{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:PWFA3BUFWZE35PSE6PLB3PUXFR","short_pith_number":"pith:PWFA3BUF","canonical_record":{"source":{"id":"2106.04174","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-08T08:27:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e36918c90c337e6387b6d1b70912e91779abfaee5b6048c79a3ba5c33888f7b6","abstract_canon_sha256":"90f114e370b9e1c851589827559273001a2d515b77f45f2010591a2fb07744e7"},"schema_version":"1.0"},"canonical_sha256":"7d8a0d8685b649bebe44f3d61dbe972c674d2c542ca9ed48dcb5ba18e8dc7644","source":{"kind":"arxiv","id":"2106.04174","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.04174","created_at":"2026-07-05T02:47:12Z"},{"alias_kind":"arxiv_version","alias_value":"2106.04174v1","created_at":"2026-07-05T02:47:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04174","created_at":"2026-07-05T02:47:12Z"},{"alias_kind":"pith_short_12","alias_value":"PWFA3BUFWZE3","created_at":"2026-07-05T02:47:12Z"},{"alias_kind":"pith_short_16","alias_value":"PWFA3BUFWZE35PSE","created_at":"2026-07-05T02:47:12Z"},{"alias_kind":"pith_short_8","alias_value":"PWFA3BUF","created_at":"2026-07-05T02:47:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:PWFA3BUFWZE35PSE6PLB3PUXFR","target":"record","payload":{"canonical_record":{"source":{"id":"2106.04174","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-08T08:27:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e36918c90c337e6387b6d1b70912e91779abfaee5b6048c79a3ba5c33888f7b6","abstract_canon_sha256":"90f114e370b9e1c851589827559273001a2d515b77f45f2010591a2fb07744e7"},"schema_version":"1.0"},"canonical_sha256":"7d8a0d8685b649bebe44f3d61dbe972c674d2c542ca9ed48dcb5ba18e8dc7644","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:47:12.908230Z","signature_b64":"vD1V4RXfBC5D3cZNQ7Cf0lV/SZFu1AD7TQKpGs054/jMuUkQKzrADZ1QRBaEDc1QuK1XPNuTzPiBrAW3skObDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d8a0d8685b649bebe44f3d61dbe972c674d2c542ca9ed48dcb5ba18e8dc7644","last_reissued_at":"2026-07-05T02:47:12.907703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:47:12.907703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.04174","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":"2026-07-05T02:47:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xxV6v3fdAGceGcXYPOXy9FcUnge9KWmCV3z6TzXCz6HWHzBaOJBXK0rmfeY3X6VIcRukpN/p1vJI4VV42znbBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:44:43.279745Z"},"content_sha256":"e2053ac480fb828c7cacf7c25c7657753da45579e8e70fca632cb8c81afd5028","schema_version":"1.0","event_id":"sha256:e2053ac480fb828c7cacf7c25c7657753da45579e8e70fca632cb8c81afd5028"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:PWFA3BUFWZE35PSE6PLB3PUXFR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengjiang Li, Jifan Yu, Juanzi Li, Lei Hou, Tiansi Dong, Xin Lv, Yichi Zhang, Zelin Dai, Zijun Yao","submitted_at":"2021-06-08T08:27:31Z","abstract_excerpt":"Entity Matching (EM) aims at recognizing entity records that denote the same real-world object. Neural EM models learn vector representation of entity descriptions and match entities end-to-end. Though robust, these methods require many resources for training, and lack of interpretability. In this paper, we propose a novel EM framework that consists of Heterogeneous Information Fusion (HIF) and Key Attribute Tree (KAT) Induction to decouple feature representation from matching decision. Using self-supervised learning and mask mechanism in pre-trained language modeling, HIF learns the embedding"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04174","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/2106.04174/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":"2026-07-05T02:47:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zxnV3y9U1OzogjhPGqwwyrFnV0yv/N3avkUvjQR8/QZ4t4Kcze8M/VJXPu6Bgp/GUDqQuVl2xuJPxQVYxrKsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:44:43.280121Z"},"content_sha256":"d27c356ad64f6b33746e5fc11d872f884a923664216c10a62717e2bd3feda872","schema_version":"1.0","event_id":"sha256:d27c356ad64f6b33746e5fc11d872f884a923664216c10a62717e2bd3feda872"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PWFA3BUFWZE35PSE6PLB3PUXFR/bundle.json","state_url":"https://pith.science/pith/PWFA