{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:7PAKOVAMHI5ZYE2KPPRN4V2B7E","short_pith_number":"pith:7PAKOVAM","canonical_record":{"source":{"id":"1401.6122","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-01-23T19:03:18Z","cross_cats_sorted":[],"title_canon_sha256":"9992b1cd89140bb48e762f818990b9041f78b3346a374a5bd9e442db9da789d0","abstract_canon_sha256":"1955be9b13eccca7278d059f87f7c0b962312a9c528b34e5ee0d05edda91c619"},"schema_version":"1.0"},"canonical_sha256":"fbc0a7540c3a3b9c134a7be2de5741f91acced29a8ee45b7c6fcbdd20f283f39","source":{"kind":"arxiv","id":"1401.6122","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1401.6122","created_at":"2026-05-18T03:01:22Z"},{"alias_kind":"arxiv_version","alias_value":"1401.6122v1","created_at":"2026-05-18T03:01:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1401.6122","created_at":"2026-05-18T03:01:22Z"},{"alias_kind":"pith_short_12","alias_value":"7PAKOVAMHI5Z","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"7PAKOVAMHI5ZYE2K","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"7PAKOVAM","created_at":"2026-05-18T12:28:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:7PAKOVAMHI5ZYE2KPPRN4V2B7E","target":"record","payload":{"canonical_record":{"source":{"id":"1401.6122","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-01-23T19:03:18Z","cross_cats_sorted":[],"title_canon_sha256":"9992b1cd89140bb48e762f818990b9041f78b3346a374a5bd9e442db9da789d0","abstract_canon_sha256":"1955be9b13eccca7278d059f87f7c0b962312a9c528b34e5ee0d05edda91c619"},"schema_version":"1.0"},"canonical_sha256":"fbc0a7540c3a3b9c134a7be2de5741f91acced29a8ee45b7c6fcbdd20f283f39","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:01:22.773654Z","signature_b64":"6gqo0MHHOpG2Pykf7VbrgcrOAQ4zeGorDbuL3KDYdReg68ylb7clFCA1wrhwEGfqnTskStW+l0srLLjtz6YiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbc0a7540c3a3b9c134a7be2de5741f91acced29a8ee45b7c6fcbdd20f283f39","last_reissued_at":"2026-05-18T03:01:22.772855Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:01:22.772855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1401.6122","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":"2026-05-18T03:01:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WHyFjPzZqEY4914MLbckFEWt0EBeRP0+P/h0MSDnNeM6KVTop+ol5YRQX90gQyUkc0wNrtUNDdxkC1w5S+PyDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T00:24:48.751770Z"},"content_sha256":"2a8702901b7274394b81be9b375a41b9cb3422c9d7fd255dc98306e38bc82b49","schema_version":"1.0","event_id":"sha256:2a8702901b7274394b81be9b375a41b9cb3422c9d7fd255dc98306e38bc82b49"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:7PAKOVAMHI5ZYE2KPPRN4V2B7E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Identifying Bengali Multiword Expressions using Semantic Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dipankar Das, Sivaji Bandyopadhyay, Tanmoy Chakraborty","submitted_at":"2014-01-23T19:03:18Z","abstract_excerpt":"One of the key issues in both natural language understanding and generation is the appropriate processing of Multiword Expressions (MWEs). MWEs pose a huge problem to the precise language processing due to their idiosyncratic nature and diversity in lexical, syntactical and semantic properties. The semantics of a MWE cannot be expressed after combining the semantics of its constituents. Therefore, the formalism of semantic clustering is often viewed as an instrument for extracting MWEs especially for resource constraint languages like Bengali. The present semantic clustering approach contribut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1401.6122","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":"2026-05-18T03:01:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fkfdu/0FXUrtgrBPTt8vR6PK9d/6wrVhB8LUROPL4Dp+0lP/+WYenHKbrhCR0srlKySnlWzZyG7KTyYZnEIXBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T00:24:48.752548Z"},"content_sha256":"18903814448bf77a5d08398d5902c84294f68f9ded8b375666f02e190463b577","schema_version":"1.0","event_id":"sha256:18903814448bf77a5d08398d5902c84294f68f9ded8b375666f02e190463b577"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7PAKOVAMHI5ZYE2KPPRN4V2B7E/bundle.json","state_url":"https://pith.science/pith/7PAKOVAMHI5ZYE2KPPRN4V2B7E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7PAKOVAMHI5ZYE2KPPRN4V2B7E/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":"2026-06-11T00:24:48Z","links":{"resolver":"https://pith.science/pith/7PAKOVAMHI5ZYE2KPPRN4V2B7E","bundle":"https://pith.science/pith/7PAKOVAMHI5ZYE2KPPRN4V2B7E/bundle.json","state":"https://pith.science/pith/7PAKOVAMHI5ZYE2KPPRN4V2B7E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7PAKOVAMHI5ZYE2KPPRN4V2B7E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:7PAKOVAMHI5ZYE2KPPRN4V2B7E","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":"1955be9b13eccca7278d059f87f7c0b962312a9c528b34e5ee0d05edda91c619","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-01-23T19:03:18Z","title_canon_sha256":"9992b1cd89140bb48e762f818990b9041f78b3346a374a5bd9e442db9da789d0"},"schema_version":"1.0","source":{"id":"1401.6122","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1401.6122","created_at":"2026-05-18T03:01:22Z"},{"alias_kind":"arxiv_version","alias_value":"1401.6122v1","created_at":"2026-05-18T03:01:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1401.6122","created_at":"2026-05-18T03:01:22Z"},{"alias_kind":"pith_short_12","alias_value":"7PAKOVAMHI5Z","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"7PAKOVAMHI5ZYE2K","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"7PAKOVAM","created_at":"2026-05-18T12:28:19Z"}],"graph_snapshots":[{"event_id":"sha256:18903814448bf77a5d08398d5902c84294f68f9ded8b375666f02e190463b577","target":"graph","created_at":"2026-05-18T03:01:22Z","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":"One of the key issues in both natural language understanding and generation is the appropriate processing of Multiword Expressions (MWEs). MWEs pose a huge problem to the precise language processing due to their idiosyncratic nature and diversity in lexical, syntactical and semantic properties. The semantics of a MWE cannot be expressed after combining the semantics of its constituents. Therefore, the formalism of semantic clustering is often viewed as an instrument for extracting MWEs especially for resource constraint languages like Bengali. The present semantic clustering approach contribut","authors_text":"Dipankar Das, Sivaji Bandyopadhyay, Tanmoy Chakraborty","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-01-23T19:03:18Z","title":"Identifying Bengali Multiword Expressions using Semantic Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1401.6122","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":"sha256:2a8702901b7274394b81be9b375a41b9cb3422c9d7fd255dc98306e38bc82b49","target":"record","created_at":"2026-05-18T03:01:22Z","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":"1955be9b13eccca7278d059f87f7c0b962312a9c528b34e5ee0d05edda91c619","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-01-23T19:03:18Z","title_canon_sha256":"9992b1cd89140bb48e762f818990b9041f78b3346a374a5bd9e442db9da789d0"},"schema_version":"1.0","source":{"id":"1401.6122","kind":"arxiv","version":1}},"canonical_sha256":"fbc0a7540c3a3b9c134a7be2de5741f91acced29a8ee45b7c6fcbdd20f283f39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbc0a7540c3a3b9c134a7be2de5741f91acced29a8ee45b7c6fcbdd20f283f39","first_computed_at":"2026-05-18T03:01:22.772855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:01:22.772855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6gqo0MHHOpG2Pykf7VbrgcrOAQ4zeGorDbuL3KDYdReg68ylb7clFCA1wrhwEGfqnTskStW+l0srLLjtz6YiCA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:01:22.773654Z","signed_message":"canonical_sha256_bytes"},"source_id":"1401.6122","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a8702901b7274394b81be9b375a41b9cb3422c9d7fd255dc98306e38bc82b49","sha256:18903814448bf77a5d08398d5902c84294f68f9ded8b375666f02e190463b577"],"state_sha256":"c6fbfef50e3d72878706623843a33f485dc5b327d9ead510ca51e398a9eb055c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l02/Imw8wHtEjQ5ayZ7JQiAjsfEQit6VRvtNEnPm8eG9U5HMxdXDXwh7tDjjH0fDXxs5PJPdv4asP3FrL8hjCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T00:24:48.757053Z","bundle_sha256":"985619d06a306e2f2a676ff051f024e975c5606b6045d0fba4d0079af930ea0a"}}