{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:7ZSAPKFT3HNGNXTBUNTD6KLIB4","short_pith_number":"pith:7ZSAPKFT","canonical_record":{"source":{"id":"2104.03762","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-08T13:27:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"55d5d6afe3dfcc8c719dbe1bd0e98abc6e21cb218e3b340d2d36446b35b528cf","abstract_canon_sha256":"a6322eb5609abcf5683b71d0ce7426a7ece6e67e6cfec894864a8157cfd94fcf"},"schema_version":"1.0"},"canonical_sha256":"fe6407a8b3d9da66de61a3663f29680f01b3c00a5412e30afe2c6d93a924d7c9","source":{"kind":"arxiv","id":"2104.03762","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.03762","created_at":"2026-07-05T02:30:23Z"},{"alias_kind":"arxiv_version","alias_value":"2104.03762v1","created_at":"2026-07-05T02:30:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.03762","created_at":"2026-07-05T02:30:23Z"},{"alias_kind":"pith_short_12","alias_value":"7ZSAPKFT3HNG","created_at":"2026-07-05T02:30:23Z"},{"alias_kind":"pith_short_16","alias_value":"7ZSAPKFT3HNGNXTB","created_at":"2026-07-05T02:30:23Z"},{"alias_kind":"pith_short_8","alias_value":"7ZSAPKFT","created_at":"2026-07-05T02:30:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:7ZSAPKFT3HNGNXTBUNTD6KLIB4","target":"record","payload":{"canonical_record":{"source":{"id":"2104.03762","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-08T13:27:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"55d5d6afe3dfcc8c719dbe1bd0e98abc6e21cb218e3b340d2d36446b35b528cf","abstract_canon_sha256":"a6322eb5609abcf5683b71d0ce7426a7ece6e67e6cfec894864a8157cfd94fcf"},"schema_version":"1.0"},"canonical_sha256":"fe6407a8b3d9da66de61a3663f29680f01b3c00a5412e30afe2c6d93a924d7c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:23.167179Z","signature_b64":"gRGO3dTlSbTqVPPI34WLWqTa+SCYYiblutXu3SqkBiHIoWloabkadRyRfTRvOTA4pHiQaD5bgg13VWQjSrr+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe6407a8b3d9da66de61a3663f29680f01b3c00a5412e30afe2c6d93a924d7c9","last_reissued_at":"2026-07-05T02:30:23.166688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:23.166688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.03762","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":"2026-07-05T02:30:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xmf4Hcxal3YPCYqTT0i6SDUeu+kcgiq+yy4Aaknbv8uOFeAscMsFutlmdLcx06PmY6LVZ8d7h3RxjpXqdKrpDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:15:09.680342Z"},"content_sha256":"f53785a97aad011ed6de7f7c87cd7106472d554b8f059f4954f50d74025c542a","schema_version":"1.0","event_id":"sha256:f53785a97aad011ed6de7f7c87cd7106472d554b8f059f4954f50d74025c542a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:7ZSAPKFT3HNGNXTBUNTD6KLIB4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video Question Answering with Phrases via Semantic Roles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Arka Sadhu, Kan Chen, Ram Nevatia","submitted_at":"2021-04-08T13:27:43Z","abstract_excerpt":"Video Question Answering (VidQA) evaluation metrics have been limited to a single-word answer or selecting a phrase from a fixed set of phrases. These metrics limit the VidQA models' application scenario. In this work, we leverage semantic roles derived from video descriptions to mask out certain phrases, to introduce VidQAP which poses VidQA as a fill-in-the-phrase task. To enable evaluation of answer phrases, we compute the relative improvement of the predicted answer compared to an empty string. To reduce the influence of language bias in VidQA datasets, we retrieve a video having a differe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.03762","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/2104.03762/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":"2026-07-05T02:30:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AXAbYuL666qi/PcUo/fzZW4KWLSPgZeFGija/z9i8oxu8OjuVxeS127iMkKeoGZ5MNQkZy0XqYqAWPujlwZtAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:15:09.680946Z"},"content_sha256":"61e0b5c9f04f8d46818ab7dc6201da8d869d6accb11481f790a63378ce0a2483","schema_version":"1.0","event_id":"sha256:61e0b5c9f04f8d46818ab7dc6201da8d869d6accb11481f790a63378ce0a2483"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7ZSAPKFT3HNGNXTBUNTD6KLIB4/bundle.json","state_url":"https://pith.science/pith/7ZSAPKFT3HNGNXTBUNTD6KLIB4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7ZSAPKFT3HNGNXTBUNTD6KLIB4/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":"2026-08-10T06:15:09Z","links":{"resolver":"https://pith.science/pith/7ZSAPKFT3HNGNXTBUNTD6KLIB4","bundle":"https://pith.science/pith/7ZSAPKFT3HNGNXTBUNTD6KLIB4/bundle.json","state":"https://pith.science/pith/7ZSAPKFT3HNGNXTBUNTD6KLIB4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7ZSAPKFT3HNGNXTBUNTD6KLIB4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7ZSAPKFT3HNGNXTBUNTD6KLIB4","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":"a6322eb5609abcf5683b71d0ce7426a7ece6e67e6cfec894864a8157cfd94fcf","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-08T13:27:43Z","title_canon_sha256":"55d5d6afe3dfcc8c719dbe1bd0e98abc6e21cb218e3b340d2d36446b35b528cf"},"schema_version":"1.0","source":{"id":"2104.03762","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.03762","created_at":"2026-07-05T02:30:23Z"},{"alias_kind":"arxiv_version","alias_value":"2104.03762v1","created_at":"2026-07-05T02:30:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.03762","created_at":"2026-07-05T02:30:23Z"},{"alias_kind":"pith_short_12","alias_value":"7ZSAPKFT3HNG","created_at":"2026-07-05T02:30:23Z"},{"alias_kind":"pith_short_16","alias_value":"7ZSAPKFT3HNGNXTB","created_at":"2026-07-05T02:30:23Z"},{"alias_kind":"pith_short_8","alias_value":"7ZSAPKFT","created_at":"2026-07-05T02:30:23Z"}],"graph_snapshots":[{"event_id":"sha256:61e0b5c9f04f8d46818ab7dc6201da8d869d6accb11481f790a63378ce0a2483","target":"graph","created_at":"2026-07-05T02:30:23Z","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/2104.03762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Question Answering (VidQA) evaluation metrics have been limited to a single-word answer or selecting a phrase from a fixed set of phrases. These metrics limit the VidQA models' application scenario. In this work, we leverage semantic roles derived from video descriptions to mask out certain phrases, to introduce VidQAP which poses VidQA as a fill-in-the-phrase task. To enable evaluation of answer phrases, we compute the relative improvement of the predicted answer compared to an empty string. To reduce the influence of language bias in VidQA datasets, we retrieve a video having a differe","authors_text":"Arka Sadhu, Kan Chen, Ram Nevatia","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-08T13:27:43Z","title":"Video Question Answering with Phrases via Semantic Roles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.03762","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:f53785a97aad011ed6de7f7c87cd7106472d554b8f059f4954f50d74025c542a","target":"record","created_at":"2026-07-05T02:30:23Z","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":"a6322eb5609abcf5683b71d0ce7426a7ece6e67e6cfec894864a8157cfd94fcf","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-08T13:27:43Z","title_canon_sha256":"55d5d6afe3dfcc8c719dbe1bd0e98abc6e21cb218e3b340d2d36446b35b528cf"},"schema_version":"1.0","source":{"id":"2104.03762","kind":"arxiv","version":1}},"canonical_sha256":"fe6407a8b3d9da66de61a3663f29680f01b3c00a5412e30afe2c6d93a924d7c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe6407a8b3d9da66de61a3663f29680f01b3c00a5412e30afe2c6d93a924d7c9","first_computed_at":"2026-07-05T02:30:23.166688Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:30:23.166688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gRGO3dTlSbTqVPPI34WLWqTa+SCYYiblutXu3SqkBiHIoWloabkadRyRfTRvOTA4pHiQaD5bgg13VWQjSrr+DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:30:23.167179Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.03762","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f53785a97aad011ed6de7f7c87cd7106472d554b8f059f4954f50d74025c542a","sha256:61e0b5c9f04f8d46818ab7dc6201da8d869d6accb11481f790a63378ce0a2483"],"state_sha256":"f034b96148532a06199bc89003d8ead1883c2a5a9d6a7758e1e8ac1bf56e284c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mWMSHWxrM/WHeWRjIr5pP27q/goyxgDvbAcRS6JLpoiSvFKa/qJun57EV3JyVdEx2ltVauRrtdOYVyrbe5ENCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T06:15:09.686165Z","bundle_sha256":"90c52de2c2e9969997499afc86cfb5d381d561bb95392f80cb37f303a8c9d933"}}