{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:7FNS7PZCVYYMZOZRIKPFIFWKE5","short_pith_number":"pith:7FNS7PZC","canonical_record":{"source":{"id":"1612.00148","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-01T05:08:53Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"5b42b34ac1bd901e1b9ea273148e2a701228a5ece2b0f5f2c7e18fc7758961c0","abstract_canon_sha256":"d26a203a5e9a7a145693fde91a30f90fa571de57258dab39ec50c5c49b70f22d"},"schema_version":"1.0"},"canonical_sha256":"f95b2fbf22ae30ccbb31429e5416ca277ea57942494da96327f433d2ca6eb7e3","source":{"kind":"arxiv","id":"1612.00148","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.00148","created_at":"2026-05-18T00:56:05Z"},{"alias_kind":"arxiv_version","alias_value":"1612.00148v1","created_at":"2026-05-18T00:56:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.00148","created_at":"2026-05-18T00:56:05Z"},{"alias_kind":"pith_short_12","alias_value":"7FNS7PZCVYYM","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_16","alias_value":"7FNS7PZCVYYMZOZR","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_8","alias_value":"7FNS7PZC","created_at":"2026-05-18T12:30:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:7FNS7PZCVYYMZOZRIKPFIFWKE5","target":"record","payload":{"canonical_record":{"source":{"id":"1612.00148","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-01T05:08:53Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"5b42b34ac1bd901e1b9ea273148e2a701228a5ece2b0f5f2c7e18fc7758961c0","abstract_canon_sha256":"d26a203a5e9a7a145693fde91a30f90fa571de57258dab39ec50c5c49b70f22d"},"schema_version":"1.0"},"canonical_sha256":"f95b2fbf22ae30ccbb31429e5416ca277ea57942494da96327f433d2ca6eb7e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:05.909585Z","signature_b64":"YTYi4LTiZtJrzIkU8R9uGbc94DfMWe0w3RedQJWe2CjiA5ktiWfKXb09J3U8Ef562QDaOAusxXWyqMv7qV3CCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f95b2fbf22ae30ccbb31429e5416ca277ea57942494da96327f433d2ca6eb7e3","last_reissued_at":"2026-05-18T00:56:05.909003Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:05.909003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.00148","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":"2026-05-18T00:56:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+hmAWwqx2V16HG/f/VLUbcapbq9UluwTNJapjn67Hy1RKGkCTkU3tszJlmwfG7lmS+8oG8IMydqhAd/4qgNzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T20:24:03.563696Z"},"content_sha256":"52856c1e2b58b98166b772c819a06faa9b2ef041f599479bc3616c24996b15d5","schema_version":"1.0","event_id":"sha256:52856c1e2b58b98166b772c819a06faa9b2ef041f599479bc3616c24996b15d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:7FNS7PZCVYYMZOZRIKPFIFWKE5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Domain Adaptation for Named Entity Recognition in Online Media with Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Troy Chevalier, Vivek Kulkarni, Yashar Mehdad","submitted_at":"2016-12-01T05:08:53Z","abstract_excerpt":"Content on the Internet is heterogeneous and arises from various domains like News, Entertainment, Finance and Technology. Understanding such content requires identifying named entities (persons, places and organizations) as one of the key steps. Traditionally Named Entity Recognition (NER) systems have been built using available annotated datasets (like CoNLL, MUC) and demonstrate excellent performance. However, these models fail to generalize onto other domains like Sports and Finance where conventions and language use can differ significantly. Furthermore, several domains do not have large "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.00148","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":"2026-05-18T00:56:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6meM9W66AXmFfSDAMlsGYy3dTHcYUGgu4L6eRTE5Bj50/Uw7kVcllehZsnyJP/uKgPdjsQCuYzYNG7aha/cSCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T20:24:03.564340Z"},"content_sha256":"d83f563e4321ef335f3210d909a4540532093ed11c7541b41b1644091d5da6d2","schema_version":"1.0","event_id":"sha256:d83f563e4321ef335f3210d909a4540532093ed11c7541b41b1644091d5da6d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7FNS7PZCVYYMZOZRIKPFIFWKE5/bundle.json","state_url":"https://pith.science