{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:GXWKU3ZAJK3OFKI7YQU7BZJYA6","short_pith_number":"pith:GXWKU3ZA","canonical_record":{"source":{"id":"1608.04670","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-15T03:34:13Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"6d5201b3db0e82b8ae6a490d19499c1867ce879893239c0ca2d74037e9653cc2","abstract_canon_sha256":"32979c207c060f385869d931614e8cc8a58fd119d8ff57f05163d8e983548455"},"schema_version":"1.0"},"canonical_sha256":"35ecaa6f204ab6e2a91fc429f0e538079272bf0ae28c348ce9037489a04295a8","source":{"kind":"arxiv","id":"1608.04670","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.04670","created_at":"2026-05-18T01:08:36Z"},{"alias_kind":"arxiv_version","alias_value":"1608.04670v1","created_at":"2026-05-18T01:08:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.04670","created_at":"2026-05-18T01:08:36Z"},{"alias_kind":"pith_short_12","alias_value":"GXWKU3ZAJK3O","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"GXWKU3ZAJK3OFKI7","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"GXWKU3ZA","created_at":"2026-05-18T12:30:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:GXWKU3ZAJK3OFKI7YQU7BZJYA6","target":"record","payload":{"canonical_record":{"source":{"id":"1608.04670","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-15T03:34:13Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"6d5201b3db0e82b8ae6a490d19499c1867ce879893239c0ca2d74037e9653cc2","abstract_canon_sha256":"32979c207c060f385869d931614e8cc8a58fd119d8ff57f05163d8e983548455"},"schema_version":"1.0"},"canonical_sha256":"35ecaa6f204ab6e2a91fc429f0e538079272bf0ae28c348ce9037489a04295a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:08:36.597285Z","signature_b64":"+IimzepxDmLX60AoI52AgrSb0vWuT4B0vCIFbf8AYpde7U0e3dwsz8dEJoOna9G44/Mw6GHixb+BEuWDPUbOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35ecaa6f204ab6e2a91fc429f0e538079272bf0ae28c348ce9037489a04295a8","last_reissued_at":"2026-05-18T01:08:36.596611Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:08:36.596611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1608.04670","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":"2026-05-18T01:08:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hDB9j97635LQNr7nVcU8PBLnyrav9UkAYmRDQAkt3pITacrwTmhBFX4jDLGThuiL1hgox7ZjnXFaArZ8RHfNCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T10:37:53.750400Z"},"content_sha256":"563e98a64ef18cbe6eb2e2f3dca39bf4f1edff0f389f9327b7bf4ef8bb7b493f","schema_version":"1.0","event_id":"sha256:563e98a64ef18cbe6eb2e2f3dca39bf4f1edff0f389f9327b7bf4ef8bb7b493f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:GXWKU3ZAJK3OFKI7YQU7BZJYA6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attribute Extraction from Product Titles in eCommerce","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Ajinkya More","submitted_at":"2016-08-15T03:34:13Z","abstract_excerpt":"This paper presents a named entity extraction system for detecting attributes in product titles of eCommerce retailers like Walmart. The absence of syntactic structure in such short pieces of text makes extracting attribute values a challenging problem. We find that combining sequence labeling algorithms such as Conditional Random Fields and Structured Perceptron with a curated normalization scheme produces an effective system for the task of extracting product attribute values from titles. To keep the discussion concrete, we will illustrate the mechanics of the system from the point of view o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.04670","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":"2026-05-18T01:08:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qL1zFMVsgk3fYGcdvAiy0CZ427OCXR5ydjygpF8ie3dLDlcKRcAlgAIOzzqLqLZHM1bbgZRYEFVHpzDc41KDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T10:37:53.750740Z"},"content_sha256":"2843254ac1cacceb4bee630fe2116e5583c8fc5b652c6f353e1a01123286f10d","schema_version":"1.0","event_id":"sha256:2843254ac1cacceb4bee630fe2116e5583c8fc5b652c6f353e1a01123286f10d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GXWKU3ZAJK3OFKI7YQU7BZJYA6/bundle.json","state_url":"https://pith.science/pith/GXWKU3ZAJK3OFKI7YQU7BZJYA6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GXWKU3ZAJK3OFKI7YQU7BZJYA6/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":"2026-06-24T10:37:53Z","links":{"resolver":"https://pith.science/pith/GXWKU3ZAJK3OFKI7YQU7BZJYA6","bundle":"https://pith.science/pith/GXWKU3ZAJK3OFKI7YQU7BZJYA6/bundle.json","state":"https://pith.science/pith/GXWKU3ZAJK3OFKI7YQU7BZJYA6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GXWKU3ZAJK3OFKI7YQU7BZJYA6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:GXWKU3ZAJK3OFKI7YQU7BZJYA6","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":"32979c207c060f385869d931614e8cc8a58fd119d8ff57f05163d8e983548455","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-15T03:34:13Z","title_canon_sha256":"6d5201b3db0e82b8ae6a490d19499c1867ce879893239c0ca2d74037e9653cc2"},"schema_version":"1.0","source":{"id":"1608.04670","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.04670","created_at":"2026-05-18T01:08:36Z"},{"alias_kind":"arxiv_version","alias_value":"1608.04670v1","created_at":"2026-05-18T01:08:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.04670","created_at":"2026-05-18T01:08:36Z"},{"alias_kind":"pith_short_12","alias_value":"GXWKU3ZAJK3O","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"GXWKU3ZAJK3OFKI7","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"GXWKU3ZA","created_at":"2026-05-18T12:30:19Z"}],"graph_snapshots":[{"event_id":"sha256:2843254ac1cacceb4bee630fe2116e5583c8fc5b652c6f353e1a01123286f10d","target":"graph","created_at":"2026-05-18T01:08:36Z","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 presents a named entity extraction system for detecting attributes in product titles of eCommerce retailers like Walmart. The absence of syntactic structure in such short pieces of text makes extracting attribute values a challenging problem. We find that combining sequence labeling algorithms such as Conditional Random Fields and Structured Perceptron with a curated normalization scheme produces an effective system for the task of extracting product attribute values from titles. To keep the discussion concrete, we will illustrate the mechanics of the system from the point of view o","authors_text":"Ajinkya More","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-15T03:34:13Z","title":"Attribute Extraction from Product Titles in eCommerce"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.04670","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":"sha256:563e98a64ef18cbe6eb2e2f3dca39bf4f1edff0f389f9327b7bf4ef8bb7b493f","target":"record","created_at":"2026-05-18T01:08:36Z","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":"32979c207c060f385869d931614e8cc8a58fd119d8ff57f05163d8e983548455","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-15T03:34:13Z","title_canon_sha256":"6d5201b3db0e82b8ae6a490d19499c1867ce879893239c0ca2d74037e9653cc2"},"schema_version":"1.0","source":{"id":"1608.04670","kind":"arxiv","version":1}},"canonical_sha256":"35ecaa6f204ab6e2a91fc429f0e538079272bf0ae28c348ce9037489a04295a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35ecaa6f204ab6e2a91fc429f0e538079272bf0ae28c348ce9037489a04295a8","first_computed_at":"2026-05-18T01:08:36.596611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:08:36.596611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+IimzepxDmLX60AoI52AgrSb0vWuT4B0vCIFbf8AYpde7U0e3dwsz8dEJoOna9G44/Mw6GHixb+BEuWDPUbOAw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:08:36.597285Z","signed_message":"canonical_sha256_bytes"},"source_id":"1608.04670","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:563e98a64ef18cbe6eb2e2f3dca39bf4f1edff0f389f9327b7bf4ef8bb7b493f","sha256:2843254ac1cacceb4bee630fe2116e5583c8fc5b652c6f353e1a01123286f10d"],"state_sha256":"66eb77a4332450f9ca2b2abc6c12ece7503a234c2ed989726d498f047dbe02cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J0n6ML3u6FCFctUfqhc651CyybsXiP8ShQ7GnvDbhpdddkuL2XR2n02nlXkxHBBbgIDjSXHEoONV2d7af+b9BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-24T10:37:53.752638Z","bundle_sha256":"fa5563077d928797411f305b3f9ad18a56bfac3576b6e8d7c8b93db1f9573b71"}}