{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HENUK5YRU4QQXHHL2JBYVRUWGB","short_pith_number":"pith:HENUK5YR","canonical_record":{"source":{"id":"1908.01798","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-08-05T18:28:09Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"071112a69ca391d99f7155b853a65dc2101f0bc84beb030e870ee101c40126d5","abstract_canon_sha256":"f6df463a3a4793b06031bce129e6f0cd2e6d9a10505ed1c579e316b738d32036"},"schema_version":"1.0"},"canonical_sha256":"391b457711a7210b9cebd2438ac6963056bb46a74cacac7f60fe306354449349","source":{"kind":"arxiv","id":"1908.01798","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.01798","created_at":"2026-07-04T23:51:47Z"},{"alias_kind":"arxiv_version","alias_value":"1908.01798v1","created_at":"2026-07-04T23:51:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01798","created_at":"2026-07-04T23:51:47Z"},{"alias_kind":"pith_short_12","alias_value":"HENUK5YRU4QQ","created_at":"2026-07-04T23:51:47Z"},{"alias_kind":"pith_short_16","alias_value":"HENUK5YRU4QQXHHL","created_at":"2026-07-04T23:51:47Z"},{"alias_kind":"pith_short_8","alias_value":"HENUK5YR","created_at":"2026-07-04T23:51:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HENUK5YRU4QQXHHL2JBYVRUWGB","target":"record","payload":{"canonical_record":{"source":{"id":"1908.01798","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-08-05T18:28:09Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"071112a69ca391d99f7155b853a65dc2101f0bc84beb030e870ee101c40126d5","abstract_canon_sha256":"f6df463a3a4793b06031bce129e6f0cd2e6d9a10505ed1c579e316b738d32036"},"schema_version":"1.0"},"canonical_sha256":"391b457711a7210b9cebd2438ac6963056bb46a74cacac7f60fe306354449349","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:51:47.577382Z","signature_b64":"IemeKQa03B2vuniBA4jntAm5qkRYQC+91RqwOzCvvOqRuikpqRDEjgv0wggKPDUvESFVrVIqYXEklc2aNB7rAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"391b457711a7210b9cebd2438ac6963056bb46a74cacac7f60fe306354449349","last_reissued_at":"2026-07-04T23:51:47.577006Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:51:47.577006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.01798","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":"2026-07-04T23:51:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BZNAYik2+A04xW6aq2yRS+snuR2rjy6ig2egvxot7pq8fVR2avO4wXYdhddJmGyjyag5YqwCuCbYVPxjJ531BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:35:24.089785Z"},"content_sha256":"47118a8e94a7e05523772e09cc610e27417402d9c6de63138be27eace27af979","schema_version":"1.0","event_id":"sha256:47118a8e94a7e05523772e09cc610e27417402d9c6de63138be27eace27af979"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HENUK5YRU4QQXHHL2JBYVRUWGB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Context Retrieval for Long-tail Entities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Dar\\'io Garigliotti, Dyaa Albakour, Krisztian Balog, Miguel Martinez","submitted_at":"2019-08-05T18:28:09Z","abstract_excerpt":"Monitoring entities in media streams often relies on rich entity representations, like structured information available in a knowledge base (KB). For long-tail entities, such monitoring is highly challenging, due to their limited, if not entirely missing, representation in the reference KB. In this paper, we address the problem of retrieving textual contexts for monitoring long-tail entities. We propose an unsupervised method to overcome the limited representation of long-tail entities by leveraging established entities and their contexts as support information. Evaluation on a purpose-built t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01798","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/1908.01798/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":"2026-07-04T23:51:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z6d3b0AEfpXjbcifB3aJVa8tr2BeGLGLUHWf6xqhVF6RmU3qWJzhJR0p8PnVvjwm3yjDW28NRskb4sYDhmRbBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:35:24.090356Z"},"content_sha256":"a5b4d0659295093b3e2029b9da06b98a08bf30055015d306eafcf6128ff9a4a6","schema_version":"1.0","event_id":"sha256:a5b4d0659295093b3e2029b9da06b98a08bf30055015d306eafcf6128ff9a4a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HENUK5YRU4QQXHHL2JBYVRUWGB/bundle.json","state_url":"https://pith.science/pith/