{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:PLMSJMVA7YLLE6Z74EID5VWGVL","short_pith_number":"pith:PLMSJMVA","canonical_record":{"source":{"id":"2008.08180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-08-18T23:01:16Z","cross_cats_sorted":[],"title_canon_sha256":"36d0ded0c7652818521a124d577439054df5049faed1c065749b54d46cff3314","abstract_canon_sha256":"56c0683f274ee25660aca9c3b6986fb1de7281e7bd3ccf12b5a4fe0c04f3af67"},"schema_version":"1.0"},"canonical_sha256":"7ad924b2a0fe16b27b3fe1103ed6c6aafff74a1dbdd6d8c663d16f855a5e2cde","source":{"kind":"arxiv","id":"2008.08180","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.08180","created_at":"2026-07-05T01:28:23Z"},{"alias_kind":"arxiv_version","alias_value":"2008.08180v1","created_at":"2026-07-05T01:28:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.08180","created_at":"2026-07-05T01:28:23Z"},{"alias_kind":"pith_short_12","alias_value":"PLMSJMVA7YLL","created_at":"2026-07-05T01:28:23Z"},{"alias_kind":"pith_short_16","alias_value":"PLMSJMVA7YLLE6Z7","created_at":"2026-07-05T01:28:23Z"},{"alias_kind":"pith_short_8","alias_value":"PLMSJMVA","created_at":"2026-07-05T01:28:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:PLMSJMVA7YLLE6Z74EID5VWGVL","target":"record","payload":{"canonical_record":{"source":{"id":"2008.08180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-08-18T23:01:16Z","cross_cats_sorted":[],"title_canon_sha256":"36d0ded0c7652818521a124d577439054df5049faed1c065749b54d46cff3314","abstract_canon_sha256":"56c0683f274ee25660aca9c3b6986fb1de7281e7bd3ccf12b5a4fe0c04f3af67"},"schema_version":"1.0"},"canonical_sha256":"7ad924b2a0fe16b27b3fe1103ed6c6aafff74a1dbdd6d8c663d16f855a5e2cde","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:28:23.360183Z","signature_b64":"Fr2sxVOQuG0Wf0wggNe9QVYc+va/E0UKtPBu5Q8G4dM2CGsZauI23b+lpUBPf3NRh1HYUzOYnCYD2Uo5u2gfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ad924b2a0fe16b27b3fe1103ed6c6aafff74a1dbdd6d8c663d16f855a5e2cde","last_reissued_at":"2026-07-05T01:28:23.359763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:28:23.359763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.08180","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":"2026-07-05T01:28:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9moK/bhf2TRGARsvSuP6XQ+SewhUQYWJdOVYVA2ztyDbIihIo5lAMUWXpyJ1c8+ko9i8OjiFTyseu+j+WijkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T16:20:44.478055Z"},"content_sha256":"c947db8e5926ef3ed288245082875049d56e969d8a226a66780b5b6c097462b1","schema_version":"1.0","event_id":"sha256:c947db8e5926ef3ed288245082875049d56e969d8a226a66780b5b6c097462b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:PLMSJMVA7YLLE6Z74EID5VWGVL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semantic Product Search for Matching Structured Product Catalogs in E-Commerce","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bhaskar Mitra, Eugene Agichtein, Faizan Javed, Jason Ingyu Choi, Surya Kallumadi","submitted_at":"2020-08-18T23:01:16Z","abstract_excerpt":"Retrieving all semantically relevant products from the product catalog is an important problem in E-commerce. Compared to web documents, product catalogs are more structured and sparse due to multi-instance fields that encode heterogeneous aspects of products (e.g. brand name and product dimensions). In this paper, we propose a new semantic product search algorithm that learns to represent and aggregate multi-instance fields into a document representation using state of the art transformers as encoders. Our experiments investigate two aspects of the proposed approach: (1) effectiveness of fiel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.08180","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/2008.08180/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":"2026-07-05T01:28:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3lfEYyjxp/ksen+nMRm2HEHDcyxmwP9rDDmRxUzlh3sQN9/mkEiTvYX+r4h+RuX/Q/NJiCbAhVl/iNLhFXeEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T16:20:44.478445Z"},"content_sha256":"d2cb74f66568832bbe7842f24e499550b81cab92e7145baf3e55184364a182fd","schema_version":"1.0","event_id":"sha256:d2cb74f66568832bbe7842f24e499550b81cab92e7145baf3e55184364a182fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PLMSJMVA7YLLE6Z74EID5VWGVL/bundle.json","state_url":"https://pith.science