e35619c4b4db93038ce3106d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:34:21.761468Z","signature_b64":"mf3wkgjjBrbm4q8gb0C9cqNKL2le6+CKrZwwrwsw890stqXs+VU+0qVYZUTisVZIUPe+QFOPwmQl4v7tm265Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eed442592df3983738c55408afa5d474c48c9209e35619c4b4db93038ce3106d","last_reissued_at":"2026-07-05T02:34:21.760982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:34:21.760982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.09576","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":"2026-07-05T02:34:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rtJuHqFisbKiGcxfCuakaUsh9ZVyUC53l1Q/ynfXrUaRiZ8wTz8MIMdbGRjFHb2nuwwxqiMgoO+p10Kl7ytFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:07:34.294449Z"},"content_sha256":"fed636651df3b873aa019df7160902797b38389a0768d82e6a6c7d8eb01d640f","schema_version":"1.0","event_id":"sha256:fed636651df3b873aa019df7160902797b38389a0768d82e6a6c7d8eb01d640f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:53KEEWJN6OMDOOGFKQEK7JOUOT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LaTeX-Numeric: Language-agnostic Text attribute eXtraction for E-commerce Numeric Attributes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ioana Oprea, Kartik Mehta, Nikhil Rasiwasia","submitted_at":"2021-04-19T19:14:32Z","abstract_excerpt":"In this paper, we present LaTeX-Numeric - a high-precision fully-automated scalable framework for extracting E-commerce numeric attributes from product text like product description. Most of the past work on attribute extraction is not scalable as they rely on manually curated training data, either with or without the use of active learning. We rely on distant supervision for training data generation, removing dependency on manual labels. One issue with distant supervision is that it leads to incomplete training annotation due to missing attribute values while matching. We propose a multi-task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09576","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.09576/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":"2026-07-05T02:34:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sf9wIM9HAqNV3LxLk+5H2Tr3YIUIcCJlI4OOCGmo7XCOcfHpuGrk8GXcmsN5NJM0tleOPJTYvUMLB9VQZeJ/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:07:34.294830Z"},"content_sha256":"b3ee48cd324691a29accc6f4e8b8f1ba74b7b0fdc17c5b992055f965c133a440","schema_version":"1.0","event_id":"sha256:b3ee48cd324691a29accc6f4e8b8f1ba74b7b0fdc17c5b992055f965c133a440"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/53KEEWJN6OMDOOGFKQEK7JOUOT/bundle.json","state_url":"https://pith.science/pith/53KEEWJN6OMDOOGFKQEK7JOUOT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/53KEEWJN6OMDOOGFKQEK7JOUOT/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":"2026-07-07T08:07:34Z","links":{"resolver":"https://pith.science/pith/53KEEWJN6OMDOOGFKQEK7JOUOT","bundle":"https://pith.science/pith/53KEEWJN6OMDOOGFKQEK7JOUOT/bundle.json","state":"https://pith.science/pith/53KEEWJN6OMDOOGFKQEK7JOUOT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/53KEEWJN6OMDOOGFKQEK7JOUOT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:53KEEWJN6OMDOOGFKQEK7JOUOT","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":"de48415c8bb289f8a754b62e37b5d0b786bbb5008586aab54167782d6c6f8aa5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-19T19:14:32Z","title_canon_sha256":"2ab7f687dc3cb13133b97fd088496ef0c53fe1b6f4ded25845d65d40ccbdc2cb"},"schema_version":"1.0","source":{"id":"2104.09576","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.09576","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"arxiv_version","alias_value":"2104.09576v2","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09576","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"pith_short_12","alias_value":"53KEEWJN6OMD","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"pith_short_16","alias_value":"53KEEWJN6OMDOOGF","created_at":"2026-07-05T02:34:21Z"},{"alias_kind":"pith_short_8","alias_value":"53KEEWJN","created_at":"2026-07-05T02:34:21Z"}],"graph_snapshots":[{"event_id":"sha256:b3ee48cd324691a29accc6f4e8b8f1ba74b7b0fdc17c5b992055f965c133a440","target":"graph","created_at":"2026-07-05T02:34:21Z","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/2104.09576/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present LaTeX-Numeric - a high-precision fully-automated scalable framework for extracting E-commerce numeric attributes from product text like product description. Most of the past work on attribute extraction is not scalable as they rely on manually curated training data, either with or without the use of active learning. We rely on distant supervision for training data generation, removing dependency on manual labels. One issue with distant supervision is that it leads to incomplete training annotation due to missing attribute values while matching. We propose a multi-task","authors_text":"Ioana Oprea, Kartik Mehta, Nikhil Rasiwasia","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-19T19:14:32Z","title":"LaTeX-Numeric: Language-agnostic Text attribute eXtraction for E-commerce Numeric Attributes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09576","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:fed636651df3b873aa019df7160902797b38389a0768d82e6a6c7d8eb01d640f","target":"record","created_at":"2026-07-05T02:34:21Z","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":"de48415c8bb289f8a754b62e37b5d0b786bbb5008586aab54167782d6c6f8aa5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-19T19:14:32Z","title_canon_sha256":"2ab7f687dc3cb13133b97fd088496ef0c53fe1b6f4ded25845d65d40ccbdc2cb"},"schema_version":"1.0","source":{"id":"2104.09576","kind":"arxiv","version":2}},"canonical_sha256":"eed442592df3983738c55408afa5d474c48c9209e35619c4b4db93038ce3106d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eed442592df3983738c55408afa5d474c48c9209e35619c4b4db93038ce3106d","first_computed_at":"2026-07-05T02:34:21.760982Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:34:21.760982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mf3wkgjjBrbm4q8gb0C9cqNKL2le6+CKrZwwrwsw890stqXs+VU+0qVYZUTisVZIUPe+QFOPwmQl4v7tm265Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:34:21.761468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.09576","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fed636651df3b873aa019df7160902797b38389a0768d82e6a6c7d8eb01d640f","sha256:b3ee48cd324691a29accc6f4e8b8f1ba74b7b0fdc17c5b992055f965c133a440"],"state_sha256":"cdd9e53d5ea5b2d26bcad6c7cf443c081dd36ba804f7cc2c57c4ad3838d6cdb3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JEDaTO4XV0kzedOCtlvkySCLLXLknv4dND0e9rDSahPCZ02CF9a2CVf1/fanN9rGbueX3w7fAG3lpUzozl3dDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:07:34.296754Z","bundle_sha256":"1817b8310561819cb5e9f281477684fab5534f9235c1529a90bebc90b2718d3a"}}