3BUFWZE35PSE6PLB3PUXFR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PWFA3BUFWZE35PSE6PLB3PUXFR/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":"2026-07-06T18:44:43Z","links":{"resolver":"https://pith.science/pith/PWFA3BUFWZE35PSE6PLB3PUXFR","bundle":"https://pith.science/pith/PWFA3BUFWZE35PSE6PLB3PUXFR/bundle.json","state":"https://pith.science/pith/PWFA3BUFWZE35PSE6PLB3PUXFR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PWFA3BUFWZE35PSE6PLB3PUXFR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PWFA3BUFWZE35PSE6PLB3PUXFR","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":"90f114e370b9e1c851589827559273001a2d515b77f45f2010591a2fb07744e7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-08T08:27:31Z","title_canon_sha256":"e36918c90c337e6387b6d1b70912e91779abfaee5b6048c79a3ba5c33888f7b6"},"schema_version":"1.0","source":{"id":"2106.04174","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.04174","created_at":"2026-07-05T02:47:12Z"},{"alias_kind":"arxiv_version","alias_value":"2106.04174v1","created_at":"2026-07-05T02:47:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04174","created_at":"2026-07-05T02:47:12Z"},{"alias_kind":"pith_short_12","alias_value":"PWFA3BUFWZE3","created_at":"2026-07-05T02:47:12Z"},{"alias_kind":"pith_short_16","alias_value":"PWFA3BUFWZE35PSE","created_at":"2026-07-05T02:47:12Z"},{"alias_kind":"pith_short_8","alias_value":"PWFA3BUF","created_at":"2026-07-05T02:47:12Z"}],"graph_snapshots":[{"event_id":"sha256:d27c356ad64f6b33746e5fc11d872f884a923664216c10a62717e2bd3feda872","target":"graph","created_at":"2026-07-05T02:47:12Z","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/2106.04174/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Entity Matching (EM) aims at recognizing entity records that denote the same real-world object. Neural EM models learn vector representation of entity descriptions and match entities end-to-end. Though robust, these methods require many resources for training, and lack of interpretability. In this paper, we propose a novel EM framework that consists of Heterogeneous Information Fusion (HIF) and Key Attribute Tree (KAT) Induction to decouple feature representation from matching decision. Using self-supervised learning and mask mechanism in pre-trained language modeling, HIF learns the embedding","authors_text":"Chengjiang Li, Jifan Yu, Juanzi Li, Lei Hou, Tiansi Dong, Xin Lv, Yichi Zhang, Zelin Dai, Zijun Yao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-08T08:27:31Z","title":"Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04174","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:e2053ac480fb828c7cacf7c25c7657753da45579e8e70fca632cb8c81afd5028","target":"record","created_at":"2026-07-05T02:47:12Z","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":"90f114e370b9e1c851589827559273001a2d515b77f45f2010591a2fb07744e7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-08T08:27:31Z","title_canon_sha256":"e36918c90c337e6387b6d1b70912e91779abfaee5b6048c79a3ba5c33888f7b6"},"schema_version":"1.0","source":{"id":"2106.04174","kind":"arxiv","version":1}},"canonical_sha256":"7d8a0d8685b649bebe44f3d61dbe972c674d2c542ca9ed48dcb5ba18e8dc7644","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d8a0d8685b649bebe44f3d61dbe972c674d2c542ca9ed48dcb5ba18e8dc7644","first_computed_at":"2026-07-05T02:47:12.907703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:47:12.907703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vD1V4RXfBC5D3cZNQ7Cf0lV/SZFu1AD7TQKpGs054/jMuUkQKzrADZ1QRBaEDc1QuK1XPNuTzPiBrAW3skObDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:47:12.908230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.04174","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2053ac480fb828c7cacf7c25c7657753da45579e8e70fca632cb8c81afd5028","sha256:d27c356ad64f6b33746e5fc11d872f884a923664216c10a62717e2bd3feda872"],"state_sha256":"5f64df86e973b188550f4942438591e7a46b8ba17f898d9025f4ac96a55b86e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mjTp/SecQ5QpAwwTmX7I/RhiTZ5MyvHm5N2uQCb28Fzlv3PaukW97ZHcwXj2C/KOjX0hMIHL5+fj+tXdT5ZvCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:44:43.282151Z","bundle_sha256":"bd136ce65e3bc1d30dd75b430b4296fa63f3155fde17665b51cf81d3c07615a9"}}