{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UXLD5G6P2VS3IDQIPNNU7V7N5H","short_pith_number":"pith:UXLD5G6P","canonical_record":{"source":{"id":"2504.15918","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T14:03:16Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"61b7d927093d29a03c24355b4dae101ca1356407f6f16b3fe994ad796d333ef7","abstract_canon_sha256":"8b5e533a322d8ca2a07e730d95dd2a7e0bf014f5cb4c823bc382abbe423cb834"},"schema_version":"1.0"},"canonical_sha256":"a5d63e9bcfd565b40e087b5b4fd7ede9dd60e229add2237a6018e356d3b89034","source":{"kind":"arxiv","id":"2504.15918","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15918","created_at":"2026-07-05T10:52:40Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15918v2","created_at":"2026-07-05T10:52:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15918","created_at":"2026-07-05T10:52:40Z"},{"alias_kind":"pith_short_12","alias_value":"UXLD5G6P2VS3","created_at":"2026-07-05T10:52:40Z"},{"alias_kind":"pith_short_16","alias_value":"UXLD5G6P2VS3IDQI","created_at":"2026-07-05T10:52:40Z"},{"alias_kind":"pith_short_8","alias_value":"UXLD5G6P","created_at":"2026-07-05T10:52:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UXLD5G6P2VS3IDQIPNNU7V7N5H","target":"record","payload":{"canonical_record":{"source":{"id":"2504.15918","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T14:03:16Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"61b7d927093d29a03c24355b4dae101ca1356407f6f16b3fe994ad796d333ef7","abstract_canon_sha256":"8b5e533a322d8ca2a07e730d95dd2a7e0bf014f5cb4c823bc382abbe423cb834"},"schema_version":"1.0"},"canonical_sha256":"a5d63e9bcfd565b40e087b5b4fd7ede9dd60e229add2237a6018e356d3b89034","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:40.912769Z","signature_b64":"5qMwqaCHgg+EGM3yQNY7lWPce6uMl9gfh9Mq9+B9yXfSz1cHGZvwv5SZMdb3umjkWp/EP8FoQAKgHgfmj/1/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5d63e9bcfd565b40e087b5b4fd7ede9dd60e229add2237a6018e356d3b89034","last_reissued_at":"2026-07-05T10:52:40.912267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:40.912267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.15918","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":"2026-07-05T10:52:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"487quvhGpowq5VcHibp/LpHAJyCwsRqkm2frCzjDEDQF6IOfMO29NtIIDYSYE4N+EOg3TwwT6oEq8HHrb3oXBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:37:33.103959Z"},"content_sha256":"98d336f7154a70604451a3e344681f470759ce340ffc2e7d853cb3374a2990ce","schema_version":"1.0","event_id":"sha256:98d336f7154a70604451a3e344681f470759ce340ffc2e7d853cb3374a2990ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UXLD5G6P2VS3IDQIPNNU7V7N5H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ask2Loc: Learning to Locate Instructional Visual Answers by Asking Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CV","authors_text":"Bin Li, Chang Zong, Jian Wan, Lei Zhang, Shoujun Zhou","submitted_at":"2025-04-22T14:03:16Z","abstract_excerpt":"Locating specific segments within an instructional video is an efficient way to acquire guiding knowledge. Generally, the task of obtaining video segments for both verbal explanations and visual demonstrations is known as visual answer localization (VAL). However, users often need multiple interactions to obtain answers that align with their expectations when using the system. During these interactions, humans deepen their understanding of the video content by asking themselves questions, thereby accurately identifying the location. Therefore, we propose a new task, named In-VAL, to simulate t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15918","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/2504.15918/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":"2026-07-05T10:52:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pTvTGxosRppNLvpDmy+ayj5vdseMzbLhV8TA8obh1hbOCczmj2o3FPDo66KEk3zehPErOgHghr8leMEk3PBBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:37:33.104696Z"},"content_sha256":"571eb5bf3e2cbb3cb7a4009f9d33b4e860c0e7a9a0480a9fc727c2fcf7bf23fb","schema_version":"1.0","event_id":"sha256:571eb5bf3e2cbb3cb7a4009f9d33b4e860c0e7a9a0480a9fc727c2fcf7bf23fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UXLD5G6P2VS3IDQIPNNU7V7N5H/bundle.json","state_url":"https://pith.science