{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:U3FSPLFV6ECRX2U6ZRD5N2P43J","short_pith_number":"pith:U3FSPLFV","canonical_record":{"source":{"id":"1710.04142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2017-10-11T15:51:13Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8de1ea57e5f5f091c666f59cef632a1c8b55e1db43a9296292fde35fe622fc88","abstract_canon_sha256":"e047c7ce0fddee383487e02e088795b896b53a9fac893e4b0a484d867e313ea2"},"schema_version":"1.0"},"canonical_sha256":"a6cb27acb5f1051bea9ecc47d6e9fcda4e92a1824aa1bca5574b7f0d13d795e4","source":{"kind":"arxiv","id":"1710.04142","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.04142","created_at":"2026-05-18T00:33:04Z"},{"alias_kind":"arxiv_version","alias_value":"1710.04142v1","created_at":"2026-05-18T00:33:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.04142","created_at":"2026-05-18T00:33:04Z"},{"alias_kind":"pith_short_12","alias_value":"U3FSPLFV6ECR","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"U3FSPLFV6ECRX2U6","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"U3FSPLFV","created_at":"2026-05-18T12:31:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:U3FSPLFV6ECRX2U6ZRD5N2P43J","target":"record","payload":{"canonical_record":{"source":{"id":"1710.04142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2017-10-11T15:51:13Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8de1ea57e5f5f091c666f59cef632a1c8b55e1db43a9296292fde35fe622fc88","abstract_canon_sha256":"e047c7ce0fddee383487e02e088795b896b53a9fac893e4b0a484d867e313ea2"},"schema_version":"1.0"},"canonical_sha256":"a6cb27acb5f1051bea9ecc47d6e9fcda4e92a1824aa1bca5574b7f0d13d795e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:04.800843Z","signature_b64":"0lOGB5vH7zH3qJp9UuLaFoZWbHSkk3zuxxy5hJuw8k222/u1IE11abJLwKDmPhN829DP73RwWRxUzOslKBqmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6cb27acb5f1051bea9ecc47d6e9fcda4e92a1824aa1bca5574b7f0d13d795e4","last_reissued_at":"2026-05-18T00:33:04.800055Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:04.800055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.04142","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":"2026-05-18T00:33:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TW7qeFeK7YTTPspDgq+Bm1qiV4u6tAb5D7knOWIyVoZOaDoaXgbJYyWvX38SSaFEZKNM21eSelXt0Rnng2ayCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T13:14:57.316702Z"},"content_sha256":"19654556e5bf5095d19fc3835d3bddf04d5bf54aa74d2629f7f18c46059be373","schema_version":"1.0","event_id":"sha256:19654556e5bf5095d19fc3835d3bddf04d5bf54aa74d2629f7f18c46059be373"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:U3FSPLFV6ECRX2U6ZRD5N2P43J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bollywood Movie Corpus for Text, Images and Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CY","authors_text":"Aditi Aggarwal, Mayank Saxena, Nishtha Madaan, Sameep Mehta, Taneea S Agrawaal, Vrinda Malhotra","submitted_at":"2017-10-11T15:51:13Z","abstract_excerpt":"In past few years, several data-sets have been released for text and images. We present an approach to create the data-set for use in detecting and removing gender bias from text. We also include a set of challenges we have faced while creating this corpora. In this work, we have worked with movie data from Wikipedia plots and movie trailers from YouTube. Our Bollywood Movie corpus contains 4000 movies extracted from Wikipedia and 880 trailers extracted from YouTube which were released from 1970-2017. The corpus contains csv files with the following data about each movie - Wikipedia title of m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.04142","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":"2026-05-18T00:33:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jwQOSuc2JvwydtqHpFcJ+Y7jxFiaWLnT0um0tRzbM2X5LebL1dh/vpD5jJlOpsPbEh6LAzv8EqZfVbIK5HXiCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T13:14:57.317095Z"},"content_sha256":"b9596ec29b557628730021a86a4cc86f619605cec5afd540ca382cd7a5b37975","schema_version":"1.0","event_id":"sha256:b9596ec29b557628730021a86a4cc86f619605cec5afd540ca382cd7a5b37975"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U3FSPLFV6ECRX2U6ZRD5N2P43J/bundle.json","state_url":"https://pith