{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:P4PGKQ7OOD3RH5272GOIB45EHW","short_pith_number":"pith:P4PGKQ7O","canonical_record":{"source":{"id":"2503.16867","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T05:52:50Z","cross_cats_sorted":[],"title_canon_sha256":"209acfdd3ae5ac5eab1b71881e82920e98aa4b3fa1d1e0922fe5590679986ba7","abstract_canon_sha256":"bc6649fcdbb3f04ac8cecc9c4f4eea586f95ef9923c4f6fb2f1ae8628921ee3e"},"schema_version":"1.0"},"canonical_sha256":"7f1e6543ee70f713f75fd19c80f3a43db7fe957bdbb76d60b7cb8fb8e7af61b0","source":{"kind":"arxiv","id":"2503.16867","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.16867","created_at":"2026-07-05T11:54:45Z"},{"alias_kind":"arxiv_version","alias_value":"2503.16867v2","created_at":"2026-07-05T11:54:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16867","created_at":"2026-07-05T11:54:45Z"},{"alias_kind":"pith_short_12","alias_value":"P4PGKQ7OOD3R","created_at":"2026-07-05T11:54:45Z"},{"alias_kind":"pith_short_16","alias_value":"P4PGKQ7OOD3RH527","created_at":"2026-07-05T11:54:45Z"},{"alias_kind":"pith_short_8","alias_value":"P4PGKQ7O","created_at":"2026-07-05T11:54:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:P4PGKQ7OOD3RH5272GOIB45EHW","target":"record","payload":{"canonical_record":{"source":{"id":"2503.16867","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T05:52:50Z","cross_cats_sorted":[],"title_canon_sha256":"209acfdd3ae5ac5eab1b71881e82920e98aa4b3fa1d1e0922fe5590679986ba7","abstract_canon_sha256":"bc6649fcdbb3f04ac8cecc9c4f4eea586f95ef9923c4f6fb2f1ae8628921ee3e"},"schema_version":"1.0"},"canonical_sha256":"7f1e6543ee70f713f75fd19c80f3a43db7fe957bdbb76d60b7cb8fb8e7af61b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:45.531423Z","signature_b64":"BXRzkR1wKI11JqwVbfPaQ7CdzG0cBdZhFMhdR1nYmOFobzwJv41AFOhjQxS41HLTe90udkZZ80plLMeNmiBmDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f1e6543ee70f713f75fd19c80f3a43db7fe957bdbb76d60b7cb8fb8e7af61b0","last_reissued_at":"2026-07-05T11:54:45.530832Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:45.530832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.16867","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:54:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OQOdZIcXuhCth9KVGhDAfwq4p8y9z80/IMojNj8kz/BQuXTz+vcgd5yBIf1f87WJAkOMbkyLYDoDz5vHTLcgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:38:49.811786Z"},"content_sha256":"641d1c6c20119e93a8ede25063b22f8292fe828bd5a798d41688e0ce3686f41f","schema_version":"1.0","event_id":"sha256:641d1c6c20119e93a8ede25063b22f8292fe828bd5a798d41688e0ce3686f41f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:P4PGKQ7OOD3RH5272GOIB45EHW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaisi Guan, Kieran Liu, Meng Cao, Peng Zhang, Ruihua Song, Wei Liu, Yuchong Sun, Zhengfeng Lai","submitted_at":"2025-03-21T05:52:50Z","abstract_excerpt":"Precisely evaluating semantic alignment between text prompts and generated videos remains a challenge in Text-to-Video (T2V) Generation. Existing text-to-video alignment metrics like CLIPScore only generate coarse-grained scores without fine-grained alignment details, failing to align with human preference. To address this limitation, we propose ETVA, a novel Evaluation method of Text-to-Video Alignment via fine-grained question generation and answering. First, a multi-agent system parses prompts into semantic scene graphs to generate atomic questions. Then we design a knowledge-augmented mult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16867","kind":"arxiv","version":2},"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/2503.16867/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":"2026-07-05T11:54:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MK9NnLQPiXubmn6OVP0Z0043TM/DdaJFKIi2fNMhCgjzAhXfEA8mCAJsTrCGYWhkUYL9Lw85LmS1gZ4AmyhBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:38:49.812607Z"},"content_sha256":"bcbbac9fa0d4563f775b58a241b3e5f05e362efa7d61f805696f921723f808f7","schema_version":"1.0","event_id":"sha256:bcbbac9fa0d4563f775b58a241b3e5f05e362efa7d61f805696f921723f808f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P4PGKQ7OOD3RH5272GOIB45EHW/bundle.json","state_url":"https://pith.science/pith/P4PGKQ7OOD3RH5272GOIB45