/pith/PLMSJMVA7YLLE6Z74EID5VWGVL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PLMSJMVA7YLLE6Z74EID5VWGVL/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":"2026-07-08T16:20:44Z","links":{"resolver":"https://pith.science/pith/PLMSJMVA7YLLE6Z74EID5VWGVL","bundle":"https://pith.science/pith/PLMSJMVA7YLLE6Z74EID5VWGVL/bundle.json","state":"https://pith.science/pith/PLMSJMVA7YLLE6Z74EID5VWGVL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PLMSJMVA7YLLE6Z74EID5VWGVL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PLMSJMVA7YLLE6Z74EID5VWGVL","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":"56c0683f274ee25660aca9c3b6986fb1de7281e7bd3ccf12b5a4fe0c04f3af67","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-08-18T23:01:16Z","title_canon_sha256":"36d0ded0c7652818521a124d577439054df5049faed1c065749b54d46cff3314"},"schema_version":"1.0","source":{"id":"2008.08180","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.08180","created_at":"2026-07-05T01:28:23Z"},{"alias_kind":"arxiv_version","alias_value":"2008.08180v1","created_at":"2026-07-05T01:28:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.08180","created_at":"2026-07-05T01:28:23Z"},{"alias_kind":"pith_short_12","alias_value":"PLMSJMVA7YLL","created_at":"2026-07-05T01:28:23Z"},{"alias_kind":"pith_short_16","alias_value":"PLMSJMVA7YLLE6Z7","created_at":"2026-07-05T01:28:23Z"},{"alias_kind":"pith_short_8","alias_value":"PLMSJMVA","created_at":"2026-07-05T01:28:23Z"}],"graph_snapshots":[{"event_id":"sha256:d2cb74f66568832bbe7842f24e499550b81cab92e7145baf3e55184364a182fd","target":"graph","created_at":"2026-07-05T01:28:23Z","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/2008.08180/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieving all semantically relevant products from the product catalog is an important problem in E-commerce. Compared to web documents, product catalogs are more structured and sparse due to multi-instance fields that encode heterogeneous aspects of products (e.g. brand name and product dimensions). In this paper, we propose a new semantic product search algorithm that learns to represent and aggregate multi-instance fields into a document representation using state of the art transformers as encoders. Our experiments investigate two aspects of the proposed approach: (1) effectiveness of fiel","authors_text":"Bhaskar Mitra, Eugene Agichtein, Faizan Javed, Jason Ingyu Choi, Surya Kallumadi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-08-18T23:01:16Z","title":"Semantic Product Search for Matching Structured Product Catalogs in E-Commerce"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.08180","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:c947db8e5926ef3ed288245082875049d56e969d8a226a66780b5b6c097462b1","target":"record","created_at":"2026-07-05T01:28:23Z","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":"56c0683f274ee25660aca9c3b6986fb1de7281e7bd3ccf12b5a4fe0c04f3af67","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-08-18T23:01:16Z","title_canon_sha256":"36d0ded0c7652818521a124d577439054df5049faed1c065749b54d46cff3314"},"schema_version":"1.0","source":{"id":"2008.08180","kind":"arxiv","version":1}},"canonical_sha256":"7ad924b2a0fe16b27b3fe1103ed6c6aafff74a1dbdd6d8c663d16f855a5e2cde","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ad924b2a0fe16b27b3fe1103ed6c6aafff74a1dbdd6d8c663d16f855a5e2cde","first_computed_at":"2026-07-05T01:28:23.359763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:28:23.359763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fr2sxVOQuG0Wf0wggNe9QVYc+va/E0UKtPBu5Q8G4dM2CGsZauI23b+lpUBPf3NRh1HYUzOYnCYD2Uo5u2gfCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:28:23.360183Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.08180","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c947db8e5926ef3ed288245082875049d56e969d8a226a66780b5b6c097462b1","sha256:d2cb74f66568832bbe7842f24e499550b81cab92e7145baf3e55184364a182fd"],"state_sha256":"56f4e00ca97ce824c733ac8246aebd6a3d06931888418cea308ea9cef9639f83"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kYIyMKFlUaS0PLiOZYTRWvCNt1nNk+btJoo4J83n06t3Kj5oYJGQwqEXHivZQBSsPPQvQmo/usMo2CMYag6XAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T16:20:44.480419Z","bundle_sha256":"5a153a088873f8e03604442449b66f3fe2485d0126dac3053182942c81fa46af"}}