/pith/7FNS7PZCVYYMZOZRIKPFIFWKE5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7FNS7PZCVYYMZOZRIKPFIFWKE5/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":"2026-05-26T20:24:03Z","links":{"resolver":"https://pith.science/pith/7FNS7PZCVYYMZOZRIKPFIFWKE5","bundle":"https://pith.science/pith/7FNS7PZCVYYMZOZRIKPFIFWKE5/bundle.json","state":"https://pith.science/pith/7FNS7PZCVYYMZOZRIKPFIFWKE5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7FNS7PZCVYYMZOZRIKPFIFWKE5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:7FNS7PZCVYYMZOZRIKPFIFWKE5","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":"d26a203a5e9a7a145693fde91a30f90fa571de57258dab39ec50c5c49b70f22d","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-01T05:08:53Z","title_canon_sha256":"5b42b34ac1bd901e1b9ea273148e2a701228a5ece2b0f5f2c7e18fc7758961c0"},"schema_version":"1.0","source":{"id":"1612.00148","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.00148","created_at":"2026-05-18T00:56:05Z"},{"alias_kind":"arxiv_version","alias_value":"1612.00148v1","created_at":"2026-05-18T00:56:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.00148","created_at":"2026-05-18T00:56:05Z"},{"alias_kind":"pith_short_12","alias_value":"7FNS7PZCVYYM","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_16","alias_value":"7FNS7PZCVYYMZOZR","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_8","alias_value":"7FNS7PZC","created_at":"2026-05-18T12:30:04Z"}],"graph_snapshots":[{"event_id":"sha256:d83f563e4321ef335f3210d909a4540532093ed11c7541b41b1644091d5da6d2","target":"graph","created_at":"2026-05-18T00:56:05Z","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":"Content on the Internet is heterogeneous and arises from various domains like News, Entertainment, Finance and Technology. Understanding such content requires identifying named entities (persons, places and organizations) as one of the key steps. Traditionally Named Entity Recognition (NER) systems have been built using available annotated datasets (like CoNLL, MUC) and demonstrate excellent performance. However, these models fail to generalize onto other domains like Sports and Finance where conventions and language use can differ significantly. Furthermore, several domains do not have large ","authors_text":"Troy Chevalier, Vivek Kulkarni, Yashar Mehdad","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-01T05:08:53Z","title":"Domain Adaptation for Named Entity Recognition in Online Media with Word Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.00148","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":"sha256:52856c1e2b58b98166b772c819a06faa9b2ef041f599479bc3616c24996b15d5","target":"record","created_at":"2026-05-18T00:56:05Z","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":"d26a203a5e9a7a145693fde91a30f90fa571de57258dab39ec50c5c49b70f22d","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-01T05:08:53Z","title_canon_sha256":"5b42b34ac1bd901e1b9ea273148e2a701228a5ece2b0f5f2c7e18fc7758961c0"},"schema_version":"1.0","source":{"id":"1612.00148","kind":"arxiv","version":1}},"canonical_sha256":"f95b2fbf22ae30ccbb31429e5416ca277ea57942494da96327f433d2ca6eb7e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f95b2fbf22ae30ccbb31429e5416ca277ea57942494da96327f433d2ca6eb7e3","first_computed_at":"2026-05-18T00:56:05.909003Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:56:05.909003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YTYi4LTiZtJrzIkU8R9uGbc94DfMWe0w3RedQJWe2CjiA5ktiWfKXb09J3U8Ef562QDaOAusxXWyqMv7qV3CCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:56:05.909585Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.00148","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52856c1e2b58b98166b772c819a06faa9b2ef041f599479bc3616c24996b15d5","sha256:d83f563e4321ef335f3210d909a4540532093ed11c7541b41b1644091d5da6d2"],"state_sha256":"1dfd3407773908f564d530f7acd0bdde7371aedd891eba3b8848e7b479d6f5ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FynNZAjLD+hlUsiPwYXBD9A2SvxMsQ7o9xM9BPQJJtwMdPMhs0AdIa+rc6wdetK1lCZm2QgoZShZLX38Y4qaBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T20:24:03.567875Z","bundle_sha256":"9abe0851f16bb16fbf309658b0f00727a644c253a80d1b5d402255e4130f8da4"}}