{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:REABV55U73TKNJLGJVKULLXHHE","short_pith_number":"pith:REABV55U","canonical_record":{"source":{"id":"2512.01334","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-01T06:53:48Z","cross_cats_sorted":[],"title_canon_sha256":"33027f18e5a31748129e325cf52b989c0155f0248fd0f1c8fec5d1f98439e7cd","abstract_canon_sha256":"603f0d5a544a36255b9635a0cad31edbe881df785044597a04230c6516170ca9"},"schema_version":"1.0"},"canonical_sha256":"89001af7b4fee6a6a5664d5545aee7390586bf7b67c286a621ba4e658fe56c34","source":{"kind":"arxiv","id":"2512.01334","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.01334","created_at":"2026-05-29T01:04:59Z"},{"alias_kind":"arxiv_version","alias_value":"2512.01334v2","created_at":"2026-05-29T01:04:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.01334","created_at":"2026-05-29T01:04:59Z"},{"alias_kind":"pith_short_12","alias_value":"REABV55U73TK","created_at":"2026-05-29T01:04:59Z"},{"alias_kind":"pith_short_16","alias_value":"REABV55U73TKNJLG","created_at":"2026-05-29T01:04:59Z"},{"alias_kind":"pith_short_8","alias_value":"REABV55U","created_at":"2026-05-29T01:04:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:REABV55U73TKNJLGJVKULLXHHE","target":"record","payload":{"canonical_record":{"source":{"id":"2512.01334","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-01T06:53:48Z","cross_cats_sorted":[],"title_canon_sha256":"33027f18e5a31748129e325cf52b989c0155f0248fd0f1c8fec5d1f98439e7cd","abstract_canon_sha256":"603f0d5a544a36255b9635a0cad31edbe881df785044597a04230c6516170ca9"},"schema_version":"1.0"},"canonical_sha256":"89001af7b4fee6a6a5664d5545aee7390586bf7b67c286a621ba4e658fe56c34","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:59.265355Z","signature_b64":"XjxhiwOoUIHVPktjETH0OrgCIazNsVJNgS3vytPxQPvIPCpptXbfgd9QLPCDplPp75z9qafKldPEYc3MIIthDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89001af7b4fee6a6a5664d5545aee7390586bf7b67c286a621ba4e658fe56c34","last_reissued_at":"2026-05-29T01:04:59.264465Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:59.264465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.01334","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":"2026-05-29T01:04:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UqQJMGPWmXu3kCTJtLr6J9fLQRDMma2zJSgU1XEeN+fbPqzwspKOoRyj4re4Jz+YVcR4vuqJDwpcpqQaYIs1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:52:47.237332Z"},"content_sha256":"792a6d4096aff7bdb8044997225aeed0a7bcc11e8a9caa606a3b8b7355334787","schema_version":"1.0","event_id":"sha256:792a6d4096aff7bdb8044997225aeed0a7bcc11e8a9caa606a3b8b7355334787"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:REABV55U73TKNJLGJVKULLXHHE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoze Zheng, Harry Yang, Jingjin Zhu, Manyuan Zhang, Ser-Nam Lim, Wen-Jie Shu, Yexin Liu, Yueze Wang, Zile Huang","submitted_at":"2025-12-01T06:53:48Z","abstract_excerpt":"Text-guided image-to-video generation has made substantial progress, yet it still struggles to execute text-specified edits that require substantial changes to a reference image (\\textit{e.g., object addition, removal, or modification}). Empirically, our analysis reveals that this stems from \\textbf{visual dominance}, where the reference image causes severe attention dispersion, inhibiting the model's ability to incorporate new semantic information. To address this, we propose \\textbf{AlignVid}, a training-free intervention that re-calibrates the model's internal attention distribution. Drawin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.01334","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/2512.01334/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":"2026-05-29T01:04:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v/I48oHmSHdC1duon5wiaSQDRbGaDFSa+zUmLUEnv6chTcElFrwSvBS4M4pj2+JqUj4Xo8bVo9w/1ld1UsWNCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:52:47.237965Z"},"content_sha256":"f53212a5f907e6bc351774d7cc0e24ba2aa3b1d83e976632bc633360241e656c","schema_version":"1.0","event_id":"sha256:f53212a5f907e6bc351774d7cc0e24ba2aa3b1d83e976632bc633360241e656c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/REABV55U73TKNJLGJVKULLXHHE/bundle.json","state_url":"https://pith.science/pith/REABV55U73TKNJLGJVKULLXHHE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/REABV55U73TKNJLGJVKULLXHHE/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":"2026-05-30T16:52:47Z","links":{"resolver":"https://pith.science/pith/REABV55U73TKNJLGJVKULLXHHE","bundle":"https://pith.science/pith/REABV55U73TKNJLGJVKULLXHHE/bundle.json","state":"https://pith.science/pith/REABV55U73TKNJLGJVKULLXHHE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/REABV55U73TKNJLGJVKULLXHHE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:REABV55U73TKNJLGJVKULLXHHE","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":"603f0d5a544a36255b9635a0cad31edbe881df785044597a04230c6516170ca9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-01T06:53:48Z","title_canon_sha256":"33027f18e5a31748129e325cf52b989c0155f0248fd0f1c8fec5d1f98439e7cd"},"schema_version":"1.0","source":{"id":"2512.01334","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.01334","created_at":"2026-05-29T01:04:59Z"},{"alias_kind":"arxiv_version","alias_value":"2512.01334v2","created_at":"2026-05-29T01:04:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.01334","created_at":"2026-05-29T01:04:59Z"},{"alias_kind":"pith_short_12","alias_value":"REABV55U73TK","created_at":"2026-05-29T01:04:59Z"},{"alias_kind":"pith_short_16","alias_value":"REABV55U73TKNJLG","created_at":"2026-05-29T01:04:59Z"},{"alias_kind":"pith_short_8","alias_value":"REABV55U","created_at":"2026-05-29T01:04:59Z"}],"graph_snapshots":[{"event_id":"sha256:f53212a5f907e6bc351774d7cc0e24ba2aa3b1d83e976632bc633360241e656c","target":"graph","created_at":"2026-05-29T01:04:59Z","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/2512.01334/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-guided image-to-video generation has made substantial progress, yet it still struggles to execute text-specified edits that require substantial changes to a reference image (\\textit{e.g., object addition, removal, or modification}). Empirically, our analysis reveals that this stems from \\textbf{visual dominance}, where the reference image causes severe attention dispersion, inhibiting the model's ability to incorporate new semantic information. To address this, we propose \\textbf{AlignVid}, a training-free intervention that re-calibrates the model's internal attention distribution. Drawin","authors_text":"Haoze Zheng, Harry Yang, Jingjin Zhu, Manyuan Zhang, Ser-Nam Lim, Wen-Jie Shu, Yexin Liu, Yueze Wang, Zile Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-01T06:53:48Z","title":"AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.01334","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":"sha256:792a6d4096aff7bdb8044997225aeed0a7bcc11e8a9caa606a3b8b7355334787","target":"record","created_at":"2026-05-29T01:04:59Z","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":"603f0d5a544a36255b9635a0cad31edbe881df785044597a04230c6516170ca9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-01T06:53:48Z","title_canon_sha256":"33027f18e5a31748129e325cf52b989c0155f0248fd0f1c8fec5d1f98439e7cd"},"schema_version":"1.0","source":{"id":"2512.01334","kind":"arxiv","version":2}},"canonical_sha256":"89001af7b4fee6a6a5664d5545aee7390586bf7b67c286a621ba4e658fe56c34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89001af7b4fee6a6a5664d5545aee7390586bf7b67c286a621ba4e658fe56c34","first_computed_at":"2026-05-29T01:04:59.264465Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:04:59.264465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XjxhiwOoUIHVPktjETH0OrgCIazNsVJNgS3vytPxQPvIPCpptXbfgd9QLPCDplPp75z9qafKldPEYc3MIIthDw==","signature_status":"signed_v1","signed_at":"2026-05-29T01:04:59.265355Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.01334","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:792a6d4096aff7bdb8044997225aeed0a7bcc11e8a9caa606a3b8b7355334787","sha256:f53212a5f907e6bc351774d7cc0e24ba2aa3b1d83e976632bc633360241e656c"],"state_sha256":"ff087bc08e6753569e7b8b23b27082ccc77fed18dd1ee7a3f4f6284060e58ce3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QZvDCzbu5PMN93xaagWZ1OZt9+CiTRAs6Xzvuaof6Ab9+yCqD5e/5wT7xrni5eabRiSgmeqxfouBwqY/m68mCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T16:52:47.241417Z","bundle_sha256":"170cb37eaee85cea89594c965cb71f4bc9d942dc6f808fa052d878db843905e9"}}