EHW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P4PGKQ7OOD3RH5272GOIB45EHW/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":"2026-08-09T12:38:49Z","links":{"resolver":"https://pith.science/pith/P4PGKQ7OOD3RH5272GOIB45EHW","bundle":"https://pith.science/pith/P4PGKQ7OOD3RH5272GOIB45EHW/bundle.json","state":"https://pith.science/pith/P4PGKQ7OOD3RH5272GOIB45EHW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P4PGKQ7OOD3RH5272GOIB45EHW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P4PGKQ7OOD3RH5272GOIB45EHW","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":"bc6649fcdbb3f04ac8cecc9c4f4eea586f95ef9923c4f6fb2f1ae8628921ee3e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T05:52:50Z","title_canon_sha256":"209acfdd3ae5ac5eab1b71881e82920e98aa4b3fa1d1e0922fe5590679986ba7"},"schema_version":"1.0","source":{"id":"2503.16867","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.16867","created_at":"2026-07-05T11:54:45Z"},{"alias_kind":"arxiv_version","alias_value":"2503.16867v2","created_at":"2026-07-05T11:54:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16867","created_at":"2026-07-05T11:54:45Z"},{"alias_kind":"pith_short_12","alias_value":"P4PGKQ7OOD3R","created_at":"2026-07-05T11:54:45Z"},{"alias_kind":"pith_short_16","alias_value":"P4PGKQ7OOD3RH527","created_at":"2026-07-05T11:54:45Z"},{"alias_kind":"pith_short_8","alias_value":"P4PGKQ7O","created_at":"2026-07-05T11:54:45Z"}],"graph_snapshots":[{"event_id":"sha256:bcbbac9fa0d4563f775b58a241b3e5f05e362efa7d61f805696f921723f808f7","target":"graph","created_at":"2026-07-05T11:54:45Z","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/2503.16867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Precisely evaluating semantic alignment between text prompts and generated videos remains a challenge in Text-to-Video (T2V) Generation. Existing text-to-video alignment metrics like CLIPScore only generate coarse-grained scores without fine-grained alignment details, failing to align with human preference. To address this limitation, we propose ETVA, a novel Evaluation method of Text-to-Video Alignment via fine-grained question generation and answering. First, a multi-agent system parses prompts into semantic scene graphs to generate atomic questions. Then we design a knowledge-augmented mult","authors_text":"Kaisi Guan, Kieran Liu, Meng Cao, Peng Zhang, Ruihua Song, Wei Liu, Yuchong Sun, Zhengfeng Lai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T05:52:50Z","title":"ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16867","kind":"arxiv","version":2},"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":"sha256:641d1c6c20119e93a8ede25063b22f8292fe828bd5a798d41688e0ce3686f41f","target":"record","created_at":"2026-07-05T11:54:45Z","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":"bc6649fcdbb3f04ac8cecc9c4f4eea586f95ef9923c4f6fb2f1ae8628921ee3e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T05:52:50Z","title_canon_sha256":"209acfdd3ae5ac5eab1b71881e82920e98aa4b3fa1d1e0922fe5590679986ba7"},"schema_version":"1.0","source":{"id":"2503.16867","kind":"arxiv","version":2}},"canonical_sha256":"7f1e6543ee70f713f75fd19c80f3a43db7fe957bdbb76d60b7cb8fb8e7af61b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f1e6543ee70f713f75fd19c80f3a43db7fe957bdbb76d60b7cb8fb8e7af61b0","first_computed_at":"2026-07-05T11:54:45.530832Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:45.530832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BXRzkR1wKI11JqwVbfPaQ7CdzG0cBdZhFMhdR1nYmOFobzwJv41AFOhjQxS41HLTe90udkZZ80plLMeNmiBmDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:45.531423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.16867","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:641d1c6c20119e93a8ede25063b22f8292fe828bd5a798d41688e0ce3686f41f","sha256:bcbbac9fa0d4563f775b58a241b3e5f05e362efa7d61f805696f921723f808f7"],"state_sha256":"7074847958d87be5b1e0be1491a605e3916a27cf61302ef00cc1766ca01d923e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3yCO6UIj/cl3a6vDI+C9EmBflLWJG288a++ORz39nP6CxGE5q5sFfIB1RGrMtWJBtdSPrfY252F6svG9LhApAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T12:38:49.818175Z","bundle_sha256":"06f84bba004aaf3de9e2d955bebbe23aefdf582f06880bc22b8622a7518d00f8"}}