.science/pith/U3FSPLFV6ECRX2U6ZRD5N2P43J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U3FSPLFV6ECRX2U6ZRD5N2P43J/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":"2026-06-02T13:14:57Z","links":{"resolver":"https://pith.science/pith/U3FSPLFV6ECRX2U6ZRD5N2P43J","bundle":"https://pith.science/pith/U3FSPLFV6ECRX2U6ZRD5N2P43J/bundle.json","state":"https://pith.science/pith/U3FSPLFV6ECRX2U6ZRD5N2P43J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U3FSPLFV6ECRX2U6ZRD5N2P43J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:U3FSPLFV6ECRX2U6ZRD5N2P43J","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":"e047c7ce0fddee383487e02e088795b896b53a9fac893e4b0a484d867e313ea2","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2017-10-11T15:51:13Z","title_canon_sha256":"8de1ea57e5f5f091c666f59cef632a1c8b55e1db43a9296292fde35fe622fc88"},"schema_version":"1.0","source":{"id":"1710.04142","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.04142","created_at":"2026-05-18T00:33:04Z"},{"alias_kind":"arxiv_version","alias_value":"1710.04142v1","created_at":"2026-05-18T00:33:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.04142","created_at":"2026-05-18T00:33:04Z"},{"alias_kind":"pith_short_12","alias_value":"U3FSPLFV6ECR","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"U3FSPLFV6ECRX2U6","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"U3FSPLFV","created_at":"2026-05-18T12:31:46Z"}],"graph_snapshots":[{"event_id":"sha256:b9596ec29b557628730021a86a4cc86f619605cec5afd540ca382cd7a5b37975","target":"graph","created_at":"2026-05-18T00:33:04Z","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":"In past few years, several data-sets have been released for text and images. We present an approach to create the data-set for use in detecting and removing gender bias from text. We also include a set of challenges we have faced while creating this corpora. In this work, we have worked with movie data from Wikipedia plots and movie trailers from YouTube. Our Bollywood Movie corpus contains 4000 movies extracted from Wikipedia and 880 trailers extracted from YouTube which were released from 1970-2017. The corpus contains csv files with the following data about each movie - Wikipedia title of m","authors_text":"Aditi Aggarwal, Mayank Saxena, Nishtha Madaan, Sameep Mehta, Taneea S Agrawaal, Vrinda Malhotra","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2017-10-11T15:51:13Z","title":"Bollywood Movie Corpus for Text, Images and Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.04142","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":"sha256:19654556e5bf5095d19fc3835d3bddf04d5bf54aa74d2629f7f18c46059be373","target":"record","created_at":"2026-05-18T00:33:04Z","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":"e047c7ce0fddee383487e02e088795b896b53a9fac893e4b0a484d867e313ea2","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2017-10-11T15:51:13Z","title_canon_sha256":"8de1ea57e5f5f091c666f59cef632a1c8b55e1db43a9296292fde35fe622fc88"},"schema_version":"1.0","source":{"id":"1710.04142","kind":"arxiv","version":1}},"canonical_sha256":"a6cb27acb5f1051bea9ecc47d6e9fcda4e92a1824aa1bca5574b7f0d13d795e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6cb27acb5f1051bea9ecc47d6e9fcda4e92a1824aa1bca5574b7f0d13d795e4","first_computed_at":"2026-05-18T00:33:04.800055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:33:04.800055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0lOGB5vH7zH3qJp9UuLaFoZWbHSkk3zuxxy5hJuw8k222/u1IE11abJLwKDmPhN829DP73RwWRxUzOslKBqmBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:33:04.800843Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.04142","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19654556e5bf5095d19fc3835d3bddf04d5bf54aa74d2629f7f18c46059be373","sha256:b9596ec29b557628730021a86a4cc86f619605cec5afd540ca382cd7a5b37975"],"state_sha256":"695659f83c86360814346fc478ef0eeff6ceb310c1c0dfe5094886f19833b08b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DoO6fChtGuGxUvmlcPwuPH4uzvGkG8N6hEukbxUQXReDdeuT/GZiNMCp07UbJ4LrLDlf0VAzesM+cbpvNJ42Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T13:14:57.320232Z","bundle_sha256":"10c6c31857bb5e4f0c4e995acd29223815fa6095c210a0e2a5318566b57bb1c3"}}