/pith/UXLD5G6P2VS3IDQIPNNU7V7N5H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UXLD5G6P2VS3IDQIPNNU7V7N5H/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":"2026-08-08T13:37:33Z","links":{"resolver":"https://pith.science/pith/UXLD5G6P2VS3IDQIPNNU7V7N5H","bundle":"https://pith.science/pith/UXLD5G6P2VS3IDQIPNNU7V7N5H/bundle.json","state":"https://pith.science/pith/UXLD5G6P2VS3IDQIPNNU7V7N5H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UXLD5G6P2VS3IDQIPNNU7V7N5H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UXLD5G6P2VS3IDQIPNNU7V7N5H","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":"8b5e533a322d8ca2a07e730d95dd2a7e0bf014f5cb4c823bc382abbe423cb834","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T14:03:16Z","title_canon_sha256":"61b7d927093d29a03c24355b4dae101ca1356407f6f16b3fe994ad796d333ef7"},"schema_version":"1.0","source":{"id":"2504.15918","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15918","created_at":"2026-07-05T10:52:40Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15918v2","created_at":"2026-07-05T10:52:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15918","created_at":"2026-07-05T10:52:40Z"},{"alias_kind":"pith_short_12","alias_value":"UXLD5G6P2VS3","created_at":"2026-07-05T10:52:40Z"},{"alias_kind":"pith_short_16","alias_value":"UXLD5G6P2VS3IDQI","created_at":"2026-07-05T10:52:40Z"},{"alias_kind":"pith_short_8","alias_value":"UXLD5G6P","created_at":"2026-07-05T10:52:40Z"}],"graph_snapshots":[{"event_id":"sha256:571eb5bf3e2cbb3cb7a4009f9d33b4e860c0e7a9a0480a9fc727c2fcf7bf23fb","target":"graph","created_at":"2026-07-05T10:52:40Z","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/2504.15918/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Locating specific segments within an instructional video is an efficient way to acquire guiding knowledge. Generally, the task of obtaining video segments for both verbal explanations and visual demonstrations is known as visual answer localization (VAL). However, users often need multiple interactions to obtain answers that align with their expectations when using the system. During these interactions, humans deepen their understanding of the video content by asking themselves questions, thereby accurately identifying the location. Therefore, we propose a new task, named In-VAL, to simulate t","authors_text":"Bin Li, Chang Zong, Jian Wan, Lei Zhang, Shoujun Zhou","cross_cats":["cs.AI","cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T14:03:16Z","title":"Ask2Loc: Learning to Locate Instructional Visual Answers by Asking Questions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15918","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":"sha256:98d336f7154a70604451a3e344681f470759ce340ffc2e7d853cb3374a2990ce","target":"record","created_at":"2026-07-05T10:52:40Z","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":"8b5e533a322d8ca2a07e730d95dd2a7e0bf014f5cb4c823bc382abbe423cb834","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T14:03:16Z","title_canon_sha256":"61b7d927093d29a03c24355b4dae101ca1356407f6f16b3fe994ad796d333ef7"},"schema_version":"1.0","source":{"id":"2504.15918","kind":"arxiv","version":2}},"canonical_sha256":"a5d63e9bcfd565b40e087b5b4fd7ede9dd60e229add2237a6018e356d3b89034","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5d63e9bcfd565b40e087b5b4fd7ede9dd60e229add2237a6018e356d3b89034","first_computed_at":"2026-07-05T10:52:40.912267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:40.912267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5qMwqaCHgg+EGM3yQNY7lWPce6uMl9gfh9Mq9+B9yXfSz1cHGZvwv5SZMdb3umjkWp/EP8FoQAKgHgfmj/1/BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:40.912769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.15918","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98d336f7154a70604451a3e344681f470759ce340ffc2e7d853cb3374a2990ce","sha256:571eb5bf3e2cbb3cb7a4009f9d33b4e860c0e7a9a0480a9fc727c2fcf7bf23fb"],"state_sha256":"3bc786fb539f310c64c0db7d8183d665d26b7bdacead930db21cac65f20ddaa4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WXYmWdlJx9VTysTuD6kAIcau3yvAC5qB1AHEW/LhpbQyfIQJHDrEY2bGUP2miFIFtGWHB1fHDiw0cIYm3RqPAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:37:33.110776Z","bundle_sha256":"e35053e31a1ae1b5e35b44effb090c249456f4cf6cc06fefaeda90c58bc4d31e"}}