HENUK5YRU4QQXHHL2JBYVRUWGB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HENUK5YRU4QQXHHL2JBYVRUWGB/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":"2026-08-18T15:35:24Z","links":{"resolver":"https://pith.science/pith/HENUK5YRU4QQXHHL2JBYVRUWGB","bundle":"https://pith.science/pith/HENUK5YRU4QQXHHL2JBYVRUWGB/bundle.json","state":"https://pith.science/pith/HENUK5YRU4QQXHHL2JBYVRUWGB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HENUK5YRU4QQXHHL2JBYVRUWGB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HENUK5YRU4QQXHHL2JBYVRUWGB","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":"f6df463a3a4793b06031bce129e6f0cd2e6d9a10505ed1c579e316b738d32036","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-08-05T18:28:09Z","title_canon_sha256":"071112a69ca391d99f7155b853a65dc2101f0bc84beb030e870ee101c40126d5"},"schema_version":"1.0","source":{"id":"1908.01798","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.01798","created_at":"2026-07-04T23:51:47Z"},{"alias_kind":"arxiv_version","alias_value":"1908.01798v1","created_at":"2026-07-04T23:51:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01798","created_at":"2026-07-04T23:51:47Z"},{"alias_kind":"pith_short_12","alias_value":"HENUK5YRU4QQ","created_at":"2026-07-04T23:51:47Z"},{"alias_kind":"pith_short_16","alias_value":"HENUK5YRU4QQXHHL","created_at":"2026-07-04T23:51:47Z"},{"alias_kind":"pith_short_8","alias_value":"HENUK5YR","created_at":"2026-07-04T23:51:47Z"}],"graph_snapshots":[{"event_id":"sha256:a5b4d0659295093b3e2029b9da06b98a08bf30055015d306eafcf6128ff9a4a6","target":"graph","created_at":"2026-07-04T23:51:47Z","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/1908.01798/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Monitoring entities in media streams often relies on rich entity representations, like structured information available in a knowledge base (KB). For long-tail entities, such monitoring is highly challenging, due to their limited, if not entirely missing, representation in the reference KB. In this paper, we address the problem of retrieving textual contexts for monitoring long-tail entities. We propose an unsupervised method to overcome the limited representation of long-tail entities by leveraging established entities and their contexts as support information. Evaluation on a purpose-built t","authors_text":"Dar\\'io Garigliotti, Dyaa Albakour, Krisztian Balog, Miguel Martinez","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-08-05T18:28:09Z","title":"Unsupervised Context Retrieval for Long-tail Entities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01798","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":"sha256:47118a8e94a7e05523772e09cc610e27417402d9c6de63138be27eace27af979","target":"record","created_at":"2026-07-04T23:51:47Z","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":"f6df463a3a4793b06031bce129e6f0cd2e6d9a10505ed1c579e316b738d32036","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-08-05T18:28:09Z","title_canon_sha256":"071112a69ca391d99f7155b853a65dc2101f0bc84beb030e870ee101c40126d5"},"schema_version":"1.0","source":{"id":"1908.01798","kind":"arxiv","version":1}},"canonical_sha256":"391b457711a7210b9cebd2438ac6963056bb46a74cacac7f60fe306354449349","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"391b457711a7210b9cebd2438ac6963056bb46a74cacac7f60fe306354449349","first_computed_at":"2026-07-04T23:51:47.577006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:51:47.577006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IemeKQa03B2vuniBA4jntAm5qkRYQC+91RqwOzCvvOqRuikpqRDEjgv0wggKPDUvESFVrVIqYXEklc2aNB7rAg==","signature_status":"signed_v1","signed_at":"2026-07-04T23:51:47.577382Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.01798","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47118a8e94a7e05523772e09cc610e27417402d9c6de63138be27eace27af979","sha256:a5b4d0659295093b3e2029b9da06b98a08bf30055015d306eafcf6128ff9a4a6"],"state_sha256":"d9120582ad50b0beb95a317d400e171e19780552fbe20f70b6539335207af561"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/q+m67/T/1nwOKw8oLHsQVSXHXARjpMEi3B0876erxgCu9QFZsz5vJzENCt/NsNSU5mQQBT29Kmo9DYoG60yCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T15:35:24.096899Z","bundle_sha256":"5281d371da42ec0b7e054353cc0147076ba7c861fc7264c1b9f7eccfe3fcbb4f"}}